I have a neural network for image processing. All images are greyscaled,resized and labeled. I made a neural network model in PyTorch.
class CarBrand(nn.Module):
def __init__(self, num_classes):
super(CarBrand, self).__init__()
self.conv1 = nn.Conv2d(in_channels=1, out_channels=32, kernel_size=3, padding=1)
self.conv2 = nn.Conv2d(in_channels=32, out_channels=64, kernel_size=3, padding=1)
self.conv3 = nn.Conv2d(in_channels=64, out_channels=128, kernel_size=3, padding=1)
self.fc1 = nn.Linear(128*300*300*1, 512) # fully connected layers
self.fc2_class = nn.Linear(512, num_classes)
self.relu = nn.ReLU()
self.maxpool = nn.MaxPool2d(kernel_size=2, stride=2)
def forward(self, x):
x = self.relu(self.conv1(x))
x = self.maxpool(x)
x = self.relu(self.conv2(x))
x = self.maxpool(x)
x = self.relu(self.conv3(x))
x = self.maxpool(x)
x = x.view(x.size(0), -1)
x = self.relu(self.fc1(x))
brand_pred = self.fc2_class(x)
return brand_pred
class CarBrandDataset(Dataset):
def __init__(self, data_dir, transform=None):
self.data_dir = data_dir
self.transform = transform
self.image_paths = [filename for filename in os.listdir(data_dir) if filename.endswith('.jpg')]
def __len__(self):
return len(self.image_paths)
def __getitem__(self, index):
image_path = os.path.join(self.data_dir, self.image_paths[index])
xml_path = os.path.splitext(image_path)[0] + '.xml'
image = Image.open(image_path).convert('L') # convert to greyscale
if self.transform:
image.transform(image.size, Image.AFFINE, image)
# parse XML
tree = ET.parse(xml_path)
root = tree.getroot()
# extract label information from XML
brand_label_mapping = {
'bmw': 0,
'citroen': 1,
'mercedes': 2,
'maserati': 3,
'audi': 4,
'honda': 5
}
brand_label_str = root.text
brand_label = brand_label_mapping.get(brand_label_str, -1)
return image, brand_label
transform = transforms.Compose([
transforms.ToTensor(),
transforms.Normalize(mean=[0.5], std=[0.5]),
transforms.Resize(300)
])
data_dir = "split_data/train"
dataset = CarBrandDataset(data_dir, transform=transform)
batch_size = 32
dataloader = DataLoader(dataset, batch_size=batch_size, shuffle=True)
When I start train it ,
running_loss = 0.0
for images, brand_labels in dataloader:
optimizer.zero_grad()
brand_pred = model(images)
loss_brand = criterion_class(brand_pred, brand_labels)
loss_brand.backward()
optimizer.step()
running_loss += loss_brand.item()
I get this error, I tried to fix it but I couldn't manage to do that.
C:\Users\Cihan\AppData\Local\Temp\ipykernel_17820\2575177316.py:23: DeprecationWarning: AFFINE is deprecated and will be removed in Pillow 10 (2023-07-01). Use Transform.AFFINE instead.
image.transform(image.size, Image.AFFINE, image)
---------------------------------------------------------------------------
TypeError Traceback (most recent call last)
Cell In[20], line 9
7 for epoch in range(num_epochs):
8 running_loss = 0.0
----> 9 for images, brand_labels in dataloader:
10 optimizer.zero_grad()
12 brand_pred = model(images)
File ~\OneDrive\Masaüstü\plate\pytorchNN\Lib\site-packages\torch\utils\data\dataloader.py:633, in _BaseDataLoaderIter.__next__(self)
630 if self._sampler_iter is None:
631 # TODO(https://github.com/pytorch/pytorch/issues/76750)
632 self._reset() # type: ignore[call-arg]
--> 633 data = self._next_data()
634 self._num_yielded += 1
635 if self._dataset_kind == _DatasetKind.Iterable and \
636 self._IterableDataset_len_called is not None and \
637 self._num_yielded > self._IterableDataset_len_called:
File ~\OneDrive\Masaüstü\plate\pytorchNN\Lib\site-packages\torch\utils\data\dataloader.py:677, in _SingleProcessDataLoaderIter._next_data(self)
675 def _next_data(self):
676 index = self._next_index() # may raise StopIteration
--> 677 data = self._dataset_fetcher.fetch(index) # may raise StopIteration
678 if self._pin_memory:
679 data = _utils.pin_memory.pin_memory(data, self._pin_memory_device)
File ~\OneDrive\Masaüstü\plate\pytorchNN\Lib\site-packages\torch\utils\data\_utils\fetch.py:51, in _MapDatasetFetcher.fetch(self, possibly_batched_index)
49 data = self.dataset.__getitems__(possibly_batched_index)
50 else:
---> 51 data = [self.dataset[idx] for idx in possibly_batched_index]
52 else:
53 data = self.dataset[possibly_batched_index]
File ~\OneDrive\Masaüstü\plate\pytorchNN\Lib\site-packages\torch\utils\data\_utils\fetch.py:51, in <listcomp>(.0)
49 data = self.dataset.__getitems__(possibly_batched_index)
50 else:
---> 51 data = [self.dataset[idx] for idx in possibly_batched_index]
52 else:
53 data = self.dataset[possibly_batched_index]
Cell In[16], line 23, in CarBrandDataset.__getitem__(self, index)
21 image = Image.open(image_path).convert('L') # convert to greyscale
22 if self.transform:
---> 23 image.transform(image.size, Image.AFFINE, image)
24 # if self.transform:
25 # image = self.transform(image)
26
27 # parse XML
28 tree = ET.parse(xml_path)
File ~\OneDrive\Masaüstü\plate\pytorchNN\Lib\site-packages\PIL\Image.py:2631, in Image.transform(self, size, method, data, resample, fill, fillcolor)
2627 im.__transformer(
2628 box, self, Transform.QUAD, quad, resample, fillcolor is None
2629 )
2630 else:
-> 2631 im.__transformer(
2632 (0, 0) + size, self, method, data, resample, fillcolor is None
2633 )
2635 return im
File ~\OneDrive\Masaüstü\plate\pytorchNN\Lib\site-packages\PIL\Image.py:2644, in Image.__transformer(self, box, image, method, data, resample, fill)
2641 h = box[3] - box[1]
2643 if method == Transform.AFFINE:
-> 2644 data = data[:6]
2646 elif method == Transform.EXTENT:
2647 # convert extent to an affine transform
2648 x0, y0, x1, y1 = data
TypeError: 'Image' object is not subscriptable*
I have tried converting image object to a numpy array but it did not work, I have no idea what should I do in order to solve that problem. Edit:I added 'dataloader', sorry I forgot to add it.
