CNN channels problem

hello everybody,
I am new to pytorch and had a problem with channels in AlexNet.
I am using it for a ‘gta san andreas self driving car’ project, I collected the dataset from a black and white image that has one channel and trying to train AlexNet using the script:

from AlexNetPytorch import*
import torchvision
import torchvision.transforms as transforms
import torch.optim as optim
import numpy as np
import torch
from IPython.core.debugger import set_trace

AlexNet = AlexNet()

criterion = nn.CrossEntropyLoss()
optimizer = optim.SGD(AlexNet.parameters(), lr=0.001, momentum=0.9)

all_data = np.load('training_data.npy')
inputs= all_data[:,0]
labels= all_data[:,1]
inputs_tensors = torch.stack([torch.Tensor(i) for i in inputs])
labels_tensors = torch.stack([torch.Tensor(i) for i in labels])

data_set =,labels_tensors)
data_loader =, batch_size=3,shuffle=True, num_workers=2)

if __name__ == '__main__':
 for epoch in range(8):
  runing_loss = 0.0
  for i,data in enumerate(data_loader , 0):
     inputs= data[0]
     inputs = torch.FloatTensor(inputs)
     labels= data[1]
     labels = torch.FloatTensor(labels)
     # set_trace()
     inputs = torch.unsqueeze(inputs, 1)
     outputs = AlexNet(inputs)
     loss = criterion(outputs , labels)
     runing_loss +=loss.item()
     if i % 2000 == 1999:    # print every 2000 mini-batches
            print('[%d, %5d] loss: %.3f' %
                  (epoch + 1, i + 1, running_loss / 2000))
            running_loss = 0.0

I am using AlexNet from the link

but changed line 18 from
nn.Conv2d(3, 64, kernel_size=11, stride=4, padding=2)
nn.Conv2d(1, 64, kernel_size=11, stride=4, padding=2)
because i am using oly one channel in training images,but i get this error

Traceback (most recent call last):
  File "", line 44, in <module>
    outputs = AlexNet(inputs)
  File "C:\Users\Mukhtar\Anaconda3\lib\site-packages\torch\nn\modules\", line 477, in __call__
    result = self.forward(*input, **kwargs)
  File "C:\Users\Mukhtar\Documents\AI_projects\gta\", line 34, in forward
    x = self.features(x)
  File "C:\Users\Mukhtar\Anaconda3\lib\site-packages\torch\nn\modules\", line 477, in __call__
    result = self.forward(*input, **kwargs)
  File "C:\Users\Mukhtar\Anaconda3\lib\site-packages\torch\nn\modules\", line 91, in forward
    input = module(input)
  File "C:\Users\Mukhtar\Anaconda3\lib\site-packages\torch\nn\modules\", line 477, in __call__
    result = self.forward(*input, **kwargs)
  File "C:\Users\Mukhtar\Anaconda3\lib\site-packages\torch\nn\modules\", line 142, in forward
  File "C:\Users\Mukhtar\Anaconda3\lib\site-packages\torch\nn\", line 396, in max_pool2d
    ret = torch._C._nn.max_pool2d_with_indices(input, kernel_size, stride, padding, dilation, ceil_mode)
RuntimeError: Given input size: (256x1x1). Calculated output size: (256x0x0). Output size is too small at c:\programdata\miniconda3\conda-bld\pytorch-cpu_1532499824793\work\aten\src\thnn\generic/SpatialDilatedMaxPooling.c:67

I dont know what is wrong, is it wrong to change the channel size like this , and if it is wrong can you please lead me to a neural network that work with one channel , as i said i am a newbie in pytorch and i dont want to write the nn myself.

It looks like your fix regarding the input channels is right, but the spatial size might be too small.
How large is your input? AlexNet should work with 224x224 sized images.

1 Like

Yes, my input size was the problem i gave it a (32x32) images rather than a (224x224) .
I reshaped the input to (224x224) and now i am training the CNN.
thanks for the help.