How to build for pytorch CNN model for color images

1

Hi, I am newbie the PyTorch, I am trying to build a CNN model for the Image classification problem, but getting some error.
Here My code:

file_path='dataset'
train=pd.read_csv('dataset/train.csv')
test=pd.read_csv('dataset/test.csv')
train_img = []
for img_name in tqdm(train['Image']):
    # defining the image path
    img_path=os.path.join(file_path,'Train Images',img_name)
    # reading the image
    img=cv2.imread(img_path)
    img=cv2.resize(img,(64,64))
    # appending the image into the list
    train_img.append(img)

# converting the list to numpy array
train_x = np.array(train_img)
train_x, val_x, train_y, y_val = train_test_split(train_x, y, test_size = 0.1)
train_x  = torch.from_numpy(np.array(train_x))

# converting the target into torch format
train_y = torch.from_numpy(np.array(train_y))

Here My model.

import torch.nn as nn
import torch.nn.functional as F
class Net(Module):
  def __init__(self):
    super(Net,self).__init__()
    self.conv1=nn.Conv2d(3,64,5)
    self.pool=nn.MaxPool2d(2, 2)
    self.conv2=nn.Conv2d(64,128,5)
    self.fc1 = nn.Linear(4 * 8 * 8, 120)
    self.fc2 = nn.Linear(120, 84)
    self.fc3 = nn.Linear(84, 4)
  def forward(self, x):
        x = self.pool(F.relu(self.conv1(x)))
        x = self.pool(F.relu(self.conv2(x)))
        x = x.view(-1, 8* 8 * 5)
        x = F.relu(self.fc1(x))
        x = F.relu(self.fc2(x))
        x = self.fc3(x)
        return x
model=Net()
optimizer = Adam(model.parameters(), lr=0.07)
# defining the loss function
criterion = CrossEntropyLoss()
# checking if GPU is available
if torch.cuda.is_available():
    model = model.cuda()
    criterion = criterion.cuda()
    
print(model)
def train(epoch):
    model.train()
    tr_loss = 0
    # getting the training set
    x_train, y_train = Variable(train_x), Variable(train_y)
    # getting the validation set
    x_val, y_val = Variable(val_x), Variable(val_y)
    # converting the data into GPU format
    if torch.cuda.is_available():
        x_train = x_train.cuda()
        y_train = y_train.cuda()
        x_val = x_val.cuda()
        y_val = y_val.cuda()

    # clearing the Gradients of the model parameters
    optimizer.zero_grad()
    
    # prediction for training and validation set
    output_train = model(x_train)
    output_val = model(x_val)

    # computing the training and validation loss
    loss_train = criterion(output_train, y_train)
    loss_val = criterion(output_val, y_val)
    train_losses.append(loss_train)
    val_losses.append(loss_val)

    # computing the updated weights of all the model parameters
    loss_train.backward()
    optimizer.step()
    tr_loss = loss_train.item()
    if epoch%2 == 0:
        # printing the validation loss
        print('Epoch : ',epoch+1, '\t', 'loss :', loss_val)
n_epochs = 25
# empty list to store training losses
train_losses = []
# empty list to store validation losses
val_losses = []
# training the model
for epoch in range(n_epochs):
    train(epoch)

Here the Error:

340                             _pair(0), self.dilation, self.groups)
    341         return F.conv2d(input, weight, self.bias, self.stride,
--> 342                         self.padding, self.dilation, self.groups)
    343 
    344     def forward(self, input):

RuntimeError: Given groups=1, weight of size 64 3 5 5, expected input[5384, 64, 64, 3] to have 3 channels, but got 64 channels instead
2

You need to transpose your image dimensions. PyTorch expect (3, 64, 64) as shape and you are inputting (64, 64, 3).

You can use np.transpose to correct this.

1 Like
3

Hi fs4ss1,
I change image data shape, but still, it showing the same error.

data=train_x.transpose((2, 1,3, 0))
data.shape
(64, 64, 3, 5384)
4

Pytorch Conv layers expect the shape to be [B, C, H, W](in ur case: [5384, 3, 64, 64]); however, ur shape is [H, W, C, B](64, 64, 3, 5384), and ur original shape should be [B, H, W, C]([5384, 64, 64, 3]).

1 Like