diff --git a/Heat sink defect detection/dataset/README.md b/Heat sink defect detection/dataset/README.md
new file mode 100644
index 000000000..4ef4b43f3
--- /dev/null
+++ b/Heat sink defect detection/dataset/README.md	
@@ -0,0 +1 @@
+### Dataset Link : https://www.kaggle.com/datasets/kaifengyang/heat-sink-surface-defect-dataset
\ No newline at end of file
diff --git a/Heat sink defect detection/images/01.png b/Heat sink defect detection/images/01.png
new file mode 100644
index 000000000..3120b7867
Binary files /dev/null and b/Heat sink defect detection/images/01.png differ
diff --git a/Heat sink defect detection/images/02.png b/Heat sink defect detection/images/02.png
new file mode 100644
index 000000000..945ef9ec7
Binary files /dev/null and b/Heat sink defect detection/images/02.png differ
diff --git a/Heat sink defect detection/images/03.png b/Heat sink defect detection/images/03.png
new file mode 100644
index 000000000..1b1472edf
Binary files /dev/null and b/Heat sink defect detection/images/03.png differ
diff --git a/Heat sink defect detection/images/04.png b/Heat sink defect detection/images/04.png
new file mode 100644
index 000000000..eb515d570
Binary files /dev/null and b/Heat sink defect detection/images/04.png differ
diff --git a/Heat sink defect detection/images/05.png b/Heat sink defect detection/images/05.png
new file mode 100644
index 000000000..223ce1a7f
Binary files /dev/null and b/Heat sink defect detection/images/05.png differ
diff --git a/Heat sink defect detection/images/06.png b/Heat sink defect detection/images/06.png
new file mode 100644
index 000000000..ee66c0663
Binary files /dev/null and b/Heat sink defect detection/images/06.png differ
diff --git a/Heat sink defect detection/model/README.md b/Heat sink defect detection/model/README.md
new file mode 100644
index 000000000..839399359
--- /dev/null
+++ b/Heat sink defect detection/model/README.md	
@@ -0,0 +1,26 @@
+**HEAT SINK DEFECT DETECTION**
+
+**GOAL**
+
+To detect stains and scratches on the given heat sink images.
+
+**DATASET**
+
+https://www.kaggle.com/datasets/kaifengyang/heat-sink-surface-defect-dataset
+
+**DESCRIPTION**
+
+This project aims to develop a robust defect detection system utilizing U-Net architecture models, an effective neural network design for image segmentation tasks. By harnessing deep learning techniques, this project strives to accurately identify and localize defects within heat sinks.
+
+
+**MODELS USED**
+
+U-net - U-Net, a deep learning architecture, excels in image segmentation tasks. Its unique design incorporates encoder-decoder pathways, ideal for precise localization, widely applied in medical imaging and object detection.
+
+Resnet50 - ResNet-50 is a 50-layer convolutional neural network (48 convolutional layers, one MaxPool layer, and one average pool layer). Residual neural networks are a type of artificial neural network (ANN) that forms networks by stacking residual blocks. It excels in image recognition tasks, offering high accuracy and efficiency in deep learning models.
+
+Vgg16 - VGG16 is a deep convolutional neural network renowned for its 16 layers, characterized by a simple yet effective architecture. Its design, with small receptive fields and stacked layers, excels in image classification tasks, making it a popular choice for feature extraction and transfer learning in computer vision applications.
+
+**ACCURACIES**
+
+All 3 models gave accuracies of 97.8% on training upon 40 epochs of batch size 32.
diff --git a/Heat sink defect detection/model/model.ipynb b/Heat sink defect detection/model/model.ipynb
new file mode 100644
index 000000000..ac962ea19
--- /dev/null
+++ b/Heat sink defect detection/model/model.ipynb	
@@ -0,0 +1,1777 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": 79,
+   "id": "f6b2653b",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "#importing the necessary libraries\n",
+    "import numpy as np\n",
+    "import tensorflow as tf\n",
+    "import keras\n",
+    "import os\n",
+    "import matplotlib.pyplot as plt\n",
+    "%matplotlib inline\n",
+    "import imageio\n",
+    "from sklearn.model_selection import train_test_split\n",
+    "from collections import Counter\n",
+    "\n",
+    "from tensorflow.keras.layers import Input\n",
+    "from tensorflow.keras.layers import Conv2D\n",
+    "from tensorflow.keras.layers import MaxPooling2D\n",
+    "from tensorflow.keras.layers import Dropout \n",
+    "from tensorflow.keras.layers import Conv2DTranspose\n",
+    "from tensorflow.keras.layers import concatenate\n",
+    "\n",
+    "import pandas as pd\n",
+    "import seaborn as sns\n",
+    "from sklearn.metrics import confusion_matrix"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 46,
+   "id": "242aa3ac",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "#making image and mask lists from the kaggle dataset\n",
+    "image_list = os.listdir('heat_sink_defect_detection/Heat_Sink_Surface_Defect_Dataset/images')\n",
+    "mask_list = os.listdir('heat_sink_defect_detection/Heat_Sink_Surface_Defect_Dataset/labels')\n",
+    "image_list = ['heat_sink_defect_detection/Heat_Sink_Surface_Defect_Dataset/images/'+i for i in image_list]\n",
+    "mask_list = ['heat_sink_defect_detection/Heat_Sink_Surface_Defect_Dataset/labels/'+i for i in mask_list]"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 49,
+   "id": "bf64a8a1",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "Text(0.5, 1.0, 'Mask')"
+      ]
+     },
+     "execution_count": 49,
+     "metadata": {},
+     "output_type": "execute_result"
+    },
+    {
+     "data": {
+      "image/png": "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",
+      "text/plain": [
+       "<Figure size 1000x1000 with 2 Axes>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "N = 100 #no. of images to read\n",
+    "img = imageio.v3.imread(image_list[N])\n",
+    "mask = imageio.v3.imread(mask_list[N])\n",
+    "\n",
+    "#plotting image and corresponding mask\n",
+    "fig, arr = plt.subplots(1, 2, figsize=(10, 10))\n",
+    "arr[0].imshow(img)\n",
+    "arr[0].set_title('Image')\n",
+    "arr[1].imshow(mask)\n",
+    "arr[1].set_title('Mask')"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 76,
+   "id": "48a5a62c",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "mask_mat = np.zeros([320, 320, 1000])         \n",
+    "for i, mask in enumerate(mask_list):\n",
+    "    m = tf.io.read_file(mask)                 #reading mask png files\n",
+    "    m = tf.image.decode_png(m, channels=3)    #decoding png to tensor\n",
+    "    mask_mat[:, :, i] = tf.squeeze(tf.math.reduce_max(m, axis=-1, keepdims=True)) #dimensionality reduction of tensor\n",
+    "    \n",
+    "y = np.unique(mask_mat, return_counts = True)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 77,
+   "id": "ac50e6c0",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "image/png": "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",
+      "text/plain": [
+       "<Figure size 640x480 with 1 Axes>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "labels = 'Background (Defect-Free)', 'Scratch', 'Stain'\n",
+    "sizes = [99357441, 1333995, 1708564]    #obtained from values from above calculation\n",
+    "\n",
+    "fig1, ax1 = plt.subplots()\n",
+    "ax1.pie(sizes, labels=labels, autopct='%1.1f%%')\n",
+    "ax1.axis('equal')\n",
+    "\n",
+    "ax1.set_title(\"Pixel Composition of All Images\")\n",
+    "\n",
+    "plt.show()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 78,
+   "id": "7ada9be5",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "Counter({(0.0, 1.0, 2.0): 672, (0.0, 2.0): 300, (0.0, 1.0): 28})"
+      ]
+     },
+     "execution_count": 78,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "mask_mat_re = np.reshape(mask_mat, (-1, 1000)) #reshaped the last dimension of dataset\n",
+    "\n",
+    "mask_unique = []\n",
+    "\n",
+    "for i in range(1000):\n",
+    "    mask_unique.append(tuple(set(mask_mat_re[:, i])))\n",
+    "    \n",
+    "Counter(mask_unique)\n",
+    "\n",
+    "#(0.0, 1.0, 2.0) represent heat sink with scratch and stains\n",
+    "#(0.0, 2.0) represent heat sink with stains\n",
+    "#(0.0, 1.0) represent heat sink with scratches"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 54,
+   "id": "497e0e40",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "x_train, x_test, y_train, y_test = train_test_split(image_list,mask_list,test_size=0.3,random_state=30)\n",
+    "x_val, x_test, y_val, y_test = train_test_split(x_test, y_test, test_size=0.5, random_state=30)\n",
+    "#dataset is split into 70:15:15 (train:val:test)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 55,
+   "id": "3c1eba2f",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "#converting all splits to a constant tensor\n",
+    "image_train = tf.constant(x_train)\n",
+    "masks_train =  tf.constant(y_train)\n",
+    "image_val = tf.constant(x_val)\n",
+    "masks_val = tf.constant(y_val)\n",
+    "image_test = tf.constant(x_test)\n",
+    "masks_test = tf.constant(y_test)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 56,
+   "id": "030eabb0",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "#preparation of dataset by merging image and masks of corresponding splits\n",
+    "dataset_train = tf.data.Dataset.from_tensor_slices((image_train,masks_train))\n",
+    "dataset_val = tf.data.Dataset.from_tensor_slices((image_val, masks_val))\n",
+    "dataset_test = tf.data.Dataset.from_tensor_slices((image_test, masks_test))"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 14,
+   "id": "ed157d50",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "def process_path(image_path, mask_path):\n",
+    "    img = tf.io.read_file(image_path)                         #reading the image file path\n",
+    "    img = tf.image.decode_bmp(img, channels=3)                #conversion of bmp to tensor\n",
+    "    img = tf.image.convert_image_dtype(img, tf.float32)       #converting tensor to image\n",
+    "\n",
+    "    mask = tf.io.read_file(mask_path)\n",
+    "    mask = tf.image.decode_png(mask, channels=3)\n",
+    "    mask = tf.math.reduce_max(mask, axis=-1, keepdims=True)  #dimension reduction\n",
+    "    return img, mask\n",
+    "\n",
+    "def preprocess(image, mask):\n",
+    "    #resizing image and masks\n",
+    "    input_image = tf.image.resize(image, (256, 256), method='nearest')\n",
+    "    input_mask = tf.image.resize(mask, (256, 256), method='nearest')\n",
+    "    return input_image, input_mask\n",
+    "\n",
+    "#applying the above functions to train,val and test datasets\n",
+    "processed_ds_train = dataset_train.map(process_path).map(preprocess)\n",
+    "processed_ds_val = dataset_val.map(process_path).map(preprocess)\n",
+    "processed_ds_test = dataset_test.map(process_path).map(preprocess)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "9c92e100",
+   "metadata": {},
+   "source": [
+    "## U-Net"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "e6a7cd7f",
+   "metadata": {},
+   "source": [
+    "## Contracting Block"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 18,
+   "id": "889e57cb",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "#architecture for contracting block\n",
+    "def conv_block(inputs=None, n_filters=32, dropout_prob=0, max_pooling=True):\n",
+    "    conv = Conv2D(n_filters,3,activation='relu',padding='same',kernel_initializer='he_normal')(inputs)\n",
+    "    conv = Conv2D(n_filters,3,activation='relu',padding='same',kernel_initializer='he_normal')(conv)\n",
+    "    \n",
+    "    if dropout_prob > 0:\n",
+    "        conv = Dropout(dropout_prob)(conv)\n",
+    "    \n",
+    "    if max_pooling:\n",
+    "        next_layer = MaxPooling2D((2,2))(conv)\n",
+    "    else:\n",
+    "        next_layer = conv\n",
+    "    \n",
+    "    skip_connection = conv\n",
+    "    \n",
+    "    return next_layer, skip_connection"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "d2de8a1e",
+   "metadata": {},
+   "source": [
+    "## Upsampling block"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 20,
+   "id": "d771baf6",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "#architecture for upsampling block\n",
+    "def upsampling_block(expansive_input, contractive_input, n_filters=32):\n",
+    "\n",
+    "    up = Conv2DTranspose(\n",
+    "                 n_filters,\n",
+    "                 (3,3),\n",
+    "                 strides=(2,2),\n",
+    "                 padding='same')(expansive_input)\n",
+    "\n",
+    "    merge = concatenate([up, contractive_input], axis=3)\n",
+    "    \n",
+    "    conv = Conv2D(n_filters,\n",
+    "                 3,\n",
+    "                 activation='relu',\n",
+    "                 padding='same',\n",
+    "                 kernel_initializer='he_normal')(merge)\n",
+    "    conv = Conv2D(n_filters,\n",
+    "                 3,\n",
+    "                 activation='relu',\n",
+    "                 padding='same',\n",
+    "                 kernel_initializer='he_normal')(conv)\n",
+    "    \n",
+    "    return conv"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 21,
+   "id": "77e5e4ca",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "#adding the model blocks\n",
+    "def unet_model(input_size=(256, 256, 3), n_filters=32, n_classes=3):\n",
+    "\n",
+    "    inputs = Input(input_size)\n",
+    "    # Contracting Path (encoding)\n",
+    "    cblock1 = conv_block(inputs, n_filters)\n",
+    "    cblock2 = conv_block(cblock1[0], 2*n_filters)\n",
+    "    cblock3 = conv_block(cblock2[0], 4*n_filters)\n",
+    "    cblock4 = conv_block(cblock3[0], 8*n_filters, dropout_prob=0.3)\n",
+    "    cblock5 = conv_block(cblock4[0], 16*n_filters, dropout_prob=0.3, max_pooling=False) \n",
+    "    \n",
+    "    # Expanding Path (decoding)\n",
+    "    ublock6 = upsampling_block(cblock5[0], cblock4[1],  8*n_filters)\n",
+    "    ublock7 = upsampling_block(ublock6, cblock3[1],  4*n_filters)\n",
+    "    ublock8 = upsampling_block(ublock7, cblock2[1],  2*n_filters)\n",
+    "    ublock9 = upsampling_block(ublock8, cblock1[1],  n_filters)\n",
+    "\n",
+    "    conv9 = Conv2D(n_filters,\n",
+    "                 3,\n",
+    "                 activation='relu',\n",
+    "                 padding='same',\n",
+    "                 kernel_initializer='he_normal')(ublock9)\n",
+    "\n",
+    "    conv10 = Conv2D(n_classes, 1, padding='same')(conv9)\n",
+    "    \n",
+    "    model = tf.keras.Model(inputs=inputs, outputs=conv10)\n",
+    "    return model"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 22,
+   "id": "7aadebf8",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "WARNING:tensorflow:From D:\\anaconda3\\Lib\\site-packages\\keras\\src\\backend.py:1398: The name tf.executing_eagerly_outside_functions is deprecated. Please use tf.compat.v1.executing_eagerly_outside_functions instead.\n",
+      "\n",
+      "WARNING:tensorflow:From D:\\anaconda3\\Lib\\site-packages\\keras\\src\\layers\\pooling\\max_pooling2d.py:161: The name tf.nn.max_pool is deprecated. Please use tf.nn.max_pool2d instead.\n",
+      "\n",
+      "Model: \"model\"\n",
+      "__________________________________________________________________________________________________\n",
+      " Layer (type)                Output Shape                 Param #   Connected to                  \n",
+      "==================================================================================================\n",
+      " input_1 (InputLayer)        [(None, 256, 256, 3)]        0         []                            \n",
+      "                                                                                                  \n",
+      " conv2d (Conv2D)             (None, 256, 256, 32)         896       ['input_1[0][0]']             \n",
+      "                                                                                                  \n",
+      " conv2d_1 (Conv2D)           (None, 256, 256, 32)         9248      ['conv2d[0][0]']              \n",
+      "                                                                                                  \n",
+      " max_pooling2d (MaxPooling2  (None, 128, 128, 32)         0         ['conv2d_1[0][0]']            \n",
+      " D)                                                                                               \n",
+      "                                                                                                  \n",
+      " conv2d_2 (Conv2D)           (None, 128, 128, 64)         18496     ['max_pooling2d[0][0]']       \n",
