Use the new and updated torchinfo.
Keras has a neat API to view the visualization of the model which is very helpful while debugging your network. Here is a barebone code to try and mimic the same in PyTorch. The aim is to provide information complementary to, what is not provided by print(your_model) in PyTorch.
pip install torchsummaryorgit clone https://github.com/sksq96/pytorch-summary
from torchsummary import summary
summary(your_model, input_size=(channels, H, W))- Note that the
input_sizeis required to make a forward pass through the network.
import torch
import torch.nn as nn
import torch.nn.functional as F
from torchsummary import summary
class Net(nn.Module):
def __init__(self):
super(Net, self).__init__()
self.conv1 = nn.Conv2d(1, 10, kernel_size=5)
self.conv2 = nn.Conv2d(10, 20, kernel_size=5)
self.conv2_drop = nn.Dropout2d()
self.fc1 = nn.Linear(320, 50)
self.fc2 = nn.Linear(50, 10)
def forward(self, x):
x = F.relu(F.max_pool2d(self.conv1(x), 2))
x = F.relu(F.max_pool2d(self.conv2_drop(self.conv2(x)), 2))
x = x.view(-1, 320)
x = F.relu(self.fc1(x))
x = F.dropout(x, training=self.training)
x = self.fc2(x)
return F.log_softmax(x, dim=1)
device = torch.device("cuda" if torch.cuda.is_available() else "cpu") # PyTorch v0.4.0
model = Net().to(device)
summary(model, (1, 28, 28))----------------------------------------------------------------
Layer (type) Output Shape Param #
================================================================
Conv2d-1 [-1, 10, 24, 24] 260
Conv2d-2 [-1, 20, 8, 8] 5,020
Dropout2d-3 [-1, 20, 8, 8] 0
Linear-4 [-1, 50] 16,050
Linear-5 [-1, 10] 510
================================================================
Total params: 21,840
Trainable params: 21,840
Non-trainable params: 0
----------------------------------------------------------------
Input size (MB): 0.00
Forward/backward pass size (MB): 0.06
Params size (MB): 0.08
Estimated Total Size (MB): 0.15
----------------------------------------------------------------
import torch
from torchvision import models
from torchsummary import summary
device = torch.device('cuda' if torch.cuda.is_available() else 'cpu')
vgg = models.vgg16().to(device)
summary(vgg, (3, 224, 224))----------------------------------------------------------------
Layer (type) Output Shape Param #
================================================================
Conv2d-1 [-1, 64, 224, 224] 1,792
ReLU-2 [-1, 64, 224, 224] 0
Conv2d-3 [-1, 64, 224, 224] 36,928
ReLU-4 [-1, 64, 224, 224] 0
MaxPool2d-5 [-1, 64, 112, 112] 0
Conv2d-6 [-1, 128, 112, 112] 73,856
ReLU-7 [-1, 128, 112, 112] 0
Conv2d-8 [-1, 128, 112, 112] 147,584
ReLU-9 [-1, 128, 112, 112] 0
MaxPool2d-10 [-1, 128, 56, 56] 0
Conv2d-11 [-1, 256, 56, 56] 295,168
ReLU-12 [-1, 256, 56, 56] 0
Conv2d-13 [-1, 256, 56, 56] 590,080
ReLU-14 [-1, 256, 56, 56] 0
Conv2d-15 [-1, 256, 56, 56] 590,080
ReLU-16 [-1, 256, 56, 56] 0
MaxPool2d-17 [-1, 256, 28, 28] 0
Conv2d-18 [-1, 512, 28, 28] 1,180,160
ReLU-19 [-1, 512, 28, 28] 0
Conv2d-20 [-1, 512, 28, 28] 2,359,808
ReLU-21 [-1, 512, 28, 28] 0
Conv2d-22 [-1, 512, 28, 28] 2,359,808
ReLU-23 [-1, 512, 28, 28] 0
MaxPool2d-24 [-1, 512, 14, 14] 0
Conv2d-25 [-1, 512, 14, 14] 2,359,808
ReLU-26 [-1, 512, 14, 14] 0
Conv2d-27 [-1, 512, 14, 14] 2,359,808
ReLU-28 [-1, 512, 14, 14] 0
Conv2d-29 [-1, 512, 14, 14] 2,359,808
ReLU-30 [-1, 512, 14, 14] 0
MaxPool2d-31 [-1, 512, 7, 7] 0
Linear-32 [-1, 4096] 102,764,544
ReLU-33 [-1, 4096] 0
Dropout-34 [-1, 4096] 0
Linear-35 [-1, 4096] 16,781,312
ReLU-36 [-1, 4096] 0
Dropout-37 [-1, 4096] 0
Linear-38 [-1, 1000] 4,097,000
================================================================
Total params: 138,357,544
Trainable params: 138,357,544
Non-trainable params: 0
----------------------------------------------------------------
Input size (MB): 0.57
Forward/backward pass size (MB): 218.59
Params size (MB): 527.79
Estimated Total Size (MB): 746.96
----------------------------------------------------------------
import torch
import torch.nn as nn
from torchsummary import summary
class SimpleConv(nn.Module):
def __init__(self):
super(SimpleConv, self).__init__()
self.features = nn.Sequential(
nn.Conv2d(1, 1, kernel_size=3, stride=1, padding=1),
nn.ReLU(),
)
def forward(self, x, y):
x1 = self.features(x)
x2 = self.features(y)
return x1, x2
device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
model = SimpleConv().to(device)
summary(model, [(1, 16, 16), (1, 28, 28)])----------------------------------------------------------------
Layer (type) Output Shape Param #
================================================================
Conv2d-1 [-1, 1, 16, 16] 10
ReLU-2 [-1, 1, 16, 16] 0
Conv2d-3 [-1, 1, 28, 28] 10
ReLU-4 [-1, 1, 28, 28] 0
================================================================
Total params: 20
Trainable params: 20
Non-trainable params: 0
----------------------------------------------------------------
Input size (MB): 0.77
Forward/backward pass size (MB): 0.02
Params size (MB): 0.00
Estimated Total Size (MB): 0.78
----------------------------------------------------------------
- The idea for this package sparked from this PyTorch issue.
- Thanks to @ncullen93 and @HTLife.
- For Model Size Estimation @jacobkimmel (details here)
pytorch-summary is MIT-licensed.