I am trying to convert TensorFlow
model to PyTorch
but having trouble with padding
. My code for for relevant platforms are as follow:
TensorFlow
conv1 = tf.layers.conv2d(
inputs=input_layer,
filters=32,
kernel_size=[5, 5],
padding="same",
activation=tf.nn.relu,
name = "conv1")
PyTorch
conv1 = nn.Conv2d(1, 32, kernel_size=5, stride=1, padding=2)
I have few questions:
- Are the above codes equivalent?
- How many
padding
s are added on left/right/top/bottom if we usesame
padding intensorflow
? - How many
padding
s are added on left/right/top/bottom if we usepadding=2
inpytorch
? - If the above two code snippets are not equivalent then how can we make the same
conv
layer?
Thanks in advance.