+      "                                                                                                  \n",
+      " conv2d_3 (Conv2D)           (None, 128, 128, 64)         36928     ['conv2d_2[0][0]']            \n",
+      "                                                                                                  \n",
+      " max_pooling2d_1 (MaxPoolin  (None, 64, 64, 64)           0         ['conv2d_3[0][0]']            \n",
+      " g2D)                                                                                             \n",
+      "                                                                                                  \n",
+      " conv2d_4 (Conv2D)           (None, 64, 64, 128)          73856     ['max_pooling2d_1[0][0]']     \n",
+      "                                                                                                  \n",
+      " conv2d_5 (Conv2D)           (None, 64, 64, 128)          147584    ['conv2d_4[0][0]']            \n",
+      "                                                                                                  \n",
+      " max_pooling2d_2 (MaxPoolin  (None, 32, 32, 128)          0         ['conv2d_5[0][0]']            \n",
+      " g2D)                                                                                             \n",
+      "                                                                                                  \n",
+      " conv2d_6 (Conv2D)           (None, 32, 32, 256)          295168    ['max_pooling2d_2[0][0]']     \n",
+      "                                                                                                  \n",
+      " conv2d_7 (Conv2D)           (None, 32, 32, 256)          590080    ['conv2d_6[0][0]']            \n",
+      "                                                                                                  \n",
+      " dropout (Dropout)           (None, 32, 32, 256)          0         ['conv2d_7[0][0]']            \n",
+      "                                                                                                  \n",
+      " max_pooling2d_3 (MaxPoolin  (None, 16, 16, 256)          0         ['dropout[0][0]']             \n",
+      " g2D)                                                                                             \n",
+      "                                                                                                  \n",
+      " conv2d_8 (Conv2D)           (None, 16, 16, 512)          1180160   ['max_pooling2d_3[0][0]']     \n",
+      "                                                                                                  \n",
+      " conv2d_9 (Conv2D)           (None, 16, 16, 512)          2359808   ['conv2d_8[0][0]']            \n",
+      "                                                                                                  \n",
+      " dropout_1 (Dropout)         (None, 16, 16, 512)          0         ['conv2d_9[0][0]']            \n",
+      "                                                                                                  \n",
+      " conv2d_transpose (Conv2DTr  (None, 32, 32, 256)          1179904   ['dropout_1[0][0]']           \n",
+      " anspose)                                                                                         \n",
+      "                                                                                                  \n",
+      " concatenate (Concatenate)   (None, 32, 32, 512)          0         ['conv2d_transpose[0][0]',    \n",
+      "                                                                     'dropout[0][0]']             \n",
+      "                                                                                                  \n",
+      " conv2d_10 (Conv2D)          (None, 32, 32, 256)          1179904   ['concatenate[0][0]']         \n",
+      "                                                                                                  \n",
+      " conv2d_11 (Conv2D)          (None, 32, 32, 256)          590080    ['conv2d_10[0][0]']           \n",
+      "                                                                                                  \n",
+      " conv2d_transpose_1 (Conv2D  (None, 64, 64, 128)          295040    ['conv2d_11[0][0]']           \n",
+      " Transpose)                                                                                       \n",
+      "                                                                                                  \n",
+      " concatenate_1 (Concatenate  (None, 64, 64, 256)          0         ['conv2d_transpose_1[0][0]',  \n",
+      " )                                                                   'conv2d_5[0][0]']            \n",
+      "                                                                                                  \n",
+      " conv2d_12 (Conv2D)          (None, 64, 64, 128)          295040    ['concatenate_1[0][0]']       \n",
+      "                                                                                                  \n",
+      " conv2d_13 (Conv2D)          (None, 64, 64, 128)          147584    ['conv2d_12[0][0]']           \n",
+      "                                                                                                  \n",
+      " conv2d_transpose_2 (Conv2D  (None, 128, 128, 64)         73792     ['conv2d_13[0][0]']           \n",
+      " Transpose)                                                                                       \n",
+      "                                                                                                  \n",
+      " concatenate_2 (Concatenate  (None, 128, 128, 128)        0         ['conv2d_transpose_2[0][0]',  \n",
+      " )                                                                   'conv2d_3[0][0]']            \n",
+      "                                                                                                  \n",
+      " conv2d_14 (Conv2D)          (None, 128, 128, 64)         73792     ['concatenate_2[0][0]']       \n",
+      "                                                                                                  \n",
+      " conv2d_15 (Conv2D)          (None, 128, 128, 64)         36928     ['conv2d_14[0][0]']           \n",
+      "                                                                                                  \n",
+      " conv2d_transpose_3 (Conv2D  (None, 256, 256, 32)         18464     ['conv2d_15[0][0]']           \n",
+      " Transpose)                                                                                       \n",
+      "                                                                                                  \n",
+      " concatenate_3 (Concatenate  (None, 256, 256, 64)         0         ['conv2d_transpose_3[0][0]',  \n",
+      " )                                                                   'conv2d_1[0][0]']            \n",
+      "                                                                                                  \n",
+      " conv2d_16 (Conv2D)          (None, 256, 256, 32)         18464     ['concatenate_3[0][0]']       \n",
+      "                                                                                                  \n"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      " conv2d_17 (Conv2D)          (None, 256, 256, 32)         9248      ['conv2d_16[0][0]']           \n",
+      "                                                                                                  \n",
+      " conv2d_18 (Conv2D)          (None, 256, 256, 32)         9248      ['conv2d_17[0][0]']           \n",
+      "                                                                                                  \n",
+      " conv2d_19 (Conv2D)          (None, 256, 256, 3)          99        ['conv2d_18[0][0]']           \n",
+      "                                                                                                  \n",
+      "==================================================================================================\n",
+      "Total params: 8639811 (32.96 MB)\n",
+      "Trainable params: 8639811 (32.96 MB)\n",
+      "Non-trainable params: 0 (0.00 Byte)\n",
+      "__________________________________________________________________________________________________\n"
+     ]
+    }
+   ],
+   "source": [
+    "unet = unet_model((256, 256, 3), n_filters=32, n_classes=3)\n",
+    "unet.summary()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 23,
+   "id": "8c030055",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "WARNING:tensorflow:From D:\\anaconda3\\Lib\\site-packages\\keras\\src\\optimizers\\__init__.py:309: The name tf.train.Optimizer is deprecated. Please use tf.compat.v1.train.Optimizer instead.\n",
+      "\n"
+     ]
+    }
+   ],
+   "source": [
+    "unet.compile(optimizer='adam',\n",
+    "             loss = tf.keras.losses.SparseCategoricalCrossentropy(from_logits=True),\n",
+    "             metrics=['accuracy']\n",
+    "            )"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 57,
+   "id": "69afc965",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "train_dataset = processed_ds_train.batch(32)\n",
+    "# model_history = unet.fit(train_dataset, epochs=10)\n",
+    "# plt.plot(model_history.history[\"accuracy\"])\n",
+    "\n",
+    "\n",
+    "#train and save model to avoid any training time for future use"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 61,
+   "id": "311169e6",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# unet.save('model_1.h5')\n",
+    "unet = tf.keras.models.load_model('model_1.h5')"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 28,
+   "id": "45886007",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import segmentation_models as sm #importing pre-trained models"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 26,
+   "id": "6b7462ef",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "#if the above code block produces error, run this cell\n",
+    "import os            \n",
+    "os.environ[\"SM_FRAMEWORK\"] = \"tf.keras\""
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "4cb943c2",
+   "metadata": {},
+   "source": [
+    "## Resnet50"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 29,
+   "id": "aa8beff7",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Model: \"model_2\"\n",
+      "__________________________________________________________________________________________________\n",
+      " Layer (type)                Output Shape                 Param #   Connected to                  \n",
+      "==================================================================================================\n",
+      " data (InputLayer)           [(None, None, None, 3)]      0         []                            \n",
+      "                                                                                                  \n",
+      " bn_data (BatchNormalizatio  (None, None, None, 3)        9         ['data[0][0]']                \n",
+      " n)                                                                                               \n",
+      "                                                                                                  \n",
+      " zero_padding2d (ZeroPaddin  (None, None, None, 3)        0         ['bn_data[0][0]']             \n",
+      " g2D)                                                                                             \n",
+      "                                                                                                  \n",
+      " conv0 (Conv2D)              (None, None, None, 64)       9408      ['zero_padding2d[0][0]']      \n",
+      "                                                                                                  \n",
+      " bn0 (BatchNormalization)    (None, None, None, 64)       256       ['conv0[0][0]']               \n",
+      "                                                                                                  \n",
+      " relu0 (Activation)          (None, None, None, 64)       0         ['bn0[0][0]']                 \n",
+      "                                                                                                  \n",
+      " zero_padding2d_1 (ZeroPadd  (None, None, None, 64)       0         ['relu0[0][0]']               \n",
+      " ing2D)                                                                                           \n",
+      "                                                                                                  \n",
+      " pooling0 (MaxPooling2D)     (None, None, None, 64)       0         ['zero_padding2d_1[0][0]']    \n",
+      "                                                                                                  \n",
+      " stage1_unit1_bn1 (BatchNor  (None, None, None, 64)       256       ['pooling0[0][0]']            \n",
+      " malization)                                                                                      \n",
+      "                                                                                                  \n",
+      " stage1_unit1_relu1 (Activa  (None, None, None, 64)       0         ['stage1_unit1_bn1[0][0]']    \n",
+      " tion)                                                                                            \n",
+      "                                                                                                  \n",
+      " stage1_unit1_conv1 (Conv2D  (None, None, None, 64)       4096      ['stage1_unit1_relu1[0][0]']  \n",
+      " )                                                                                                \n",
+      "                                                                                                  \n",
+      " stage1_unit1_bn2 (BatchNor  (None, None, None, 64)       256       ['stage1_unit1_conv1[0][0]']  \n",
+      " malization)                                                                                      \n",
+      "                                                                                                  \n",
+      " stage1_unit1_relu2 (Activa  (None, None, None, 64)       0         ['stage1_unit1_bn2[0][0]']    \n",
+      " tion)                                                                                            \n",
+      "                                                                                                  \n",
+      " zero_padding2d_2 (ZeroPadd  (None, None, None, 64)       0         ['stage1_unit1_relu2[0][0]']  \n",
+      " ing2D)                                                                                           \n",
+      "                                                                                                  \n",
+      " stage1_unit1_conv2 (Conv2D  (None, None, None, 64)       36864     ['zero_padding2d_2[0][0]']    \n",
+      " )                                                                                                \n",
+      "                                                                                                  \n",
+      " stage1_unit1_bn3 (BatchNor  (None, None, None, 64)       256       ['stage1_unit1_conv2[0][0]']  \n",
+      " malization)                                                                                      \n",
+      "                                                                                                  \n",
+      " stage1_unit1_relu3 (Activa  (None, None, None, 64)       0         ['stage1_unit1_bn3[0][0]']    \n",
+      " tion)                                                                                            \n",
+      "                                                                                                  \n",
+      " stage1_unit1_conv3 (Conv2D  (None, None, None, 256)      16384     ['stage1_unit1_relu3[0][0]']  \n",
+      " )                                                                                                \n",
+      "                                                                                                  \n",
+      " stage1_unit1_sc (Conv2D)    (None, None, None, 256)      16384     ['stage1_unit1_relu1[0][0]']  \n",
+      "                                                                                                  \n",
+      " add (Add)                   (None, None, None, 256)      0         ['stage1_unit1_conv3[0][0]',  \n",
