i’m getting this error from criterion, it says that inputs is none which is strange since code works for fully connected layer.
here is the full project https://github.com/kanedaaaa/Pytorch-MNIST-fully-connected-nns
you can find cnn.py in Models folder and data/train/test in main.py
code snippets:
class CnnNet(nn.Module):
def __init__(self):
super(CnnNet, 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.pool = nn.MaxPool2d(2,2)
self.fc1 = nn.Linear(64*7*7, 128)
self.fc2 = nn.Linear(128, 10)
self.dropout = torch.nn.Dropout(p=0.5)
self.relu = torch.nn.ReLU()
def forward(self, x):
x = self.conv1(x)
x = self.relu(x)
x = self.pool(x)
x = self.conv2(x)
x = self.relu(x)
x = self.pool(x)
x = x.reshape(x.size(0), -1)
x = self.fc1(x)
x = self.dropout(x)
prediction = self.fc2(x)
def train():
for epoch in range(num_epochs):
running_loss = 0
for i, (inputs, labels) in enumerate(trainloader):
#inputs, labels = inputs.reshape(-1, 28*28).to(device), labels.to(device)
inputs, labels = inputs.to(device), labels.to(device)
optimizer.zero_grad()
output= net(inputs)
loss = criterion(output, labels)
loss.backward()
optimizer.step()
running_loss =+ loss.item() * inputs.size(0)
if(i+1) % 100 == 0:
print('Epoch [{}/{}], Step [{}/{}], Loss: {:.4f}'.format(epoch+1, num_epochs, i+1, total_step, loss.item()))
loss_values.append(running_loss / total_step)
btw, fully connected layer needs reshaped inputs.