Here is a network and if you could please explain to me how the 128 * 1 * 1 shape is calculated I will appreciate it very much.
I am aware of this formula (W + F + 2P / S) + 1 but I am having trouble calculating128 * 1 * 1.
In this formula:
W = Input Width
F = Kernel size
P = Padding
S = Stride
The size of the input is (1,28,28) ie the MNIST dataset from torchvision.
So as you can see I have looked into this problem but I cannot calculate the 128 * 1 * 1 input to
self.f1 = nn.Linear(128 * 1 * 1, 1000) in the network below So, if you could answer this question using some formula I will appreciate it very much.
class Net(nn.Module):
"""A representation of a convolutional neural network comprised of VGG blocks."""
def __init__(self, n_channels):
super(Net, self).__init__()
# VGG block 1
self.conv1 = nn.Conv2d(n_channels, 64, (3,3))
self.act1 = nn.ReLU()
self.pool1 = nn.MaxPool2d((2,2), stride=(2,2))
# VGG block 2
self.conv2 = nn.Conv2d(64, 64, (3,3))
self.act2 = nn.ReLU()
self.pool2 = nn.MaxPool2d((2,2), stride=(2,2))
# VGG block 3
self.conv3 = nn.Conv2d(64, 128, (3,3))
self.act3 = nn.ReLU()
self.pool3 = nn.MaxPool2d((2,2), stride=(2,2))
# Fully connected layer
self.f1 = nn.Linear(128 * 1 * 1, 1000)
self.act4 = nn.ReLU()
# Output layer
self.f2 = nn.Linear(1000, 10)
self.act5 = nn.Softmax(dim=1)
def forward(self, X):
"""This function forward propagates the input."""
# VGG block 1
X = self.conv1(X)
X = self.act1(X)
X = self.pool1(X)
# VGG block 2
X = self.conv2(X)
X = self.act2(X)
X = self.pool2(X)
# VGG block 3
X = self.conv3(X)
X = self.act3(X)
X = self.pool3(X)
# Flatten
X = X.view(-1, 128)
# Fully connected layer
X = self.f1(X)
X = self.act4(X)
# Output layer
X = self.f2(X)
X = self.act5(X)
return X
thanks!