+      "                                                                     'stage1_unit1_sc[0][0]']     \n",
+      "                                                                                                  \n",
+      " stage1_unit2_bn1 (BatchNor  (None, None, None, 256)      1024      ['add[0][0]']                 \n",
+      " malization)                                                                                      \n",
+      "                                                                                                  \n",
+      " stage1_unit2_relu1 (Activa  (None, None, None, 256)      0         ['stage1_unit2_bn1[0][0]']    \n",
+      " tion)                                                                                            \n",
+      "                                                                                                  \n",
+      " stage1_unit2_conv1 (Conv2D  (None, None, None, 64)       16384     ['stage1_unit2_relu1[0][0]']  \n",
+      " )                                                                                                \n",
+      "                                                                                                  \n",
+      " stage1_unit2_bn2 (BatchNor  (None, None, None, 64)       256       ['stage1_unit2_conv1[0][0]']  \n",
+      " malization)                                                                                      \n",
+      "                                                                                                  \n",
+      " stage1_unit2_relu2 (Activa  (None, None, None, 64)       0         ['stage1_unit2_bn2[0][0]']    \n",
+      " tion)                                                                                            \n",
+      "                                                                                                  \n",
+      " zero_padding2d_3 (ZeroPadd  (None, None, None, 64)       0         ['stage1_unit2_relu2[0][0]']  \n",
+      " ing2D)                                                                                           \n",
+      "                                                                                                  \n",
+      " stage1_unit2_conv2 (Conv2D  (None, None, None, 64)       36864     ['zero_padding2d_3[0][0]']    \n",
+      " )                                                                                                \n",
+      "                                                                                                  \n",
+      " stage1_unit2_bn3 (BatchNor  (None, None, None, 64)       256       ['stage1_unit2_conv2[0][0]']  \n",
+      " malization)                                                                                      \n",
+      "                                                                                                  \n",
+      " stage1_unit2_relu3 (Activa  (None, None, None, 64)       0         ['stage1_unit2_bn3[0][0]']    \n",
+      " tion)                                                                                            \n"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "                                                                                                  \n",
+      " stage1_unit2_conv3 (Conv2D  (None, None, None, 256)      16384     ['stage1_unit2_relu3[0][0]']  \n",
+      " )                                                                                                \n",
+      "                                                                                                  \n",
+      " add_1 (Add)                 (None, None, None, 256)      0         ['stage1_unit2_conv3[0][0]',  \n",
+      "                                                                     'add[0][0]']                 \n",
+      "                                                                                                  \n",
+      " stage1_unit3_bn1 (BatchNor  (None, None, None, 256)      1024      ['add_1[0][0]']               \n",
+      " malization)                                                                                      \n",
+      "                                                                                                  \n",
+      " stage1_unit3_relu1 (Activa  (None, None, None, 256)      0         ['stage1_unit3_bn1[0][0]']    \n",
+      " tion)                                                                                            \n",
+      "                                                                                                  \n",
+      " stage1_unit3_conv1 (Conv2D  (None, None, None, 64)       16384     ['stage1_unit3_relu1[0][0]']  \n",
+      " )                                                                                                \n",
+      "                                                                                                  \n",
+      " stage1_unit3_bn2 (BatchNor  (None, None, None, 64)       256       ['stage1_unit3_conv1[0][0]']  \n",
+      " malization)                                                                                      \n",
+      "                                                                                                  \n",
+      " stage1_unit3_relu2 (Activa  (None, None, None, 64)       0         ['stage1_unit3_bn2[0][0]']    \n",
+      " tion)                                                                                            \n",
+      "                                                                                                  \n",
+      " zero_padding2d_4 (ZeroPadd  (None, None, None, 64)       0         ['stage1_unit3_relu2[0][0]']  \n",
+      " ing2D)                                                                                           \n",
+      "                                                                                                  \n",
+      " stage1_unit3_conv2 (Conv2D  (None, None, None, 64)       36864     ['zero_padding2d_4[0][0]']    \n",
+      " )                                                                                                \n",
+      "                                                                                                  \n",
+      " stage1_unit3_bn3 (BatchNor  (None, None, None, 64)       256       ['stage1_unit3_conv2[0][0]']  \n",
+      " malization)                                                                                      \n",
+      "                                                                                                  \n",
+      " stage1_unit3_relu3 (Activa  (None, None, None, 64)       0         ['stage1_unit3_bn3[0][0]']    \n",
+      " tion)                                                                                            \n",
+      "                                                                                                  \n",
+      " stage1_unit3_conv3 (Conv2D  (None, None, None, 256)      16384     ['stage1_unit3_relu3[0][0]']  \n",
+      " )                                                                                                \n",
+      "                                                                                                  \n",
+      " add_2 (Add)                 (None, None, None, 256)      0         ['stage1_unit3_conv3[0][0]',  \n",
+      "                                                                     'add_1[0][0]']               \n",
+      "                                                                                                  \n",
+      " stage2_unit1_bn1 (BatchNor  (None, None, None, 256)      1024      ['add_2[0][0]']               \n",
+      " malization)                                                                                      \n",
+      "                                                                                                  \n",
+      " stage2_unit1_relu1 (Activa  (None, None, None, 256)      0         ['stage2_unit1_bn1[0][0]']    \n",
+      " tion)                                                                                            \n",
+      "                                                                                                  \n",
+      " stage2_unit1_conv1 (Conv2D  (None, None, None, 128)      32768     ['stage2_unit1_relu1[0][0]']  \n",
+      " )                                                                                                \n",
+      "                                                                                                  \n",
+      " stage2_unit1_bn2 (BatchNor  (None, None, None, 128)      512       ['stage2_unit1_conv1[0][0]']  \n",
+      " malization)                                                                                      \n",
+      "                                                                                                  \n",
+      " stage2_unit1_relu2 (Activa  (None, None, None, 128)      0         ['stage2_unit1_bn2[0][0]']    \n",
+      " tion)                                                                                            \n",
+      "                                                                                                  \n",
+      " zero_padding2d_5 (ZeroPadd  (None, None, None, 128)      0         ['stage2_unit1_relu2[0][0]']  \n",
+      " ing2D)                                                                                           \n",
+      "                                                                                                  \n",
+      " stage2_unit1_conv2 (Conv2D  (None, None, None, 128)      147456    ['zero_padding2d_5[0][0]']    \n",
+      " )                                                                                                \n",
+      "                                                                                                  \n",
+      " stage2_unit1_bn3 (BatchNor  (None, None, None, 128)      512       ['stage2_unit1_conv2[0][0]']  \n",
+      " malization)                                                                                      \n",
+      "                                                                                                  \n",
+      " stage2_unit1_relu3 (Activa  (None, None, None, 128)      0         ['stage2_unit1_bn3[0][0]']    \n",
+      " tion)                                                                                            \n",
+      "                                                                                                  \n",
+      " stage2_unit1_conv3 (Conv2D  (None, None, None, 512)      65536     ['stage2_unit1_relu3[0][0]']  \n",
+      " )                                                                                                \n",
+      "                                                                                                  \n",
+      " stage2_unit1_sc (Conv2D)    (None, None, None, 512)      131072    ['stage2_unit1_relu1[0][0]']  \n",
+      "                                                                                                  \n",
+      " add_3 (Add)                 (None, None, None, 512)      0         ['stage2_unit1_conv3[0][0]',  \n",
+      "                                                                     'stage2_unit1_sc[0][0]']     \n",
+      "                                                                                                  \n",
+      " stage2_unit2_bn1 (BatchNor  (None, None, None, 512)      2048      ['add_3[0][0]']               \n",
+      " malization)                                                                                      \n",
+      "                                                                                                  \n",
+      " stage2_unit2_relu1 (Activa  (None, None, None, 512)      0         ['stage2_unit2_bn1[0][0]']    \n",
+      " tion)                                                                                            \n",
+      "                                                                                                  \n",
+      " stage2_unit2_conv1 (Conv2D  (None, None, None, 128)      65536     ['stage2_unit2_relu1[0][0]']  \n",
+      " )                                                                                                \n"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "                                                                                                  \n",
+      " stage2_unit2_bn2 (BatchNor  (None, None, None, 128)      512       ['stage2_unit2_conv1[0][0]']  \n",
+      " malization)                                                                                      \n",
+      "                                                                                                  \n",
+      " stage2_unit2_relu2 (Activa  (None, None, None, 128)      0         ['stage2_unit2_bn2[0][0]']    \n",
+      " tion)                                                                                            \n",
+      "                                                                                                  \n",
+      " zero_padding2d_6 (ZeroPadd  (None, None, None, 128)      0         ['stage2_unit2_relu2[0][0]']  \n",
+      " ing2D)                                                                                           \n",
+      "                                                                                                  \n",
+      " stage2_unit2_conv2 (Conv2D  (None, None, None, 128)      147456    ['zero_padding2d_6[0][0]']    \n",
+      " )                                                                                                \n",
+      "                                                                                                  \n",
+      " stage2_unit2_bn3 (BatchNor  (None, None, None, 128)      512       ['stage2_unit2_conv2[0][0]']  \n",
+      " malization)                                                                                      \n",
+      "                                                                                                  \n",
+      " stage2_unit2_relu3 (Activa  (None, None, None, 128)      0         ['stage2_unit2_bn3[0][0]']    \n",
+      " tion)                                                                                            \n",
+      "                                                                                                  \n",
+      " stage2_unit2_conv3 (Conv2D  (None, None, None, 512)      65536     ['stage2_unit2_relu3[0][0]']  \n",
+      " )                                                                                                \n",
+      "                                                                                                  \n",
+      " add_4 (Add)                 (None, None, None, 512)      0         ['stage2_unit2_conv3[0][0]',  \n",
+      "                                                                     'add_3[0][0]']               \n",
+      "                                                                                                  \n",
+      " stage2_unit3_bn1 (BatchNor  (None, None, None, 512)      2048      ['add_4[0][0]']               \n",
+      " malization)                                                                                      \n",
+      "                                                                                                  \n",
+      " stage2_unit3_relu1 (Activa  (None, None, None, 512)      0         ['stage2_unit3_bn1[0][0]']    \n",
+      " tion)                                                                                            \n",
+      "                                                                                                  \n",
+      " stage2_unit3_conv1 (Conv2D  (None, None, None, 128)      65536     ['stage2_unit3_relu1[0][0]']  \n",
+      " )                                                                                                \n",
+      "                                                                                                  \n",
+      " stage2_unit3_bn2 (BatchNor  (None, None, None, 128)      512       ['stage2_unit3_conv1[0][0]']  \n",
+      " malization)                                                                                      \n",
+      "                                                                                                  \n",
+      " stage2_unit3_relu2 (Activa  (None, None, None, 128)      0         ['stage2_unit3_bn2[0][0]']    \n",
+      " tion)                                                                                            \n",
