basic_covid_model.ipynb

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 1,
   "id": "98c60f02",
   "metadata": {},
   "outputs": [],
   "source": [
    "import numpy as np\n",
    "import time\n",
    "\n",
    "import PIL.Image as Image\n",
    "import matplotlib.pylab as plt\n",
    "\n",
    "import tensorflow as tf\n",
    "import tensorflow_hub as hub\n",
    "\n",
    "import datetime\n",
    "\n",
    "%load_ext tensorboard\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "id": "d30ceba5",
   "metadata": {},
   "outputs": [],
   "source": [
    "mobilenet_v2 =\"https://tfhub.dev/google/tf2-preview/mobilenet_v2/classification/4\"\n",
    "inception_v3 = \"https://tfhub.dev/google/imagenet/inception_v3/classification/5\"\n",
    "\n",
    "classifier_model = mobilenet_v2\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "id": "b61bee02",
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "2022-08-08 05:41:22.655132: I tensorflow/core/common_runtime/pluggable_device/pluggable_device_factory.cc:305] Could not identify NUMA node of platform GPU ID 0, defaulting to 0. Your kernel may not have been built with NUMA support.\n",
      "2022-08-08 05:41:22.655232: I tensorflow/core/common_runtime/pluggable_device/pluggable_device_factory.cc:271] Created TensorFlow device (/job:localhost/replica:0/task:0/device:GPU:0 with 0 MB memory) -> physical PluggableDevice (device: 0, name: METAL, pci bus id: <undefined>)\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Metal device set to: Apple M1\n"
     ]
    }
   ],
   "source": [
    "IMAGE_SHAPE = (224, 224)\n",
    "\n",
    "classifier = tf.keras.Sequential([\n",
    "    hub.KerasLayer(classifier_model, input_shape=IMAGE_SHAPE+(3,))\n",
    "])\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "id": "4c22f1c8",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Found 2141 files belonging to 2 classes.\n",
      "Using 1927 files for training.\n",
      "Found 2141 files belonging to 2 classes.\n",
      "Using 214 files for validation.\n"
     ]
    }
   ],
   "source": [
    "batch_size = 32\n",
    "img_height = 224\n",
    "img_width = 224\n",
    "data_root = r\"COVID_dataset\"\n",
    "\n",
    "\n",
    "train_ds = tf.keras.utils.image_dataset_from_directory(\n",
    "  str(data_root),\n",
    "  validation_split=0.1,\n",
    "  subset=\"training\",\n",
    "  seed=123,\n",
    "  image_size=(img_height, img_width),\n",
    "  batch_size=batch_size\n",
    ")\n",
    "\n",
    "val_ds = tf.keras.utils.image_dataset_from_directory(\n",
    "  str(data_root),\n",
    "  validation_split=0.1,\n",
    "  subset=\"validation\",\n",
    "  seed=123,\n",
    "  image_size=(img_height, img_width),\n",
    "  batch_size=batch_size\n",
    ")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "id": "a35a14f8",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "['COVID19' 'NORMAL']\n"
     ]
    }
   ],
   "source": [
    "class_names = np.array(train_ds.class_names)\n",
    "print(class_names)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "id": "30294621",
   "metadata": {},
   "outputs": [],
   "source": [
    "normalization_layer = tf.keras.layers.Rescaling(1./255)\n",
    "train_ds = train_ds.map(lambda x, y: (normalization_layer(x), y)) # Where x—images, y—labels.\n",
    "val_ds = val_ds.map(lambda x, y: (normalization_layer(x), y)) # Where x—images, y—labels."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "id": "1fb79e1b",
   "metadata": {},
   "outputs": [],
   "source": [
    "AUTOTUNE = tf.data.AUTOTUNE\n",
    "train_ds = train_ds.cache().prefetch(buffer_size=AUTOTUNE)\n",
    "val_ds = val_ds.cache().prefetch(buffer_size=AUTOTUNE)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "id": "14e6eba8",
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "2022-08-08 05:41:46.734801: W tensorflow/core/platform/profile_utils/cpu_utils.cc:128] Failed to get CPU frequency: 0 Hz\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "(32, 224, 224, 3)\n",
      "(32,)\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "2022-08-08 05:41:47.916753: W tensorflow/core/kernels/data/cache_dataset_ops.cc:856] The calling iterator did not fully read the dataset being cached. In order to avoid unexpected truncation of the dataset, the partially cached contents of the dataset  will be discarded. This can happen if you have an input pipeline similar to `dataset.cache().take(k).repeat()`. You should use `dataset.take(k).cache().repeat()` instead.\n"
     ]
    }
   ],
   "source": [
    "for image_batch, labels_batch in train_ds:\n",
    "  print(image_batch.shape)\n",
    "  print(labels_batch.shape)\n",
    "  break"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "id": "5f7c489d",
   "metadata": {},
   "outputs": [],
   "source": [
