pytorch-summary | Model summary in PyTorch | Machine Learning library

batch_X = batch_X.to(device=device, dtype=torch.int64) #gpu                        # input data here!!!!!!!!!!!!!!!!!!!!!!!!!!
batch_y = batch_y.to(device=device, dtype=torch.int64) #gpu  

batch_X = batch_X.to(devi

import numpy as np
import torch
import torch.nn as nn
import torch.nn.functional as F
from captum.attr import IntegratedGradients, LayerIntegratedGradients
from torchsummary import summary

device = torch.device("cuda:0" if torch.cuda.is_a

            if i in [0, 1]:
                f = nn.AvgPool2d(kernel_size=(11, 24), stride=(7, 4))(f)

            elif i == 2:
                f = nn.AvgPool2d(kernel_size=(9, 11), stride=(7, 2))(f)
            elif i == 3:
               

if flag:
    # for Cifar10
    layers += [nn.Flatten(), nn.Linear(512, 10)]  # <<< add Flatten before Linear

def forward(self, x):
    x = self.features(x)
    x = x.view(x.size(0), -1)  # here, equivalent

from torchsummary import summary

input_shape = (3,32,32)
summary(Net(), input_shape)

----------------------------------------------------------------
        Layer (type)               Output Shape         Param #

{'state_dict': {'model.conv1.weight': tensor([[[[ 2.0076e-02,  1.5264e-02, -1.2309e-02,  ..., -4.0222e-02,
           -4.0527e-02, -6.4458e-02],
          [ 6.3291e-03,  3.8393e-03,  1.2400e-02,  ..., -3.3926e-03,
           -2.1063e-02, -

for layer in vgg16.features:
    print()
    print(layer)
    if (hasattr(layer,'weight')):
        
        # supress .requires_grad
        layer.bias.requires_grad = False
        layer.weight.requires_grad = False
        
        dim