+      "                                                                                                  \n",
+      " zero_padding2d_7 (ZeroPadd  (None, None, None, 128)      0         ['stage2_unit3_relu2[0][0]']  \n",
+      " ing2D)                                                                                           \n",
+      "                                                                                                  \n",
+      " stage2_unit3_conv2 (Conv2D  (None, None, None, 128)      147456    ['zero_padding2d_7[0][0]']    \n",
+      " )                                                                                                \n",
+      "                                                                                                  \n",
+      " stage2_unit3_bn3 (BatchNor  (None, None, None, 128)      512       ['stage2_unit3_conv2[0][0]']  \n",
+      " malization)                                                                                      \n",
+      "                                                                                                  \n",
+      " stage2_unit3_relu3 (Activa  (None, None, None, 128)      0         ['stage2_unit3_bn3[0][0]']    \n",
+      " tion)                                                                                            \n",
+      "                                                                                                  \n",
+      " stage2_unit3_conv3 (Conv2D  (None, None, None, 512)      65536     ['stage2_unit3_relu3[0][0]']  \n",
+      " )                                                                                                \n",
+      "                                                                                                  \n",
+      " add_5 (Add)                 (None, None, None, 512)      0         ['stage2_unit3_conv3[0][0]',  \n",
+      "                                                                     'add_4[0][0]']               \n",
+      "                                                                                                  \n",
+      " stage2_unit4_bn1 (BatchNor  (None, None, None, 512)      2048      ['add_5[0][0]']               \n",
+      " malization)                                                                                      \n",
+      "                                                                                                  \n",
+      " stage2_unit4_relu1 (Activa  (None, None, None, 512)      0         ['stage2_unit4_bn1[0][0]']    \n",
+      " tion)                                                                                            \n",
+      "                                                                                                  \n",
+      " stage2_unit4_conv1 (Conv2D  (None, None, None, 128)      65536     ['stage2_unit4_relu1[0][0]']  \n",
+      " )                                                                                                \n",
+      "                                                                                                  \n",
+      " stage2_unit4_bn2 (BatchNor  (None, None, None, 128)      512       ['stage2_unit4_conv1[0][0]']  \n",
+      " malization)                                                                                      \n",
+      "                                                                                                  \n",
+      " stage2_unit4_relu2 (Activa  (None, None, None, 128)      0         ['stage2_unit4_bn2[0][0]']    \n",
+      " tion)                                                                                            \n",
+      "                                                                                                  \n",
+      " zero_padding2d_8 (ZeroPadd  (None, None, None, 128)      0         ['stage2_unit4_relu2[0][0]']  \n",
+      " ing2D)                                                                                           \n",
+      "                                                                                                  \n",
+      " stage2_unit4_conv2 (Conv2D  (None, None, None, 128)      147456    ['zero_padding2d_8[0][0]']    \n",
+      " )                                                                                                \n",
+      "                                                                                                  \n",
+      " stage2_unit4_bn3 (BatchNor  (None, None, None, 128)      512       ['stage2_unit4_conv2[0][0]']  \n",
+      " malization)                                                                                      \n",
+      "                                                                                                  \n",
+      " stage2_unit4_relu3 (Activa  (None, None, None, 128)      0         ['stage2_unit4_bn3[0][0]']    \n"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      " tion)                                                                                            \n",
+      "                                                                                                  \n",
+      " stage2_unit4_conv3 (Conv2D  (None, None, None, 512)      65536     ['stage2_unit4_relu3[0][0]']  \n",
+      " )                                                                                                \n",
+      "                                                                                                  \n",
+      " add_6 (Add)                 (None, None, None, 512)      0         ['stage2_unit4_conv3[0][0]',  \n",
+      "                                                                     'add_5[0][0]']               \n",
+      "                                                                                                  \n",
+      " stage3_unit1_bn1 (BatchNor  (None, None, None, 512)      2048      ['add_6[0][0]']               \n",
+      " malization)                                                                                      \n",
+      "                                                                                                  \n",
+      " stage3_unit1_relu1 (Activa  (None, None, None, 512)      0         ['stage3_unit1_bn1[0][0]']    \n",
+      " tion)                                                                                            \n",
+      "                                                                                                  \n",
+      " stage3_unit1_conv1 (Conv2D  (None, None, None, 256)      131072    ['stage3_unit1_relu1[0][0]']  \n",
+      " )                                                                                                \n",
+      "                                                                                                  \n",
+      " stage3_unit1_bn2 (BatchNor  (None, None, None, 256)      1024      ['stage3_unit1_conv1[0][0]']  \n",
+      " malization)                                                                                      \n",
+      "                                                                                                  \n",
+      " stage3_unit1_relu2 (Activa  (None, None, None, 256)      0         ['stage3_unit1_bn2[0][0]']    \n",
+      " tion)                                                                                            \n",
+      "                                                                                                  \n",
+      " zero_padding2d_9 (ZeroPadd  (None, None, None, 256)      0         ['stage3_unit1_relu2[0][0]']  \n",
+      " ing2D)                                                                                           \n",
+      "                                                                                                  \n",
+      " stage3_unit1_conv2 (Conv2D  (None, None, None, 256)      589824    ['zero_padding2d_9[0][0]']    \n",
+      " )                                                                                                \n",
+      "                                                                                                  \n",
+      " stage3_unit1_bn3 (BatchNor  (None, None, None, 256)      1024      ['stage3_unit1_conv2[0][0]']  \n",
+      " malization)                                                                                      \n",
+      "                                                                                                  \n",
+      " stage3_unit1_relu3 (Activa  (None, None, None, 256)      0         ['stage3_unit1_bn3[0][0]']    \n",
+      " tion)                                                                                            \n",
+      "                                                                                                  \n",
+      " stage3_unit1_conv3 (Conv2D  (None, None, None, 1024)     262144    ['stage3_unit1_relu3[0][0]']  \n",
+      " )                                                                                                \n",
+      "                                                                                                  \n",
+      " stage3_unit1_sc (Conv2D)    (None, None, None, 1024)     524288    ['stage3_unit1_relu1[0][0]']  \n",
+      "                                                                                                  \n",
+      " add_7 (Add)                 (None, None, None, 1024)     0         ['stage3_unit1_conv3[0][0]',  \n",
+      "                                                                     'stage3_unit1_sc[0][0]']     \n",
+      "                                                                                                  \n",
+      " stage3_unit2_bn1 (BatchNor  (None, None, None, 1024)     4096      ['add_7[0][0]']               \n",
+      " malization)                                                                                      \n",
+      "                                                                                                  \n",
+      " stage3_unit2_relu1 (Activa  (None, None, None, 1024)     0         ['stage3_unit2_bn1[0][0]']    \n",
+      " tion)                                                                                            \n",
+      "                                                                                                  \n",
+      " stage3_unit2_conv1 (Conv2D  (None, None, None, 256)      262144    ['stage3_unit2_relu1[0][0]']  \n",
+      " )                                                                                                \n",
+      "                                                                                                  \n",
+      " stage3_unit2_bn2 (BatchNor  (None, None, None, 256)      1024      ['stage3_unit2_conv1[0][0]']  \n",
+      " malization)                                                                                      \n",
+      "                                                                                                  \n",
+      " stage3_unit2_relu2 (Activa  (None, None, None, 256)      0         ['stage3_unit2_bn2[0][0]']    \n",
+      " tion)                                                                                            \n",
+      "                                                                                                  \n",
+      " zero_padding2d_10 (ZeroPad  (None, None, None, 256)      0         ['stage3_unit2_relu2[0][0]']  \n",
+      " ding2D)                                                                                          \n",
+      "                                                                                                  \n",
+      " stage3_unit2_conv2 (Conv2D  (None, None, None, 256)      589824    ['zero_padding2d_10[0][0]']   \n",
+      " )                                                                                                \n",
+      "                                                                                                  \n",
+      " stage3_unit2_bn3 (BatchNor  (None, None, None, 256)      1024      ['stage3_unit2_conv2[0][0]']  \n",
+      " malization)                                                                                      \n",
+      "                                                                                                  \n",
+      " stage3_unit2_relu3 (Activa  (None, None, None, 256)      0         ['stage3_unit2_bn3[0][0]']    \n",
+      " tion)                                                                                            \n",
+      "                                                                                                  \n",
+      " stage3_unit2_conv3 (Conv2D  (None, None, None, 1024)     262144    ['stage3_unit2_relu3[0][0]']  \n",
+      " )                                                                                                \n",
+      "                                                                                                  \n",
+      " add_8 (Add)                 (None, None, None, 1024)     0         ['stage3_unit2_conv3[0][0]',  \n",
+      "                                                                     'add_7[0][0]']               \n",
+      "                                                                                                  \n",
+      " stage3_unit3_bn1 (BatchNor  (None, None, None, 1024)     4096      ['add_8[0][0]']               \n",
+      " malization)                                                                                      \n",
+      "                                                                                                  \n",
+      " stage3_unit3_relu1 (Activa  (None, None, None, 1024)     0         ['stage3_unit3_bn1[0][0]']    \n",
+      " tion)                                                                                            \n",
+      "                                                                                                  \n",
+      " stage3_unit3_conv1 (Conv2D  (None, None, None, 256)      262144    ['stage3_unit3_relu1[0][0]']  \n"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      " )                                                                                                \n",
+      "                                                                                                  \n",
+      " stage3_unit3_bn2 (BatchNor  (None, None, None, 256)      1024      ['stage3_unit3_conv1[0][0]']  \n",
+      " malization)                                                                                      \n",
+      "                                                                                                  \n",
+      " stage3_unit3_relu2 (Activa  (None, None, None, 256)      0         ['stage3_unit3_bn2[0][0]']    \n",
+      " tion)                                                                                            \n",
+      "                                                                                                  \n",
+      " zero_padding2d_11 (ZeroPad  (None, None, None, 256)      0         ['stage3_unit3_relu2[0][0]']  \n",
+      " ding2D)                                                                                          \n",
+      "                                                                                                  \n",
+      " stage3_unit3_conv2 (Conv2D  (None, None, None, 256)      589824    ['zero_padding2d_11[0][0]']   \n",
+      " )                                                                                                \n",
+      "                                                                                                  \n",
+      " stage3_unit3_bn3 (BatchNor  (None, None, None, 256)      1024      ['stage3_unit3_conv2[0][0]']  \n",
+      " malization)                                                                                      \n",
+      "                                                                                                  \n",
+      " stage3_unit3_relu3 (Activa  (None, None, None, 256)      0         ['stage3_unit3_bn3[0][0]']    \n",
+      " tion)                                                                                            \n",
+      "                                                                                                  \n",
+      " stage3_unit3_conv3 (Conv2D  (None, None, None, 1024)     262144    ['stage3_unit3_relu3[0][0]']  \n",
+      " )                                                                                                \n",
