torchsummaryX
torchsummaryX copied to clipboard
nmhkahn
torchsummaryX: Improved visualization tool of torchsummary
When trying to run the sample code ``` from torchsummaryX import summary import torch from torch import nn from torch.nn import functional as F class Net(nn.Module): def __init__(self): super(Net, self).__init__()...
Why？？what caused the negative value？ 
Is it possible to convert the output file into a readily available CSV file?
Same as here https://github.com/numpy/numpy/issues/18355 Fixed by `python -m pip install pandas>=1.3.2` ```` File "/repo.py", line 160, in __init__ torchsummaryX.summary(model, x_rand) File "/usr/local/lib/python3.7/dist-packages/torchsummaryX/torchsummaryX.py", line 122, in summary index=['Totals'] File "/usr/local/lib/python3.7/dist-packages/pandas/core/frame.py", line...
The tool can not compute the Madds of matrix multiplication. such as matrix X multiply matrix Y in forward, the results is 0.
For large networks, negative MAdds appear. It's because the caculated macs exceed the data range at line 53: param.nelement() returns python int64 but np.prod(info["out"][2:])) returns numpy np.int32 multiplication of these...
Issue #19 reported a feature warning while using pandas package. The details can be found at (https://pandas.pydata.org/pandas-docs/stable/whatsnew/v1.3.0.html#deprecations). To sum up, users need to select only valid columns before calling the...
I get the following FutureWarning on torchsummary 1.3.0 (latest) and pandas 1.3.1 (latest) on Python 3.9 under Windows10 FutureWarning: Dropping of nuisance columns in DataFrame reductions (with 'numeric_only=None') is deprecated;...
weight_norm layer prevents "Kernel Shape" output Taking the example from the README ``` from torchsummaryX import summary import torch import torch.nn as nn import torch.nn.functional as F class Net(nn.Module): def...