I'm trying to perform a Convolutional operation on the covid CT Dataset and constantly getting this error. My image size in the train loader was (10, 150, 150, 3) and I reshaped it into [10, 3, 150, 150], using torch.reshape(). Can anybody help me with problem
My CNN Code
class BConv(nn.Module):
def __init__(self, out=3):
super(BConv, self).__init__()
#(10, 150, 150, 3)
self.conv1=nn.Conv2d(in_channels=3,out_channels=12,kernel_size=3,stride=1,padding=1)
self.bn1=nn.BatchNorm2d(num_features=12)
self.relu1=nn.ReLU()
self.pool=nn.MaxPool2d(kernel_size=2)
self.conv2=nn.Conv2d(in_channels=12,out_channels=20,kernel_size=3,stride=1,padding=1)
self.relu2=nn.ReLU()
# self.conv3=nn.Conv2d(in_channels=20,out_channels=32,kernel_size=3,stride=1,padding=1)
# self.bn3=nn.BatchNorm2d(num_features=32)
# self.relu3=nn.ReLU()
self.fc=nn.Linear(in_features= 20*75*75, out_features=3)
def forward(self,input):
output=self.conv1(input)
#print("output 1", output.shape)
output=self.bn1(output)
#print("output 1", output.shape)
output=self.relu1(output)
#print("output 1", output.shape)
output=self.pool(output)
#print("output 1", output.shape)
output=self.conv2(output)
#print("output 1", output.shape)
output=self.relu2(output)
#print("output 1", output.shape)
# output=self.conv3(output)
# output=self.bn3(output)
# output=self.relu3(output)
print(output.shape)
#Above output will be in matrix form, with shape (256,32,75,75)
output=output.view(output.size(0), -1)
output=self.fc(output)
return output
Data Preprocessing
class Ctdataset(Dataset):
def __init__(self, path):
self.data= pd.read_csv(path, delimiter=" ")
data= self.data.values.tolist()
self.image= []
self.labels=[]
for i in data:
self.image.append(i[0])
self.labels.append(i[1])
#print(len(self.image), len(self.labels))
#self.class_map = {"0": 0, "1":1 , "2": 2}
def __len__(self):
return len(self.image)
def __getitem__(self, idx):
img_path = os.path.join("2A_images", self.image[idx])
img= Image.open(img_path).convert("RGB")
img= img.resize((150, 150))
img= np.array(img)
img= img.astype(float)
return img, label
Here I'm considering your whole model including the third block consisting of conv3, bn3, and relu3. There are a few things to note:
Reshaping is substantially different from permuting the axes. When you say you have an input shape of (batch_size, 150, 150, 3), it means the channel axis is last. Since PyTorch 2D builtin layers work in the NHW format you need to permute the axes: you can do so with torch.Tensor.permute:
>>> x = torch.rand(10, 150, 150, 3)
>>> x.permute(0, 3, 1, 2).shape
(10, 3, 150, 150)
Assuming your input is shaped (batch_size, 3, 150, 150), then the output shape of relu3 will be (32, 75, 75). As such the following fully connected layer must have exactly 32*75*75 input features.
However you need to flatten this tensor as you did in your code with a view: output = output.view(output.size(0), -1). Another approach is to define a self.flatten = nn.Flatten() layer and call it with output = self.flatten(output).
As of PyTorch v1.8.0, an alternative to setting the in_features in your fully connected layer is to use nn.LazyLinear which will initialize it for you based on the first inference:
>>> self.fc = nn.LazyLinear(out_features=3)
Side note: you don't need to define separate ReLU layers with relu1, relu2, and relu3 as they're non-parametric functions:
>>> self.relu = nn.ReLU()
Here is the full code for reference:
class BConv(nn.Module):
def __init__(self, out=3):
super().__init__()
# input shape (10, 150, 150, 3)
self.conv1 = nn.Conv2d(3, 12,kernel_size=3, stride=1, padding=1)
self.bn1 = nn.BatchNorm2d(num_features=12)
self.pool = nn.MaxPool2d(kernel_size=2)
self.conv2 = nn.Conv2d(12, 20,kernel_size=3, stride=1, padding=1)
self.conv3 = nn.Conv2d(20, 32, kernel_size=3, stride=1, padding=1)
self.bn3 = nn.BatchNorm2d(num_features=32)
self.relu = nn.ReLU()
self.flatten = nn.Flatten()
self.fc = nn.Linear(in_features=32*75*75, out_features=out)
def forward(self,input):
output = input.permute(0, 3, 1, 2)
output = self.conv1(output)
output = self.bn1(output)
output = self.relu(output)
output = self.pool(output)
output = self.conv2(output)
output = self.relu(output)
output = self.conv3(output)
output = self.bn3(output)
output = self.relu(output)
output = self.flatten(output)
output = self.fc(output)
return output