wkentaro / pytorch-fcn

PyTorch Implementation of Fully Convolutional Networks. (Training code to reproduce the original result is available.)

padding=100

LynnHg opened this issue 5 years ago · comments

wang commented 5 years ago

would you mind tell me why is the first conv's padding =100?( self.conv1_1 = nn.Conv2d(3, 64, 3, padding=100))

Kentaro Wada commented 5 years ago

Please refer to #40

wang commented 5 years ago

thanks！

Niloy-Chakraborty commented 4 years ago

Do you know how to add padding=100, in Keras?