+      "                                                                                                  \n",
+      " add_9 (Add)                 (None, None, None, 1024)     0         ['stage3_unit3_conv3[0][0]',  \n",
+      "                                                                     'add_8[0][0]']               \n",
+      "                                                                                                  \n",
+      " stage3_unit4_bn1 (BatchNor  (None, None, None, 1024)     4096      ['add_9[0][0]']               \n",
+      " malization)                                                                                      \n",
+      "                                                                                                  \n",
+      " stage3_unit4_relu1 (Activa  (None, None, None, 1024)     0         ['stage3_unit4_bn1[0][0]']    \n",
+      " tion)                                                                                            \n",
+      "                                                                                                  \n",
+      " stage3_unit4_conv1 (Conv2D  (None, None, None, 256)      262144    ['stage3_unit4_relu1[0][0]']  \n",
+      " )                                                                                                \n",
+      "                                                                                                  \n",
+      " stage3_unit4_bn2 (BatchNor  (None, None, None, 256)      1024      ['stage3_unit4_conv1[0][0]']  \n",
+      " malization)                                                                                      \n",
+      "                                                                                                  \n",
+      " stage3_unit4_relu2 (Activa  (None, None, None, 256)      0         ['stage3_unit4_bn2[0][0]']    \n",
+      " tion)                                                                                            \n",
+      "                                                                                                  \n",
+      " zero_padding2d_12 (ZeroPad  (None, None, None, 256)      0         ['stage3_unit4_relu2[0][0]']  \n",
+      " ding2D)                                                                                          \n",
+      "                                                                                                  \n",
+      " stage3_unit4_conv2 (Conv2D  (None, None, None, 256)      589824    ['zero_padding2d_12[0][0]']   \n",
+      " )                                                                                                \n",
+      "                                                                                                  \n",
+      " stage3_unit4_bn3 (BatchNor  (None, None, None, 256)      1024      ['stage3_unit4_conv2[0][0]']  \n",
+      " malization)                                                                                      \n",
+      "                                                                                                  \n",
+      " stage3_unit4_relu3 (Activa  (None, None, None, 256)      0         ['stage3_unit4_bn3[0][0]']    \n",
+      " tion)                                                                                            \n",
+      "                                                                                                  \n",
+      " stage3_unit4_conv3 (Conv2D  (None, None, None, 1024)     262144    ['stage3_unit4_relu3[0][0]']  \n",
+      " )                                                                                                \n",
+      "                                                                                                  \n",
+      " add_10 (Add)                (None, None, None, 1024)     0         ['stage3_unit4_conv3[0][0]',  \n",
+      "                                                                     'add_9[0][0]']               \n",
+      "                                                                                                  \n",
+      " stage3_unit5_bn1 (BatchNor  (None, None, None, 1024)     4096      ['add_10[0][0]']              \n",
+      " malization)                                                                                      \n",
+      "                                                                                                  \n",
+      " stage3_unit5_relu1 (Activa  (None, None, None, 1024)     0         ['stage3_unit5_bn1[0][0]']    \n",
+      " tion)                                                                                            \n",
+      "                                                                                                  \n",
+      " stage3_unit5_conv1 (Conv2D  (None, None, None, 256)      262144    ['stage3_unit5_relu1[0][0]']  \n",
+      " )                                                                                                \n",
+      "                                                                                                  \n",
+      " stage3_unit5_bn2 (BatchNor  (None, None, None, 256)      1024      ['stage3_unit5_conv1[0][0]']  \n",
+      " malization)                                                                                      \n",
+      "                                                                                                  \n",
+      " stage3_unit5_relu2 (Activa  (None, None, None, 256)      0         ['stage3_unit5_bn2[0][0]']    \n",
+      " tion)                                                                                            \n",
+      "                                                                                                  \n",
+      " zero_padding2d_13 (ZeroPad  (None, None, None, 256)      0         ['stage3_unit5_relu2[0][0]']  \n",
+      " ding2D)                                                                                          \n",
+      "                                                                                                  \n",
+      " stage3_unit5_conv2 (Conv2D  (None, None, None, 256)      589824    ['zero_padding2d_13[0][0]']   \n",
+      " )                                                                                                \n",
+      "                                                                                                  \n",
+      " stage3_unit5_bn3 (BatchNor  (None, None, None, 256)      1024      ['stage3_unit5_conv2[0][0]']  \n",
+      " malization)                                                                                      \n",
+      "                                                                                                  \n"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      " stage3_unit5_relu3 (Activa  (None, None, None, 256)      0         ['stage3_unit5_bn3[0][0]']    \n",
+      " tion)                                                                                            \n",
+      "                                                                                                  \n",
+      " stage3_unit5_conv3 (Conv2D  (None, None, None, 1024)     262144    ['stage3_unit5_relu3[0][0]']  \n",
+      " )                                                                                                \n",
+      "                                                                                                  \n",
+      " add_11 (Add)                (None, None, None, 1024)     0         ['stage3_unit5_conv3[0][0]',  \n",
+      "                                                                     'add_10[0][0]']              \n",
+      "                                                                                                  \n",
+      " stage3_unit6_bn1 (BatchNor  (None, None, None, 1024)     4096      ['add_11[0][0]']              \n",
+      " malization)                                                                                      \n",
+      "                                                                                                  \n",
+      " stage3_unit6_relu1 (Activa  (None, None, None, 1024)     0         ['stage3_unit6_bn1[0][0]']    \n",
+      " tion)                                                                                            \n",
+      "                                                                                                  \n",
+      " stage3_unit6_conv1 (Conv2D  (None, None, None, 256)      262144    ['stage3_unit6_relu1[0][0]']  \n",
+      " )                                                                                                \n",
+      "                                                                                                  \n",
+      " stage3_unit6_bn2 (BatchNor  (None, None, None, 256)      1024      ['stage3_unit6_conv1[0][0]']  \n",
+      " malization)                                                                                      \n",
+      "                                                                                                  \n",
+      " stage3_unit6_relu2 (Activa  (None, None, None, 256)      0         ['stage3_unit6_bn2[0][0]']    \n",
+      " tion)                                                                                            \n",
+      "                                                                                                  \n",
+      " zero_padding2d_14 (ZeroPad  (None, None, None, 256)      0         ['stage3_unit6_relu2[0][0]']  \n",
+      " ding2D)                                                                                          \n",
+      "                                                                                                  \n",
+      " stage3_unit6_conv2 (Conv2D  (None, None, None, 256)      589824    ['zero_padding2d_14[0][0]']   \n",
+      " )                                                                                                \n",
+      "                                                                                                  \n",
+      " stage3_unit6_bn3 (BatchNor  (None, None, None, 256)      1024      ['stage3_unit6_conv2[0][0]']  \n",
+      " malization)                                                                                      \n",
+      "                                                                                                  \n",
+      " stage3_unit6_relu3 (Activa  (None, None, None, 256)      0         ['stage3_unit6_bn3[0][0]']    \n",
+      " tion)                                                                                            \n",
+      "                                                                                                  \n",
+      " stage3_unit6_conv3 (Conv2D  (None, None, None, 1024)     262144    ['stage3_unit6_relu3[0][0]']  \n",
+      " )                                                                                                \n",
+      "                                                                                                  \n",
+      " add_12 (Add)                (None, None, None, 1024)     0         ['stage3_unit6_conv3[0][0]',  \n",
+      "                                                                     'add_11[0][0]']              \n",
+      "                                                                                                  \n",
+      " stage4_unit1_bn1 (BatchNor  (None, None, None, 1024)     4096      ['add_12[0][0]']              \n",
+      " malization)                                                                                      \n",
+      "                                                                                                  \n",
+      " stage4_unit1_relu1 (Activa  (None, None, None, 1024)     0         ['stage4_unit1_bn1[0][0]']    \n",
+      " tion)                                                                                            \n",
+      "                                                                                                  \n",
+      " stage4_unit1_conv1 (Conv2D  (None, None, None, 512)      524288    ['stage4_unit1_relu1[0][0]']  \n",
+      " )                                                                                                \n",
+      "                                                                                                  \n",
+      " stage4_unit1_bn2 (BatchNor  (None, None, None, 512)      2048      ['stage4_unit1_conv1[0][0]']  \n",
+      " malization)                                                                                      \n",
+      "                                                                                                  \n",
+      " stage4_unit1_relu2 (Activa  (None, None, None, 512)      0         ['stage4_unit1_bn2[0][0]']    \n",
+      " tion)                                                                                            \n",
+      "                                                                                                  \n",
+      " zero_padding2d_15 (ZeroPad  (None, None, None, 512)      0         ['stage4_unit1_relu2[0][0]']  \n",
+      " ding2D)                                                                                          \n",
+      "                                                                                                  \n",
+      " stage4_unit1_conv2 (Conv2D  (None, None, None, 512)      2359296   ['zero_padding2d_15[0][0]']   \n",
+      " )                                                                                                \n",
+      "                                                                                                  \n",
+      " stage4_unit1_bn3 (BatchNor  (None, None, None, 512)      2048      ['stage4_unit1_conv2[0][0]']  \n",
+      " malization)                                                                                      \n",
+      "                                                                                                  \n",
+      " stage4_unit1_relu3 (Activa  (None, None, None, 512)      0         ['stage4_unit1_bn3[0][0]']    \n",
+      " tion)                                                                                            \n",
+      "                                                                                                  \n",
+      " stage4_unit1_conv3 (Conv2D  (None, None, None, 2048)     1048576   ['stage4_unit1_relu3[0][0]']  \n",
+      " )                                                                                                \n",
+      "                                                                                                  \n",
+      " stage4_unit1_sc (Conv2D)    (None, None, None, 2048)     2097152   ['stage4_unit1_relu1[0][0]']  \n",
+      "                                                                                                  \n",
+      " add_13 (Add)                (None, None, None, 2048)     0         ['stage4_unit1_conv3[0][0]',  \n",
+      "                                                                     'stage4_unit1_sc[0][0]']     \n",
+      "                                                                                                  \n",
+      " stage4_unit2_bn1 (BatchNor  (None, None, None, 2048)     8192      ['add_13[0][0]']              \n",
+      " malization)                                                                                      \n",
+      "                                                                                                  \n",
+      " stage4_unit2_relu1 (Activa  (None, None, None, 2048)     0         ['stage4_unit2_bn1[0][0]']    \n",
+      " tion)                                                                                            \n",
+      "                                                                                                  \n"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      " stage4_unit2_conv1 (Conv2D  (None, None, None, 512)      1048576   ['stage4_unit2_relu1[0][0]']  \n",
+      " )                                                                                                \n",
+      "                                                                                                  \n",
+      " stage4_unit2_bn2 (BatchNor  (None, None, None, 512)      2048      ['stage4_unit2_conv1[0][0]']  \n",
+      " malization)                                                                                      \n",