    "mobilenet_v2 = \"https://tfhub.dev/google/tf2-preview/mobilenet_v2/feature_vector/4\"\n",
    "inception_v3 = \"https://tfhub.dev/google/tf2-preview/inception_v3/feature_vector/4\"\n",
    "\n",
    "feature_extractor_model = mobilenet_v2"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "id": "2d789cb3",
   "metadata": {},
   "outputs": [],
   "source": [
    "feature_extractor_layer = hub.KerasLayer(\n",
    "    feature_extractor_model,\n",
    "    input_shape=(224, 224, 3),\n",
    "    trainable=False)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "id": "5dc87d8d",
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "2022-08-08 05:41:55.116231: I tensorflow/core/grappler/optimizers/custom_graph_optimizer_registry.cc:113] Plugin optimizer for device_type GPU is enabled.\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "(32, 1280)\n"
     ]
    }
   ],
   "source": [
    "feature_batch = feature_extractor_layer(image_batch)\n",
    "print(feature_batch.shape)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "id": "d53c1466",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Model: \"sequential_1\"\n",
      "_________________________________________________________________\n",
      " Layer (type)                Output Shape              Param #   \n",
      "=================================================================\n",
      " keras_layer_1 (KerasLayer)  (None, 1280)              2257984   \n",
      "                                                                 \n",
      " dense (Dense)               (None, 2)                 2562      \n",
      "                                                                 \n",
      "=================================================================\n",
      "Total params: 2,260,546\n",
      "Trainable params: 2,562\n",
      "Non-trainable params: 2,257,984\n",
      "_________________________________________________________________\n"
     ]
    }
   ],
   "source": [
    "num_classes = len(class_names)\n",
    "\n",
    "model = tf.keras.Sequential([\n",
    "  feature_extractor_layer,\n",
    "  tf.keras.layers.Dense(num_classes)\n",
    "])\n",
    "\n",
    "model.summary()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "id": "66921458",
   "metadata": {},
   "outputs": [],
   "source": [
    "predictions = model(image_batch)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 14,
   "id": "e441aeb3",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "TensorShape([32, 2])"
      ]
     },
     "execution_count": 14,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "predictions.shape"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 15,
   "id": "2c996773",
   "metadata": {},
   "outputs": [],
   "source": [
    "model.compile(\n",
    "  optimizer=tf.keras.optimizers.Adam(),\n",
    "  loss=tf.keras.losses.SparseCategoricalCrossentropy(from_logits=True),\n",
    "  metrics=['acc'])\n",
    "\n",
    "log_dir = \"logs/fit/\" + datetime.datetime.now().strftime(\"%Y%m%d-%H%M%S\")\n",
    "tensorboard_callback = tf.keras.callbacks.TensorBoard(\n",
    "    log_dir=log_dir,\n",
    "    histogram_freq=1) # Enable histogram computation for every epoch."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 16,
   "id": "d0614f14",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Epoch 1/10\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "2022-08-08 05:42:20.525039: I tensorflow/core/grappler/optimizers/custom_graph_optimizer_registry.cc:113] Plugin optimizer for device_type GPU is enabled.\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "61/61 [==============================] - ETA: 0s - loss: 0.1654 - acc: 0.9351"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "2022-08-08 05:43:11.663363: I tensorflow/core/grappler/optimizers/custom_graph_optimizer_registry.cc:113] Plugin optimizer for device_type GPU is enabled.\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "61/61 [==============================] - 66s 929ms/step - loss: 0.1654 - acc: 0.9351 - val_loss: 0.0485 - val_acc: 0.9813\n",
      "Epoch 2/10\n",
      "61/61 [==============================] - 35s 557ms/step - loss: 0.0442 - acc: 0.9891 - val_loss: 0.0312 - val_acc: 0.9860\n",
      "Epoch 3/10\n",
      "61/61 [==============================] - 33s 514ms/step - loss: 0.0311 - acc: 0.9912 - val_loss: 0.0226 - val_acc: 0.9907\n",
      "Epoch 4/10\n",
      "61/61 [==============================] - 29s 463ms/step - loss: 0.0234 - acc: 0.9948 - val_loss: 0.0176 - val_acc: 0.9953\n",
      "Epoch 5/10\n",
      "61/61 [==============================] - 28s 456ms/step - loss: 0.0184 - acc: 0.9953 - val_loss: 0.0143 - val_acc: 1.0000\n",
      "Epoch 6/10\n",
      "61/61 [==============================] - 28s 460ms/step - loss: 0.0151 - acc: 0.9979 - val_loss: 0.0119 - val_acc: 1.0000\n",
