Custom dataset Loader pytorch - machine-learning

Question

i am doing covid-19 classification.i took dataset from kaggle. it has folder named dataset which contain 3 folders normal pnuemonia and covid-19 each contaning images for these classes i am stucked in writting getitem in pytorch custom dataloader ?
Dataset has 189 covid images but by this get item i get 920 images of covid kindly help
class_names = ['normal', 'viral', 'covid']
root_dir = 'COVID-19 Radiography Database'
source_dirs = ['NORMAL', 'Viral Pneumonia', 'COVID-19']
if os.path.isdir(os.path.join(root_dir, source_dirs[1])):
os.mkdir(os.path.join(root_dir, 'test'))
for i, d in enumerate(source_dirs):
os.rename(os.path.join(root_dir, d), os.path.join(root_dir, class_names[i]))
for c in class_names:
os.mkdir(os.path.join(root_dir, 'test', c))
for c in class_names:
images = [x for x in os.listdir(os.path.join(root_dir, c)) if x.lower().endswith('png')]
selected_images = random.sample(images, 30)
for image in selected_images:
source_path = os.path.join(root_dir, c, image)
target_path = os.path.join(root_dir, 'test', c, image)
shutil.move(source_path, target_path)
Above code is used to create test dataset which has 30 images of each class
class ChestXRayDataset(torch.utils.data.Dataset):
def __init__(self, image_dirs, transform):
def get_images(class_name):
images = [x for x in os.listdir(image_dirs[class_name]) if
x[-3:].lower().endswith('png')]
print(f'Found {len(images)} {class_name} examples')
return images
self.images = {}
self.class_names = ['normal', 'viral', 'covid']
for class_name in self.class_names:
self.images[class_name] = get_images(class_name)
self.image_dirs = image_dirs
self.transform = transform
def __len__(self):
return sum([len(self.images[class_name]) for class_name in self.class_names])
def __getitem__(self, index):
class_name = random.choice(self.class_names)
index = index % len(self.images[class_name])
image_name = self.images[class_name][index]
image_path = os.path.join(self.image_dirs[class_name], image_name)
image = Image.open(image_path).convert('RGB')
return self.transform(image), self.class_names.index(class_name)
**Stucked in get item of this **
images in folder are arranged as follows
Dataset is as follows
**Code for confusion matrix is **
nb_classes = 3
confusion_matrix = torch.zeros(nb_classes, nb_classes)
with torch.no_grad():
for data in tqdm_notebook(dl_train,total=len(dl_train),unit='batch'):
img,lab = data
print(lab)
img,lab = img.to(device),lab.to(device)
_,output = torch.max(model(img),1)
print(output)
for t, p in zip(lab.view(-1), output.view(-1)):
confusion_matrix[t.long(), p.long()] += 1
output for confusion matrix only one class is getting trained
confusio matrix image

Answer 1

Putting you images in a dictionary complicates the manipulation, rather use a list. Also you Dataset should not have any randomness, shuffling of the data should happen from the DataLoader not from the Dataset.
Use something like below:
class ChestXRayDataset(torch.utils.data.Dataset):
def __init__(self, image_dirs, transform):
def get_images(class_name):
images = [x for x in os.listdir(image_dirs[class_name]) if
x[-3:].lower().endswith('png')]
print(f'Found {len(images)} {class_name} examples')
return images
self.images = []
self.labels = []
self.class_names = ['normal', 'viral', 'covid']
for class_name in self.class_names:
images = get_images(class_name)
# This is a list containing all the images
self.images.extend(images)
# This is a list containing all the corresponding image labels
self.labels.extend([class_name]*len(images))
self.image_dirs = image_dirs
self.transform = transform
def __len__(self):
return len(self.images)
# Will return the image and its label at the position `index`
def __getitem__(self, index):
# image at index position of all the images
image_name = self.images[index]
# Its label
class_name = self.labels[index]
image_path = os.path.join(self.image_dirs[class_name], image_name)
image = Image.open(image_path).convert('RGB')
return self.transform(image), self.class_names.index(class_name)
If you enumerate it say using
ds = ChestXRayDataset(image_dirs, transform)
for x, y in ds:
print (x.shape, y)
You should see all the images and the labels in the sequential order.
However in real case you would rather use a Torch DataLoader and pass it the ds object with shuffle parameter set to True. So the DataLoader will take care of shuffling the Dataset by calling the __getitem__ with shuffled index values.