+      "                                                                                                  \n",
+      " stage4_unit2_relu2 (Activa  (None, None, None, 512)      0         ['stage4_unit2_bn2[0][0]']    \n",
+      " tion)                                                                                            \n",
+      "                                                                                                  \n",
+      " zero_padding2d_16 (ZeroPad  (None, None, None, 512)      0         ['stage4_unit2_relu2[0][0]']  \n",
+      " ding2D)                                                                                          \n",
+      "                                                                                                  \n",
+      " stage4_unit2_conv2 (Conv2D  (None, None, None, 512)      2359296   ['zero_padding2d_16[0][0]']   \n",
+      " )                                                                                                \n",
+      "                                                                                                  \n",
+      " stage4_unit2_bn3 (BatchNor  (None, None, None, 512)      2048      ['stage4_unit2_conv2[0][0]']  \n",
+      " malization)                                                                                      \n",
+      "                                                                                                  \n",
+      " stage4_unit2_relu3 (Activa  (None, None, None, 512)      0         ['stage4_unit2_bn3[0][0]']    \n",
+      " tion)                                                                                            \n",
+      "                                                                                                  \n",
+      " stage4_unit2_conv3 (Conv2D  (None, None, None, 2048)     1048576   ['stage4_unit2_relu3[0][0]']  \n",
+      " )                                                                                                \n",
+      "                                                                                                  \n",
+      " add_14 (Add)                (None, None, None, 2048)     0         ['stage4_unit2_conv3[0][0]',  \n",
+      "                                                                     'add_13[0][0]']              \n",
+      "                                                                                                  \n",
+      " stage4_unit3_bn1 (BatchNor  (None, None, None, 2048)     8192      ['add_14[0][0]']              \n",
+      " malization)                                                                                      \n",
+      "                                                                                                  \n",
+      " stage4_unit3_relu1 (Activa  (None, None, None, 2048)     0         ['stage4_unit3_bn1[0][0]']    \n",
+      " tion)                                                                                            \n",
+      "                                                                                                  \n",
+      " stage4_unit3_conv1 (Conv2D  (None, None, None, 512)      1048576   ['stage4_unit3_relu1[0][0]']  \n",
+      " )                                                                                                \n",
+      "                                                                                                  \n",
+      " stage4_unit3_bn2 (BatchNor  (None, None, None, 512)      2048      ['stage4_unit3_conv1[0][0]']  \n",
+      " malization)                                                                                      \n",
+      "                                                                                                  \n",
+      " stage4_unit3_relu2 (Activa  (None, None, None, 512)      0         ['stage4_unit3_bn2[0][0]']    \n",
+      " tion)                                                                                            \n",
+      "                                                                                                  \n",
+      " zero_padding2d_17 (ZeroPad  (None, None, None, 512)      0         ['stage4_unit3_relu2[0][0]']  \n",
+      " ding2D)                                                                                          \n",
+      "                                                                                                  \n",
+      " stage4_unit3_conv2 (Conv2D  (None, None, None, 512)      2359296   ['zero_padding2d_17[0][0]']   \n",
+      " )                                                                                                \n",
+      "                                                                                                  \n",
+      " stage4_unit3_bn3 (BatchNor  (None, None, None, 512)      2048      ['stage4_unit3_conv2[0][0]']  \n",
+      " malization)                                                                                      \n",
+      "                                                                                                  \n",
+      " stage4_unit3_relu3 (Activa  (None, None, None, 512)      0         ['stage4_unit3_bn3[0][0]']    \n",
+      " tion)                                                                                            \n",
+      "                                                                                                  \n",
+      " stage4_unit3_conv3 (Conv2D  (None, None, None, 2048)     1048576   ['stage4_unit3_relu3[0][0]']  \n",
+      " )                                                                                                \n",
+      "                                                                                                  \n",
+      " add_15 (Add)                (None, None, None, 2048)     0         ['stage4_unit3_conv3[0][0]',  \n",
+      "                                                                     'add_14[0][0]']              \n",
+      "                                                                                                  \n",
+      " bn1 (BatchNormalization)    (None, None, None, 2048)     8192      ['add_15[0][0]']              \n",
+      "                                                                                                  \n",
+      " relu1 (Activation)          (None, None, None, 2048)     0         ['bn1[0][0]']                 \n",
+      "                                                                                                  \n",
+      " decoder_stage0_upsampling   (None, None, None, 2048)     0         ['relu1[0][0]']               \n",
+      " (UpSampling2D)                                                                                   \n",
+      "                                                                                                  \n",
+      " decoder_stage0_concat (Con  (None, None, None, 3072)     0         ['decoder_stage0_upsampling[0]\n",
+      " catenate)                                                          [0]',                         \n",
+      "                                                                     'stage4_unit1_relu1[0][0]']  \n",
+      "                                                                                                  \n",
+      " decoder_stage0a_conv (Conv  (None, None, None, 256)      7077888   ['decoder_stage0_concat[0][0]'\n",
+      " 2D)                                                                ]                             \n",
+      "                                                                                                  \n",
+      " decoder_stage0a_bn (BatchN  (None, None, None, 256)      1024      ['decoder_stage0a_conv[0][0]']\n",
+      " ormalization)                                                                                    \n",
+      "                                                                                                  \n",
+      " decoder_stage0a_relu (Acti  (None, None, None, 256)      0         ['decoder_stage0a_bn[0][0]']  \n",
+      " vation)                                                                                          \n",
+      "                                                                                                  \n",
+      " decoder_stage0b_conv (Conv  (None, None, None, 256)      589824    ['decoder_stage0a_relu[0][0]']\n",
+      " 2D)                                                                                              \n",
+      "                                                                                                  \n"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      " decoder_stage0b_bn (BatchN  (None, None, None, 256)      1024      ['decoder_stage0b_conv[0][0]']\n",
+      " ormalization)                                                                                    \n",
+      "                                                                                                  \n",
+      " decoder_stage0b_relu (Acti  (None, None, None, 256)      0         ['decoder_stage0b_bn[0][0]']  \n",
+      " vation)                                                                                          \n",
+      "                                                                                                  \n",
+      " decoder_stage1_upsampling   (None, None, None, 256)      0         ['decoder_stage0b_relu[0][0]']\n",
+      " (UpSampling2D)                                                                                   \n",
+      "                                                                                                  \n",
+      " decoder_stage1_concat (Con  (None, None, None, 768)      0         ['decoder_stage1_upsampling[0]\n",
+      " catenate)                                                          [0]',                         \n",
+      "                                                                     'stage3_unit1_relu1[0][0]']  \n",
+      "                                                                                                  \n",
+      " decoder_stage1a_conv (Conv  (None, None, None, 128)      884736    ['decoder_stage1_concat[0][0]'\n",
+      " 2D)                                                                ]                             \n",
+      "                                                                                                  \n",
+      " decoder_stage1a_bn (BatchN  (None, None, None, 128)      512       ['decoder_stage1a_conv[0][0]']\n",
+      " ormalization)                                                                                    \n",
+      "                                                                                                  \n",
+      " decoder_stage1a_relu (Acti  (None, None, None, 128)      0         ['decoder_stage1a_bn[0][0]']  \n",
+      " vation)                                                                                          \n",
+      "                                                                                                  \n",
+      " decoder_stage1b_conv (Conv  (None, None, None, 128)      147456    ['decoder_stage1a_relu[0][0]']\n",
+      " 2D)                                                                                              \n",
+      "                                                                                                  \n",
+      " decoder_stage1b_bn (BatchN  (None, None, None, 128)      512       ['decoder_stage1b_conv[0][0]']\n",
+      " ormalization)                                                                                    \n",
+      "                                                                                                  \n",
+      " decoder_stage1b_relu (Acti  (None, None, None, 128)      0         ['decoder_stage1b_bn[0][0]']  \n",
+      " vation)                                                                                          \n",
+      "                                                                                                  \n",
+      " decoder_stage2_upsampling   (None, None, None, 128)      0         ['decoder_stage1b_relu[0][0]']\n",
+      " (UpSampling2D)                                                                                   \n",
+      "                                                                                                  \n",
+      " decoder_stage2_concat (Con  (None, None, None, 384)      0         ['decoder_stage2_upsampling[0]\n",
+      " catenate)                                                          [0]',                         \n",
+      "                                                                     'stage2_unit1_relu1[0][0]']  \n",
+      "                                                                                                  \n",
+      " decoder_stage2a_conv (Conv  (None, None, None, 64)       221184    ['decoder_stage2_concat[0][0]'\n",
+      " 2D)                                                                ]                             \n",
+      "                                                                                                  \n",
+      " decoder_stage2a_bn (BatchN  (None, None, None, 64)       256       ['decoder_stage2a_conv[0][0]']\n",
+      " ormalization)                                                                                    \n",
+      "                                                                                                  \n",
+      " decoder_stage2a_relu (Acti  (None, None, None, 64)       0         ['decoder_stage2a_bn[0][0]']  \n",
+      " vation)                                                                                          \n",
+      "                                                                                                  \n",
+      " decoder_stage2b_conv (Conv  (None, None, None, 64)       36864     ['decoder_stage2a_relu[0][0]']\n",
+      " 2D)                                                                                              \n",
+      "                                                                                                  \n",
+      " decoder_stage2b_bn (BatchN  (None, None, None, 64)       256       ['decoder_stage2b_conv[0][0]']\n",
+      " ormalization)                                                                                    \n",
+      "                                                                                                  \n",
+      " decoder_stage2b_relu (Acti  (None, None, None, 64)       0         ['decoder_stage2b_bn[0][0]']  \n",
+      " vation)                                                                                          \n",
+      "                                                                                                  \n",
+      " decoder_stage3_upsampling   (None, None, None, 64)       0         ['decoder_stage2b_relu[0][0]']\n",
+      " (UpSampling2D)                                                                                   \n",
+      "                                                                                                  \n",
+      " decoder_stage3_concat (Con  (None, None, None, 128)      0         ['decoder_stage3_upsampling[0]\n",
+      " catenate)                                                          [0]',                         \n",
+      "                                                                     'relu0[0][0]']               \n",
+      "                                                                                                  \n",
+      " decoder_stage3a_conv (Conv  (None, None, None, 32)       36864     ['decoder_stage3_concat[0][0]'\n",
+      " 2D)                                                                ]                             \n",
+      "                                                                                                  \n",
+      " decoder_stage3a_bn (BatchN  (None, None, None, 32)       128       ['decoder_stage3a_conv[0][0]']\n",
+      " ormalization)                                                                                    \n",
+      "                                                                                                  \n",
+      " decoder_stage3a_relu (Acti  (None, None, None, 32)       0         ['decoder_stage3a_bn[0][0]']  \n",
+      " vation)                                                                                          \n",
