Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

fix bugs: fix some bugs in loading data #774

Merged
merged 1 commit into from
Apr 26, 2024
Merged

fix bugs: fix some bugs in loading data #774

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
49 changes: 29 additions & 20 deletions docs/en/how_to_guides/finetune_with_a_custom_dataset.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -55,21 +55,24 @@ DATASET_NAME
Next, we'll take the annotation file ./aircraft/data/images_variant_trainval.txt as an example, locally generate the file of train set ./aircraft/data/images/trainval/, which meets the request of a tree-structure directory.

```python
import shutil
import os
import shutil


# only for Aircraft dataset but not a general one
def extract_images(images_path, subset_name, annotation_file_path, copy=True):
# read the annotation file to get the label of each image
def annotations(annotation_file_path):
image_label = {}
for i in open(annotation_file_path, "r"):
label = " ".join(i.split(" ")[1:]).replace("\n", "").replace("/", "_")
if label not in image_label.keys():
image_label[label] = []
image_label[label].append(i.split(" ")[0])
else:
image_label[label].append(i.split(" ")[0])
with open(annotation_file_path, "r") as f:
lines = f.readlines()
for line in lines:
label = " ".join(line.split(" ")[1:]).replace("\n", "").replace("/", "_")
if label not in image_label.keys():
image_label[label] = []
image_label[label].append(line.split(" ")[0])
else:
image_label[label].append(line.split(" ")[0])
return image_label

# make a new folder for subset
Expand All @@ -89,6 +92,7 @@ def extract_images(images_path, subset_name, annotation_file_path, copy=True):
shutil.move(images_path + image_name, label_folder)


# take train set of aircraft dataset as an example
images_path = "./aircraft/data/images/"
subset_name = "trainval"
annotation_file_path = "./aircraft/data/images_variant_trainval.txt"
Expand Down Expand Up @@ -138,18 +142,21 @@ Here's how we generate a random-accessible dataset object that stores the images

```python
import numpy as np

from mindspore.dataset import GeneratorDataset


class ImageClsDataset:
def __init__(self, annotation_dir, images_dir):
# Read annotations
self.annotation = {}
for i in open(annotation_dir, "r"):
image_label = i.replace("\n", "").replace("/", "_").split(" ")
image = image_label[0] + ".jpg"
label = " ".join(image_label[1:])
self.annotation[image] = label
with open(annotation_dir, "r") as f:
lines = f.readlines()
for line in lines:
image_label = line.replace("\n", "").replace("/", "_").split(" ")
image = image_label[0] + ".jpg"
label = " ".join(image_label[1:])
self.annotation[image] = label

# Transfer string-type label to int-type label
self.label2id = {}
Expand All @@ -161,13 +168,13 @@ class ImageClsDataset:
self.annotation[image] = self.label2id[label]

# Read image-labels as mappable object
images = dict.fromkeys(self.label2id.values(), [])
label2images = {key: [] for key in self.label2id.values()}
for image, label in self.annotation.items():
read_image = np.fromfile(images_dir + image, dtype=np.uint8)
images[label].append(read_image)
label2images[label].append(read_image)

self._data = sum(list(images.values()), [])
self._label = sum([[i] * len(images[i]) for i in images.keys()], [])
self._data = sum(list(label2images.values()), [])
self._label = sum([[i] * len(label2images[i]) for i in label2images.keys()], [])

# make class ImageClsDataset a mappable object
def __getitem__(self, index):
Expand All @@ -176,10 +183,12 @@ class ImageClsDataset:
def __len__(self):
return len(self._data)


# take aircraft dataset as an example
annotation_dir = "./aircraft/data/images_variant_trainval.txt"
images_dir = "./aircraft/data/iamges/"
dataset = ImageClsDataset(annotation_dir)
ataset_train = GeneratorDataset(source=dataset, column_names=["image", "label"], shuffle=True)
images_dir = "./aircraft/data/images/"
dataset = ImageClsDataset(annotation_dir, images_dir)
dataset_train = GeneratorDataset(source=dataset, column_names=["image", "label"], shuffle=True)
```

Compared with the offline way, the online way skipped the step of splitting the data file locally and reading the local file with the `create_dataset` function. So in the subsequent training, simply **replace the part of finetune.py that uses `create_dataset` with the above code**, then you can start training by running finetune.py directly as what you do after reading the dataset offline.
Expand Down
47 changes: 28 additions & 19 deletions docs/zh/how_to_guides/finetune_with_a_custom_dataset.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -55,21 +55,25 @@ DATASET_NAME
接下来以说明文件./aircraft/data/images_variant_trainval.txt 为例，在本地生成满足前述树状结构的训练集文件 ./aircraft/data/images/trainval/。

```python
import shutil
""" Extract images and generate ImageNet-style dataset directory """
import os
import shutil


# only for Aircraft dataset but not a general one
def extract_images(images_path, subset_name, annotation_file_path, copy=True):
# read the annotation file to get the label of each image
def annotations(annotation_file_path):
image_label = {}
for i in open(annotation_file_path, "r"):
label = " ".join(i.split(" ")[1:]).replace("\n", "").replace("/", "_")
if label not in image_label.keys():
image_label[label] = []
image_label[label].append(i.split(" ")[0])
else:
image_label[label].append(i.split(" ")[0])
with open(annotation_file_path, "r") as f:
lines = f.readlines()
for line in lines:
label = " ".join(line.split(" ")[1:]).replace("\n", "").replace("/", "_")
if label not in image_label.keys():
image_label[label] = []
image_label[label].append(line.split(" ")[0])
else:
image_label[label].append(line.split(" ")[0])
return image_label