      "Epoch 7/10\n",
      "61/61 [==============================] - 28s 462ms/step - loss: 0.0126 - acc: 0.9984 - val_loss: 0.0102 - val_acc: 1.0000\n",
      "Epoch 8/10\n",
      "61/61 [==============================] - 30s 473ms/step - loss: 0.0107 - acc: 0.9990 - val_loss: 0.0089 - val_acc: 1.0000\n",
      "Epoch 9/10\n",
      "61/61 [==============================] - 30s 484ms/step - loss: 0.0093 - acc: 0.9990 - val_loss: 0.0078 - val_acc: 1.0000\n",
      "Epoch 10/10\n",
      "61/61 [==============================] - 27s 448ms/step - loss: 0.0081 - acc: 0.9990 - val_loss: 0.0069 - val_acc: 1.0000\n"
     ]
    }
   ],
   "source": [
    "NUM_EPOCHS = 10\n",
    "\n",
    "history = model.fit(train_ds,\n",
    "                    validation_data=val_ds,\n",
    "                    epochs=NUM_EPOCHS,\n",
    "                    callbacks=tensorboard_callback)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 17,
   "id": "deaa945e",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "INFO:tensorflow:Assets written to: models/basic_covid/1659959808/assets\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "INFO:tensorflow:Assets written to: models/basic_covid/1659959808/assets\n"
     ]
    },
    {
     "data": {
      "text/plain": [
       "'models/basic_covid/1659959808'"
      ]
     },
     "execution_count": 17,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "t = time.time()\n",
    "\n",
    "export_path = r\"models/basic_covid/{}\".format(int(t))\n",
    "model.save(export_path)\n",
    "model.save('model_{}.h5'.format(int(t)))\n",
    "\n",
    "export_path"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 18,
   "id": "b680f3c4",
   "metadata": {},
   "outputs": [],
   "source": [
    "import gradio as gr\n",
    "from tensorflow import keras\n",
    "from tensorflow.keras import layers\n",
    "from tensorflow.keras.models import Sequential"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 23,
   "id": "091d0a8f",
   "metadata": {},
   "outputs": [],
   "source": [
    "model = keras.models.load_model('models/basic_covid/1659959808')\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 24,
   "id": "6c6d331f",
   "metadata": {},
   "outputs": [],
   "source": [
    "class_names = ['COVID19','NORMAL']\n",
    "def predict_image(img):\n",
    "  img_4d=img.reshape((-1,224,224,3))\n",
    "    \n",
    "  prediction=model.predict(img_4d).flatten()\n",
    "  return {class_names[i]: float(prediction[i]) for i in range(2)}"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "369d54b1",
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "/Users/pips/Desktop/tf_files/lunghealth_tf/env/lib/python3.8/site-packages/gradio/inputs.py:256: UserWarning: Usage of gradio.inputs is deprecated, and will not be supported in the future, please import your component from gradio.components\n",
      "  warnings.warn(\n",
      "/Users/pips/Desktop/tf_files/lunghealth_tf/env/lib/python3.8/site-packages/gradio/deprecation.py:40: UserWarning: `optional` parameter is deprecated, and it has no effect\n",
      "  warnings.warn(value)\n",
      "/Users/pips/Desktop/tf_files/lunghealth_tf/env/lib/python3.8/site-packages/gradio/outputs.py:196: UserWarning: Usage of gradio.outputs is deprecated, and will not be supported in the future, please import your components from gradio.components\n",
      "  warnings.warn(\n",
      "/Users/pips/Desktop/tf_files/lunghealth_tf/env/lib/python3.8/site-packages/gradio/deprecation.py:40: UserWarning: The 'type' parameter has been deprecated. Use the Number component instead.\n",
      "  warnings.warn(value)\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Running on local URL:  http://127.0.0.1:7862/\n",
      "\n",
      "To create a public link, set `share=True` in `launch()`.\n"
     ]
    },
    {
     "data": {
      "text/html": [
       "<div><iframe src=\"http://127.0.0.1:7862/\" width=\"900\" height=\"500\" allow=\"autoplay; camera; microphone;\" frameborder=\"0\" allowfullscreen></iframe></div>"
      ],
      "text/plain": [
       "<IPython.core.display.HTML object>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "2022-08-08 05:59:55.745393: I tensorflow/core/grappler/optimizers/custom_graph_optimizer_registry.cc:113] Plugin optimizer for device_type GPU is enabled.\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "1/1 [==============================] - 2s 2s/step\n"
     ]
    }
   ],
   "source": [
    "image = gr.inputs.Image(shape=(224,224))\n",
    "label = gr.outputs.Label(num_top_classes=2)\n",
    "\n",
    "gr.Interface(fn=predict_image, inputs=image, outputs=label,interpretation='default').launch(debug='True')"
   ]
  }
 ],
 "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": "3.8.13"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}