+      "                                                                                                  \n",
+      " decoder_stage3b_conv (Conv  (None, None, None, 32)       9216      ['decoder_stage3a_relu[0][0]']\n",
+      " 2D)                                                                                              \n",
+      "                                                                                                  \n",
+      " decoder_stage3b_bn (BatchN  (None, None, None, 32)       128       ['decoder_stage3b_conv[0][0]']\n",
+      " ormalization)                                                                                    \n",
+      "                                                                                                  \n",
+      " decoder_stage3b_relu (Acti  (None, None, None, 32)       0         ['decoder_stage3b_bn[0][0]']  \n",
+      " vation)                                                                                          \n",
+      "                                                                                                  \n",
+      " decoder_stage4_upsampling   (None, None, None, 32)       0         ['decoder_stage3b_relu[0][0]']\n",
+      " (UpSampling2D)                                                                                   \n"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "                                                                                                  \n",
+      " decoder_stage4a_conv (Conv  (None, None, None, 16)       4608      ['decoder_stage4_upsampling[0]\n",
+      " 2D)                                                                [0]']                         \n",
+      "                                                                                                  \n",
+      " decoder_stage4a_bn (BatchN  (None, None, None, 16)       64        ['decoder_stage4a_conv[0][0]']\n",
+      " ormalization)                                                                                    \n",
+      "                                                                                                  \n",
+      " decoder_stage4a_relu (Acti  (None, None, None, 16)       0         ['decoder_stage4a_bn[0][0]']  \n",
+      " vation)                                                                                          \n",
+      "                                                                                                  \n",
+      " decoder_stage4b_conv (Conv  (None, None, None, 16)       2304      ['decoder_stage4a_relu[0][0]']\n",
+      " 2D)                                                                                              \n",
+      "                                                                                                  \n",
+      " decoder_stage4b_bn (BatchN  (None, None, None, 16)       64        ['decoder_stage4b_conv[0][0]']\n",
+      " ormalization)                                                                                    \n",
+      "                                                                                                  \n",
+      " decoder_stage4b_relu (Acti  (None, None, None, 16)       0         ['decoder_stage4b_bn[0][0]']  \n",
+      " vation)                                                                                          \n",
+      "                                                                                                  \n",
+      " final_conv (Conv2D)         (None, None, None, 3)        435       ['decoder_stage4b_relu[0][0]']\n",
+      "                                                                                                  \n",
+      " sigmoid (Activation)        (None, None, None, 3)        0         ['final_conv[0][0]']          \n",
+      "                                                                                                  \n",
+      "==================================================================================================\n",
+      "Total params: 32561404 (124.21 MB)\n",
+      "Trainable params: 32513846 (124.03 MB)\n",
+      "Non-trainable params: 47558 (185.77 KB)\n",
+      "__________________________________________________________________________________________________\n",
+      "None\n"
+     ]
+    }
+   ],
+   "source": [
+    "BACKBONE1 = 'resnet50'       #resnet50 model\n",
+    "\n",
+    "resnet50_BB = sm.Unet(BACKBONE1, encoder_weights='imagenet', classes=3) #pre defined weights\n",
+    "\n",
+    "resnet50_BB.compile(optimizer='adam',\n",
+    "              loss=tf.keras.losses.SparseCategoricalCrossentropy(from_logits=True),\n",
+    "              metrics=['accuracy'])\n",
+    "\n",
+    "print(resnet50_BB.summary())"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 30,
+   "id": "ef0c7ddf",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "D:\\anaconda3\\Lib\\site-packages\\keras\\src\\backend.py:5727: UserWarning: \"`sparse_categorical_crossentropy` received `from_logits=True`, but the `output` argument was produced by a Softmax activation and thus does not represent logits. Was this intended?\n",
+      "  output, from_logits = _get_logits(\n"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "WARNING:tensorflow:From D:\\anaconda3\\Lib\\site-packages\\keras\\src\\utils\\tf_utils.py:492: The name tf.ragged.RaggedTensorValue is deprecated. Please use tf.compat.v1.ragged.RaggedTensorValue instead.\n",
+      "\n",
+      "WARNING:tensorflow:From D:\\anaconda3\\Lib\\site-packages\\keras\\src\\engine\\base_layer_utils.py:384: The name tf.executing_eagerly_outside_functions is deprecated. Please use tf.compat.v1.executing_eagerly_outside_functions instead.\n",
+      "\n",
+      "22/22 [==============================] - 1108s 49s/step - loss: 0.5129 - accuracy: 0.8513\n"
+     ]
+    }
+   ],
+   "source": [
+    "train_dataset_batchsize16 = processed_ds_train.batch(32)\n",
+    "history1 = resnet50_BB.fit(train_dataset_batchsize16, epochs=1)\n",
+    "#epoch is set to 1, due to low computational power\n",
+    "#users can increase the no. of epochs to 40 for good accuracy"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 31,
+   "id": "cc0138b3",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "D:\\anaconda3\\Lib\\site-packages\\keras\\src\\engine\\training.py:3103: UserWarning: You are saving your model as an HDF5 file via `model.save()`. This file format is considered legacy. We recommend using instead the native Keras format, e.g. `model.save('my_model.keras')`.\n",
+      "  saving_api.save_model(\n"
+     ]
+    }
+   ],
+   "source": [
+    "resnet50_BB.save('resnet_model.h5') #save the model for future use"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 62,
+   "id": "c7ea270b",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "def display(display_list):            #function for comparing input,true and predicted image\n",
+    "    plt.figure(figsize=(10, 10))\n",
+    "\n",
+    "    title = ['Input Image', 'True Mask', 'Predicted Mask']\n",
+    "\n",
+    "    for i in range(len(display_list)):\n",
+    "        plt.subplot(1, len(display_list), i+1)\n",
+    "        plt.title(title[i])\n",
+    "        plt.imshow(tf.keras.preprocessing.image.array_to_img(display_list[i]))\n",
+    "        plt.axis('off')\n",
+    "    plt.show()\n",
+    "\n",
+    "def create_mask(pred_mask):\n",
+    "    pred_mask = tf.argmax(pred_mask, axis=-1)\n",
+    "    pred_mask = pred_mask[..., tf.newaxis] # (...) represents all the axes before the new axis\n",
+    "    return pred_mask[0]\n",
+    "\n",
+    "def show_predictions(dataset=None, num=1, model = unet):  #function for comparing input,true and predicted image\n",
+    "    if dataset:\n",
+    "        for image, mask in dataset.take(num):\n",
+    "            pred_mask = model.predict(image)\n",
+    "            display([image[0], mask[0], create_mask(pred_mask)])\n",
+    "    else:\n",
+    "        display([sample_image, sample_mask,\n",
+    "             create_mask(unet.predict(sample_image[tf.newaxis, ...]))])"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "2dd46b0e",
+   "metadata": {},
+   "source": [
+    "## Vgg16"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 33,
+   "id": "690aab48",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Model: \"model_3\"\n",
+      "__________________________________________________________________________________________________\n",
+      " Layer (type)                Output Shape                 Param #   Connected to                  \n",
+      "==================================================================================================\n",
+      " input_2 (InputLayer)        [(None, None, None, 3)]      0         []                            \n",
+      "                                                                                                  \n",
+      " block1_conv1 (Conv2D)       (None, None, None, 64)       1792      ['input_2[0][0]']             \n",
+      "                                                                                                  \n",
+      " block1_conv2 (Conv2D)       (None, None, None, 64)       36928     ['block1_conv1[0][0]']        \n",
+      "                                                                                                  \n",
+      " block1_pool (MaxPooling2D)  (None, None, None, 64)       0         ['block1_conv2[0][0]']        \n",
+      "                                                                                                  \n",
+      " block2_conv1 (Conv2D)       (None, None, None, 128)      73856     ['block1_pool[0][0]']         \n",
+      "                                                                                                  \n",
+      " block2_conv2 (Conv2D)       (None, None, None, 128)      147584    ['block2_conv1[0][0]']        \n",
+      "                                                                                                  \n",
+      " block2_pool (MaxPooling2D)  (None, None, None, 128)      0         ['block2_conv2[0][0]']        \n",
+      "                                                                                                  \n",
+      " block3_conv1 (Conv2D)       (None, None, None, 256)      295168    ['block2_pool[0][0]']         \n",
+      "                                                                                                  \n",
+      " block3_conv2 (Conv2D)       (None, None, None, 256)      590080    ['block3_conv1[0][0]']        \n",
+      "                                                                                                  \n",
+      " block3_conv3 (Conv2D)       (None, None, None, 256)      590080    ['block3_conv2[0][0]']        \n",
+      "                                                                                                  \n",
+      " block3_pool (MaxPooling2D)  (None, None, None, 256)      0         ['block3_conv3[0][0]']        \n",
+      "                                                                                                  \n",
+      " block4_conv1 (Conv2D)       (None, None, None, 512)      1180160   ['block3_pool[0][0]']         \n",
+      "                                                                                                  \n",
+      " block4_conv2 (Conv2D)       (None, None, None, 512)      2359808   ['block4_conv1[0][0]']        \n",
+      "                                                                                                  \n",
+      " block4_conv3 (Conv2D)       (None, None, None, 512)      2359808   ['block4_conv2[0][0]']        \n",
+      "                                                                                                  \n",
+      " block4_pool (MaxPooling2D)  (None, None, None, 512)      0         ['block4_conv3[0][0]']        \n",
+      "                                                                                                  \n",
+      " block5_conv1 (Conv2D)       (None, None, None, 512)      2359808   ['block4_pool[0][0]']         \n",
+      "                                                                                                  \n",
+      " block5_conv2 (Conv2D)       (None, None, None, 512)      2359808   ['block5_conv1[0][0]']        \n",
+      "                                                                                                  \n",
+      " block5_conv3 (Conv2D)       (None, None, None, 512)      2359808   ['block5_conv2[0][0]']        \n",
+      "                                                                                                  \n",
+      " block5_pool (MaxPooling2D)  (None, None, None, 512)      0         ['block5_conv3[0][0]']        \n",
+      "                                                                                                  \n",
+      " center_block1_conv (Conv2D  (None, None, None, 512)      2359296   ['block5_pool[0][0]']         \n",
+      " )                                                                                                \n",
+      "                                                                                                  \n",
+      " center_block1_bn (BatchNor  (None, None, None, 512)      2048      ['center_block1_conv[0][0]']  \n",
+      " malization)                                                                                      \n",
+      "                                                                                                  \n",
+      " center_block1_relu (Activa  (None, None, None, 512)      0         ['center_block1_bn[0][0]']    \n",
+      " tion)                                                                                            \n",
+      "                                                                                                  \n",
+      " center_block2_conv (Conv2D  (None, None, None, 512)      2359296   ['center_block1_relu[0][0]']  \n",
+      " )                                                                                                \n",
+      "                                                                                                  \n",
+      " center_block2_bn (BatchNor  (None, None, None, 512)      2048      ['center_block2_conv[0][0]']  \n",
+      " malization)                                                                                      \n",
+      "                                                                                                  \n",
+      " center_block2_relu (Activa  (None, None, None, 512)      0         ['center_block2_bn[0][0]']    \n",
+      " tion)                                                                                            \n",
+      "                                                                                                  \n",
+      " decoder_stage0_upsampling   (None, None, None, 512)      0         ['center_block2_relu[0][0]']  \n",
+      " (UpSampling2D)                                                                                   \n",
+      "                                                                                                  \n",
+      " decoder_stage0_concat (Con  (None, None, None, 1024)     0         ['decoder_stage0_upsampling[0]\n",
+      " catenate)                                                          [0]',                         \n",
+      "                                                                     'block5_conv3[0][0]']        \n",
+      "                                                                                                  \n",
+      " decoder_stage0a_conv (Conv  (None, None, None, 256)      2359296   ['decoder_stage0_concat[0][0]'\n",
+      " 2D)                                                                ]                             \n",
+      "                                                                                                  \n",
+      " decoder_stage0a_bn (BatchN  (None, None, None, 256)      1024      ['decoder_stage0a_conv[0][0]']\n",
+      " ormalization)                                                                                    \n",
+      "                                                                                                  \n",
+      " decoder_stage0a_relu (Acti  (None, None, None, 256)      0         ['decoder_stage0a_bn[0][0]']  \n",
+      " vation)                                                                                          \n",
+      "                                                                                                  \n",
