在为模型类定义对象后，只需打印模型

class RNN(nn.Module):
    def __init__(self, input_dim, embedding_dim, hidden_dim, output_dim):
        super().__init__()

        self.embedding = nn.Embedding(input_dim, embedding_dim)
        self.rnn = nn.RNN(embedding_dim, hidden_dim)
        self.fc = nn.Linear(hidden_dim, output_dim)
    def forward():
        ...

model = RNN(input_dim, embedding_dim, hidden_dim, output_dim)
print(model)

torchinfo(以前的torchsummary)包产生类似Keras1的输出(对于给定的输入形状):2

from torchinfo import summary

model = ConvNet()
batch_size = 16
summary(model, input_size=(batch_size, 1, 28, 28))

==========================================================================================
Layer (type:depth-idx)                   Output Shape              Param #
==========================================================================================
├─Conv2d (conv1): 1-1                    [5, 10, 24, 24]           260
├─Conv2d (conv2): 1-2                    [5, 20, 8, 8]             5,020
├─Dropout2d (conv2_drop): 1-3            [5, 20, 8, 8]             --
├─Linear (fc1): 1-4                      [5, 50]                   16,050
├─Linear (fc2): 1-5                      [5, 10]                   510
==========================================================================================
Total params: 21,840
Trainable params: 21,840
Non-trainable params: 0
Total mult-adds (M): 7.69
==========================================================================================
Input size (MB): 0.05
Forward/backward pass size (MB): 0.91
Params size (MB): 0.09
Estimated Total Size (MB): 1.05
==========================================================================================

Notes: Torchinfo provides information complementary to what is provided by print(your_model) in PyTorch, similar to Tensorflow's model.summary()... Unlike Keras, PyTorch has a dynamic computational graph which can adapt to any compatible input shape across multiple calls e.g. any sufficiently large image size (for a fully convolutional network). As such, it cannot present an inherent set of input/output shapes for each layer, as these are input-dependent, and why in the above package you must specify the input dimensions.

虽然你不会像Keras的模型那样得到关于模型的详细信息。总之，简单地打印模型将使您对涉及的不同层及其规范有一些了解。

例如:

from torchvision import models
model = models.vgg16()
print(model)

这种情况下的输出如下所示:

VGG (
  (features): Sequential (
    (0): Conv2d(3, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
    (1): ReLU (inplace)
    (2): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
    (3): ReLU (inplace)
    (4): MaxPool2d (size=(2, 2), stride=(2, 2), dilation=(1, 1))
    (5): Conv2d(64, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
    (6): ReLU (inplace)
    (7): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
    (8): ReLU (inplace)
    (9): MaxPool2d (size=(2, 2), stride=(2, 2), dilation=(1, 1))
    (10): Conv2d(128, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
    (11): ReLU (inplace)
    (12): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
    (13): ReLU (inplace)
    (14): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
    (15): ReLU (inplace)
    (16): MaxPool2d (size=(2, 2), stride=(2, 2), dilation=(1, 1))
    (17): Conv2d(256, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
    (18): ReLU (inplace)
    (19): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
    (20): ReLU (inplace)
    (21): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
    (22): ReLU (inplace)
    (23): MaxPool2d (size=(2, 2), stride=(2, 2), dilation=(1, 1))
    (24): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
    (25): ReLU (inplace)
    (26): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
    (27): ReLU (inplace)
    (28): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
    (29): ReLU (inplace)
    (30): MaxPool2d (size=(2, 2), stride=(2, 2), dilation=(1, 1))
  )
  (classifier): Sequential (
    (0): Dropout (p = 0.5)
    (1): Linear (25088 -> 4096)
    (2): ReLU (inplace)
    (3): Dropout (p = 0.5)
    (4): Linear (4096 -> 4096)
    (5): ReLU (inplace)
    (6): Linear (4096 -> 1000)
  )
)

现在，正如Kashyap所提到的，您可以使用state_dict方法来获取不同层的权重。但是使用这个层列表可能会提供更多的指导，即创建一个帮助函数来获得Keras一样的模型摘要!

