It confused me because in torch you can directly print the loaded model. But in pytorch I just saw parameters inside.
print(model)
should just work.
It looks like a dictionary in python and print can just show the key/value rather than the structure of net.
There’s also a summary view of a model in the works: https://github.com/pytorch/pytorch/issues/2001
Nice! Didn’t know that. Seems to be quite useful
Yes, you can get exact Keras representation, using this code.
Example for VGG16
from torchvision import models
from summary import summary
vgg = models.vgg16()
summary(vgg, (3, 224, 224))
----------------------------------------------------------------
Layer (type) Output Shpae Param #
================================================================
Conv2d-1 [-1, 64, 224, 224] 1792
ReLU-2 [-1, 64, 224, 224] 0
Conv2d-3 [-1, 64, 224, 224] 36928
ReLU-4 [-1, 64, 224, 224] 0
MaxPool2d-5 [-1, 64, 112, 112] 0
Conv2d-6 [-1, 128, 112, 112] 73856
ReLU-7 [-1, 128, 112, 112] 0
Conv2d-8 [-1, 128, 112, 112] 147584
ReLU-9 [-1, 128, 112, 112] 0
MaxPool2d-10 [-1, 128, 56, 56] 0
Conv2d-11 [-1, 256, 56, 56] 295168
ReLU-12 [-1, 256, 56, 56] 0
Conv2d-13 [-1, 256, 56, 56] 590080
ReLU-14 [-1, 256, 56, 56] 0
Conv2d-15 [-1, 256, 56, 56] 590080
ReLU-16 [-1, 256, 56, 56] 0
MaxPool2d-17 [-1, 256, 28, 28] 0
Conv2d-18 [-1, 512, 28, 28] 1180160
ReLU-19 [-1, 512, 28, 28] 0
Conv2d-20 [-1, 512, 28, 28] 2359808
ReLU-21 [-1, 512, 28, 28] 0
Conv2d-22 [-1, 512, 28, 28] 2359808
ReLU-23 [-1, 512, 28, 28] 0
MaxPool2d-24 [-1, 512, 14, 14] 0
Conv2d-25 [-1, 512, 14, 14] 2359808
ReLU-26 [-1, 512, 14, 14] 0
Conv2d-27 [-1, 512, 14, 14] 2359808
ReLU-28 [-1, 512, 14, 14] 0
Conv2d-29 [-1, 512, 14, 14] 2359808
ReLU-30 [-1, 512, 14, 14] 0
MaxPool2d-31 [-1, 512, 7, 7] 0
Linear-32 [-1, 4096] 102764544
ReLU-33 [-1, 4096] 0
Dropout-34 [-1, 4096] 0
Linear-35 [-1, 4096] 16781312
ReLU-36 [-1, 4096] 0
Dropout-37 [-1, 4096] 0
Linear-38 [-1, 1000] 4097000
================================================================
Total params: 138357544
Trainable params: 138357544
Non-trainable params: 0
----------------------------------------------------------------
Thx. But how about the net with multiple inputs?
It looks that this code can’t work with more than one input.
torchsummary also works with more than one input. Here is the snippet from @sksq96
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)])
Hope it helps.
Thank you very much!
Is there any way to print each layer’s parameters like stride, kernel size, padding from the torch model architecture?
These arguments are only defined for some layers, so you would need to filter them out e.g. via:
for name, module in model.named_modules():
if isinstance(module, nn.Conv2d):
print(name, module.kernel_size, module.stride, ...)