+      " decoder_stage0b_conv (Conv  (None, None, None, 256)      589824    ['decoder_stage0a_relu[0][0]']\n",
+      " 2D)                                                                                              \n",
+      "                                                                                                  \n",
+      " decoder_stage0b_bn (BatchN  (None, None, None, 256)      1024      ['decoder_stage0b_conv[0][0]']\n",
+      " ormalization)                                                                                    \n",
+      "                                                                                                  \n",
+      " decoder_stage0b_relu (Acti  (None, None, None, 256)      0         ['decoder_stage0b_bn[0][0]']  \n",
+      " vation)                                                                                          \n"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "                                                                                                  \n",
+      " decoder_stage1_upsampling   (None, None, None, 256)      0         ['decoder_stage0b_relu[0][0]']\n",
+      " (UpSampling2D)                                                                                   \n",
+      "                                                                                                  \n",
+      " decoder_stage1_concat (Con  (None, None, None, 768)      0         ['decoder_stage1_upsampling[0]\n",
+      " catenate)                                                          [0]',                         \n",
+      "                                                                     'block4_conv3[0][0]']        \n",
+      "                                                                                                  \n",
+      " decoder_stage1a_conv (Conv  (None, None, None, 128)      884736    ['decoder_stage1_concat[0][0]'\n",
+      " 2D)                                                                ]                             \n",
+      "                                                                                                  \n",
+      " decoder_stage1a_bn (BatchN  (None, None, None, 128)      512       ['decoder_stage1a_conv[0][0]']\n",
+      " ormalization)                                                                                    \n",
+      "                                                                                                  \n",
+      " decoder_stage1a_relu (Acti  (None, None, None, 128)      0         ['decoder_stage1a_bn[0][0]']  \n",
+      " vation)                                                                                          \n",
+      "                                                                                                  \n",
+      " decoder_stage1b_conv (Conv  (None, None, None, 128)      147456    ['decoder_stage1a_relu[0][0]']\n",
+      " 2D)                                                                                              \n",
+      "                                                                                                  \n",
+      " decoder_stage1b_bn (BatchN  (None, None, None, 128)      512       ['decoder_stage1b_conv[0][0]']\n",
+      " ormalization)                                                                                    \n",
+      "                                                                                                  \n",
+      " decoder_stage1b_relu (Acti  (None, None, None, 128)      0         ['decoder_stage1b_bn[0][0]']  \n",
+      " vation)                                                                                          \n",
+      "                                                                                                  \n",
+      " decoder_stage2_upsampling   (None, None, None, 128)      0         ['decoder_stage1b_relu[0][0]']\n",
+      " (UpSampling2D)                                                                                   \n",
+      "                                                                                                  \n",
+      " decoder_stage2_concat (Con  (None, None, None, 384)      0         ['decoder_stage2_upsampling[0]\n",
+      " catenate)                                                          [0]',                         \n",
+      "                                                                     'block3_conv3[0][0]']        \n",
+      "                                                                                                  \n",
+      " decoder_stage2a_conv (Conv  (None, None, None, 64)       221184    ['decoder_stage2_concat[0][0]'\n",
+      " 2D)                                                                ]                             \n",
+      "                                                                                                  \n",
+      " decoder_stage2a_bn (BatchN  (None, None, None, 64)       256       ['decoder_stage2a_conv[0][0]']\n",
+      " ormalization)                                                                                    \n",
+      "                                                                                                  \n",
+      " decoder_stage2a_relu (Acti  (None, None, None, 64)       0         ['decoder_stage2a_bn[0][0]']  \n",
+      " vation)                                                                                          \n",
+      "                                                                                                  \n",
+      " decoder_stage2b_conv (Conv  (None, None, None, 64)       36864     ['decoder_stage2a_relu[0][0]']\n",
+      " 2D)                                                                                              \n",
+      "                                                                                                  \n",
+      " decoder_stage2b_bn (BatchN  (None, None, None, 64)       256       ['decoder_stage2b_conv[0][0]']\n",
+      " ormalization)                                                                                    \n",
+      "                                                                                                  \n",
+      " decoder_stage2b_relu (Acti  (None, None, None, 64)       0         ['decoder_stage2b_bn[0][0]']  \n",
+      " vation)                                                                                          \n",
+      "                                                                                                  \n",
+      " decoder_stage3_upsampling   (None, None, None, 64)       0         ['decoder_stage2b_relu[0][0]']\n",
+      " (UpSampling2D)                                                                                   \n",
+      "                                                                                                  \n",
+      " decoder_stage3_concat (Con  (None, None, None, 192)      0         ['decoder_stage3_upsampling[0]\n",
+      " catenate)                                                          [0]',                         \n",
+      "                                                                     'block2_conv2[0][0]']        \n",
+      "                                                                                                  \n",
+      " decoder_stage3a_conv (Conv  (None, None, None, 32)       55296     ['decoder_stage3_concat[0][0]'\n",
+      " 2D)                                                                ]                             \n",
+      "                                                                                                  \n",
+      " decoder_stage3a_bn (BatchN  (None, None, None, 32)       128       ['decoder_stage3a_conv[0][0]']\n",
+      " ormalization)                                                                                    \n",
+      "                                                                                                  \n",
+      " decoder_stage3a_relu (Acti  (None, None, None, 32)       0         ['decoder_stage3a_bn[0][0]']  \n",
+      " vation)                                                                                          \n",
+      "                                                                                                  \n",
+      " decoder_stage3b_conv (Conv  (None, None, None, 32)       9216      ['decoder_stage3a_relu[0][0]']\n",
+      " 2D)                                                                                              \n",
+      "                                                                                                  \n",
+      " decoder_stage3b_bn (BatchN  (None, None, None, 32)       128       ['decoder_stage3b_conv[0][0]']\n",
+      " ormalization)                                                                                    \n",
+      "                                                                                                  \n",
+      " decoder_stage3b_relu (Acti  (None, None, None, 32)       0         ['decoder_stage3b_bn[0][0]']  \n",
+      " vation)                                                                                          \n",
+      "                                                                                                  \n",
+      " decoder_stage4_upsampling   (None, None, None, 32)       0         ['decoder_stage3b_relu[0][0]']\n",
+      " (UpSampling2D)                                                                                   \n",
+      "                                                                                                  \n",
+      " decoder_stage4a_conv (Conv  (None, None, None, 16)       4608      ['decoder_stage4_upsampling[0]\n",
+      " 2D)                                                                [0]']                         \n",
+      "                                                                                                  \n",
+      " decoder_stage4a_bn (BatchN  (None, None, None, 16)       64        ['decoder_stage4a_conv[0][0]']\n"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      " ormalization)                                                                                    \n",
+      "                                                                                                  \n",
+      " decoder_stage4a_relu (Acti  (None, None, None, 16)       0         ['decoder_stage4a_bn[0][0]']  \n",
+      " vation)                                                                                          \n",
+      "                                                                                                  \n",
+      " decoder_stage4b_conv (Conv  (None, None, None, 16)       2304      ['decoder_stage4a_relu[0][0]']\n",
+      " 2D)                                                                                              \n",
+      "                                                                                                  \n",
+      " decoder_stage4b_bn (BatchN  (None, None, None, 16)       64        ['decoder_stage4b_conv[0][0]']\n",
+      " ormalization)                                                                                    \n",
+      "                                                                                                  \n",
+      " decoder_stage4b_relu (Acti  (None, None, None, 16)       0         ['decoder_stage4b_bn[0][0]']  \n",
+      " vation)                                                                                          \n",
+      "                                                                                                  \n",
+      " final_conv (Conv2D)         (None, None, None, 3)        435       ['decoder_stage4b_relu[0][0]']\n",
+      "                                                                                                  \n",
+      " sigmoid (Activation)        (None, None, None, 3)        0         ['final_conv[0][0]']          \n",
+      "                                                                                                  \n",
+      "==================================================================================================\n",
+      "Total params: 23752563 (90.61 MB)\n",
+      "Trainable params: 23748531 (90.59 MB)\n",
+      "Non-trainable params: 4032 (15.75 KB)\n",
+      "__________________________________________________________________________________________________\n",
+      "None\n"
+     ]
+    }
+   ],
+   "source": [
+    "BACKBONE2 = 'vgg16' #pre trained model\n",
+    "\n",
+    "vgg16_BB = sm.Unet(BACKBONE2, encoder_weights='imagenet', classes=3) #pre trained weights on imagenet\n",
+    "\n",
+    "vgg16_BB.compile(optimizer='adam',\n",
+    "              loss=tf.keras.losses.SparseCategoricalCrossentropy(from_logits=True),\n",
+    "              metrics=['accuracy'])\n",
+    "\n",
+    "print(vgg16_BB.summary())"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 34,
+   "id": "ef269533",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "22/22 [==============================] - 510s 22s/step - loss: 0.4795 - accuracy: 0.9011\n"
+     ]
+    }
+   ],
+   "source": [
+    "history2 = vgg16_BB.fit(train_dataset_batchsize16, epochs=1)\n",
+    "#epoch is set to 1, due to low computational power\n",
+    "#users can increase the no. of epochs to 40 for good accuracy"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 35,
+   "id": "584a73ba",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "vgg16_BB.save('vgg16_BB_batch16.h5') #saving the model"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 63,
+   "id": "db931af6",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "test_dataset = processed_ds_test.batch(32) #seperated into batches of size 32"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "a8ca5ff5",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "resnet50_BB.evaluate(test_dataset, batch_size = 32, verbose = True) #for evaluating the model accuracy "
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "d1e16f87",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "show_predictions(train_dataset, 1)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 67,
+   "id": "58781d23",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "val_real_image = np.empty([0, 256, 256, 3])\n",
+    "val_real_mask = np.empty([0, 256, 256, 1])\n",
+    "\n",
+    "for img, mask in val_dataset:\n",
+    "    val_real_image = np.append(val_real_image, img, axis = 0)\n",
+    "    val_real_mask = np.append(val_real_mask, mask, axis = 0)\n",
+    "\n",
+    "val_real_mask_sq = np.reshape(np.squeeze(val_real_mask), (val_real_mask.shape[0], -1))\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 80,
+   "id": "388e575e",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "5/5 [==============================] - 18s 3s/step\n"
+     ]
+    }
+   ],
+   "source": [
+    "val_results = np.argmax(unet.predict(val_dataset), axis=-1) #axis=-1 represents the last axis\n",
+    "val_results = val_results[..., tf.newaxis]\n",
+    "val_results_sq = np.reshape(np.squeeze(val_results), (val_results.shape[0], -1))\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "d7f1ef1c",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "#code for obtaining confusion matrix for the required model\n",
+    "#confusion matrix can be changed by changing unet.predict with (required model).predict\n",
+    "cm = confusion_matrix(val_real_mask_sq.reshape(-1), val_results_sq.reshape(-1))\n",
+    "cmn = cm.astype('float') / cm.sum(axis=1)[:, np.newaxis]\n",
+    "\n",
+    "cm_df = pd.DataFrame(cmn,index = ['No Defect','Scratch','Stain'], columns = ['No Defect','Scratch','Stain'])\n",
+    "\n",
+    "fig, ax = plt.subplots(figsize=(10,8))\n",
+    "sns.heatmap(cm_df, annot=True, fmt='.2%', annot_kws={\"size\": 20})\n",
+    "plt.ylabel('Actual')\n",
+    "plt.xlabel('Predicted')"
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3 (ipykernel)",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.11.5"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}
diff --git a/Heat sink defect detection/requirements.txt b/Heat sink defect detection/requirements.txt
new file mode 100644
index 000000000..48528333a
--- /dev/null
+++ b/Heat sink defect detection/requirements.txt	
@@ -0,0 +1,9 @@
+imageio==2.26.0
+keras==2.15.0
+matplotlib==3.7.2
+numpy==1.24.3
+pandas==2.0.3
+scikit-learn==1.3.0
+seaborn==0.12.2
+segmentation-models==1.0.1
+tensorflow==2.15.0