在为模型类定义对象后，只需打印模型

class RNN(nn.Module):
    def __init__(self, input_dim, embedding_dim, hidden_dim, output_dim):
        super().__init__()

        self.embedding = nn.Embedding(input_dim, embedding_dim)
        self.rnn = nn.RNN(embedding_dim, hidden_dim)
        self.fc = nn.Linear(hidden_dim, output_dim)
    def forward():
        ...

model = RNN(input_dim, embedding_dim, hidden_dim, output_dim)
print(model)

这将显示模型的权重和参数(但不输出形状)。

from torch.nn.modules.module import _addindent
import torch
import numpy as np
def torch_summarize(model, show_weights=True, show_parameters=True):
    """Summarizes torch model by showing trainable parameters and weights."""
    tmpstr = model.__class__.__name__ + ' (\n'
    for key, module in model._modules.items():
        # if it contains layers let call it recursively to get params and weights
        if type(module) in [
            torch.nn.modules.container.Container,
            torch.nn.modules.container.Sequential
        ]:
            modstr = torch_summarize(module)
        else:
            modstr = module.__repr__()
        modstr = _addindent(modstr, 2)

        params = sum([np.prod(p.size()) for p in module.parameters()])
        weights = tuple([tuple(p.size()) for p in module.parameters()])

        tmpstr += '  (' + key + '): ' + modstr 
        if show_weights:
            tmpstr += ', weights={}'.format(weights)
        if show_parameters:
            tmpstr +=  ', parameters={}'.format(params)
        tmpstr += '\n'   

    tmpstr = tmpstr + ')'
    return tmpstr

# Test
import torchvision.models as models
model = models.alexnet()
print(torch_summarize(model))

# # Output
# AlexNet (
#   (features): Sequential (
#     (0): Conv2d(3, 64, kernel_size=(11, 11), stride=(4, 4), padding=(2, 2)), weights=((64, 3, 11, 11), (64,)), parameters=23296
#     (1): ReLU (inplace), weights=(), parameters=0
#     (2): MaxPool2d (size=(3, 3), stride=(2, 2), dilation=(1, 1)), weights=(), parameters=0
#     (3): Conv2d(64, 192, kernel_size=(5, 5), stride=(1, 1), padding=(2, 2)), weights=((192, 64, 5, 5), (192,)), parameters=307392
#     (4): ReLU (inplace), weights=(), parameters=0
#     (5): MaxPool2d (size=(3, 3), stride=(2, 2), dilation=(1, 1)), weights=(), parameters=0
#     (6): Conv2d(192, 384, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)), weights=((384, 192, 3, 3), (384,)), parameters=663936
#     (7): ReLU (inplace), weights=(), parameters=0
#     (8): Conv2d(384, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)), weights=((256, 384, 3, 3), (256,)), parameters=884992
#     (9): ReLU (inplace), weights=(), parameters=0
#     (10): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)), weights=((256, 256, 3, 3), (256,)), parameters=590080
#     (11): ReLU (inplace), weights=(), parameters=0
#     (12): MaxPool2d (size=(3, 3), stride=(2, 2), dilation=(1, 1)), weights=(), parameters=0
#   ), weights=((64, 3, 11, 11), (64,), (192, 64, 5, 5), (192,), (384, 192, 3, 3), (384,), (256, 384, 3, 3), (256,), (256, 256, 3, 3), (256,)), parameters=2469696
#   (classifier): Sequential (
#     (0): Dropout (p = 0.5), weights=(), parameters=0
#     (1): Linear (9216 -> 4096), weights=((4096, 9216), (4096,)), parameters=37752832
#     (2): ReLU (inplace), weights=(), parameters=0
#     (3): Dropout (p = 0.5), weights=(), parameters=0
#     (4): Linear (4096 -> 4096), weights=((4096, 4096), (4096,)), parameters=16781312
#     (5): ReLU (inplace), weights=(), parameters=0
#     (6): Linear (4096 -> 1000), weights=((1000, 4096), (1000,)), parameters=4097000
#   ), weights=((4096, 9216), (4096,), (4096, 4096), (4096,), (1000, 4096), (1000,)), parameters=58631144
# )

编辑:isaykatsman有一个pytorch PR来添加一个完全像keras https://github.com/pytorch/pytorch/pull/3043/files的model.summary()

Summary (my_model， (3, 224, 224)， device = 'cpu')可以解决这个问题。