# make a new folder for subset
Expand All @@ -89,6 +93,7 @@ def extract_images(images_path, subset_name, annotation_file_path, copy=True):
shutil.move(images_path + image_name, label_folder)


# take train set of aircraft dataset as an example
images_path = "./aircraft/data/images/"
subset_name = "trainval"
annotation_file_path = "./aircraft/data/images_variant_trainval.txt"
Expand Down Expand Up @@ -143,18 +148,21 @@ aircraft

```python
import numpy as np

from mindspore.dataset import GeneratorDataset


class ImageClsDataset:
def __init__(self, annotation_dir, images_dir):
# Read annotations
self.annotation = {}
for i in open(annotation_dir, "r"):
image_label = i.replace("\n", "").replace("/", "_").split(" ")
image = image_label[0] + ".jpg"
label = " ".join(image_label[1:])
self.annotation[image] = label
with open(annotation_dir, "r") as f:
lines = f.readlines()
for line in lines:
image_label = line.replace("\n", "").replace("/", "_").split(" ")
image = image_label[0] + ".jpg"
label = " ".join(image_label[1:])
self.annotation[image] = label

# Transfer string-type label to int-type label
self.label2id = {}
Expand All @@ -166,13 +174,13 @@ class ImageClsDataset:
self.annotation[image] = self.label2id[label]

# Read image-labels as mappable object
images = dict.fromkeys(self.label2id.values(), [])
label2images = {key: [] for key in self.label2id.values()}
for image, label in self.annotation.items():
read_image = np.fromfile(images_dir + image, dtype=np.uint8)
images[label].append(read_image)
label2images[label].append(read_image)

self._data = sum(list(images.values()), [])
self._label = sum([[i] * len(images[i]) for i in images.keys()], [])
self._data = sum(list(label2images.values()), [])
self._label = sum([[i] * len(label2images[i]) for i in label2images.keys()], [])

# make class ImageClsDataset a mappable object
def __getitem__(self, index):
Expand All @@ -182,9 +190,10 @@ class ImageClsDataset:
return len(self._data)


# take aircraft dataset as an example
annotation_dir = "./aircraft/data/images_variant_trainval.txt"
images_dir = "./aircraft/data/iamges/"
dataset = ImageClsDataset(annotation_dir)
images_dir = "./aircraft/data/images/"
dataset = ImageClsDataset(annotation_dir, images_dir)
dataset_train = GeneratorDataset(source=dataset, column_names=["image", "label"], shuffle=True)

```
Expand Down
28 changes: 15 additions & 13 deletions examples/finetune/read_images_online.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -8,11 +8,13 @@ class ImageClsDataset:
def __init__(self, annotation_dir, images_dir):
# Read annotations
self.annotation = {}
for i in open(annotation_dir, "r"):
image_label = i.replace("\n", "").replace("/", "_").split(" ")
image = image_label[0] + ".jpg"
label = " ".join(image_label[1:])
self.annotation[image] = label
with open(annotation_dir, "r") as f:
lines = f.readlines()
for line in lines:
image_label = line.replace("\n", "").replace("/", "_").split(" ")
image = image_label[0] + ".jpg"
label = " ".join(image_label[1:])
self.annotation[image] = label

# Transfer string-type label to int-type label
self.label2id = {}
Expand All @@ -23,16 +25,16 @@ def __init__(self, annotation_dir, images_dir):
for image, label in self.annotation.items():
self.annotation[image] = self.label2id[label]

# Read image-labels as iterable object
images = dict.fromkeys(self.label2id.values(), [])
# Read image-labels as mappable object
label2images = {key: [] for key in self.label2id.values()}
for image, label in self.annotation.items():
read_image = np.fromfile(images_dir + image, dtype=np.uint8)
images[label].append(read_image)
label2images[label].append(read_image)

self._data = sum(list(images.values()), [])
self._label = sum([[i] * len(images[i]) for i in images.keys()], [])
self._data = sum(list(label2images.values()), [])
self._label = sum([[i] * len(label2images[i]) for i in label2images.keys()], [])

# make class ImageClsDataset an iterable object
# make class ImageClsDataset a mappable object
def __getitem__(self, index):
return self._data[index], self._label[index]

Expand All @@ -42,6 +44,6 @@ def __len__(self):

# take aircraft dataset as an example
annotation_dir = "./aircraft/data/images_variant_trainval.txt"
images_dir = "./aircraft/data/iamges/"
dataset = ImageClsDataset(annotation_dir)
images_dir = "./aircraft/data/images/"
dataset = ImageClsDataset(annotation_dir, images_dir)
dataset_train = GeneratorDataset(source=dataset, column_names=["image", "label"], shuffle=True)
16 changes: 9 additions & 7 deletions examples/finetune/split_files.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -8,13 +8,15 @@ def extract_images(images_path, subset_name, annotation_file_path, copy=True):
# read the annotation file to get the label of each image
def annotations(annotation_file_path):
image_label = {}
for i in open(annotation_file_path, "r"):
label = " ".join(i.split(" ")[1:]).replace("\n", "").replace("/", "_")
if label not in image_label.keys():
image_label[label] = []
image_label[label].append(i.split(" ")[0])
else:
image_label[label].append(i.split(" ")[0])
with open(annotation_file_path, "r") as f:
lines = f.readlines()
for line in lines:
label = " ".join(line.split(" ")[1:]).replace("\n", "").replace("/", "_")
if label not in image_label.keys():
image_label[label] = []
image_label[label].append(line.split(" ")[0])
else:
image_label[label].append(line.split(" ")[0])
return image_label

# make a new folder for subset
Expand Down
Loading