I think the “fix” is to use the package from the forked repository:
pip install torchinfo
from torchinfo import summary
model = ConvNet()
batch_size = 16
summary(model, input_size=(batch_size, 1, 28, 28))
I think the “fix” is to use the package from the forked repository:
pip install torchinfo
from torchinfo import summary
model = ConvNet()
batch_size = 16
summary(model, input_size=(batch_size, 1, 28, 28))