232

如何像 Keras 中的model.summary()方法一样在 PyTorch 中打印模型的摘要：

Model Summary:
____________________________________________________________________________________________________
Layer (type)                     Output Shape          Param #     Connected to                     
====================================================================================================
input_1 (InputLayer)             (None, 1, 15, 27)     0                                            
____________________________________________________________________________________________________
convolution2d_1 (Convolution2D)  (None, 8, 15, 27)     872         input_1[0][0]                    
____________________________________________________________________________________________________
maxpooling2d_1 (MaxPooling2D)    (None, 8, 7, 27)      0           convolution2d_1[0][0]            
____________________________________________________________________________________________________
flatten_1 (Flatten)              (None, 1512)          0           maxpooling2d_1[0][0]             
____________________________________________________________________________________________________
dense_1 (Dense)                  (None, 1)             1513        flatten_1[0][0]                  
====================================================================================================
Total params: 2,385
Trainable params: 2,385
Non-trainable params: 0
4

11 回答 11

216

是的，您可以使用pytorch-summary包获得准确的 Keras 表示。

VGG16 示例：

from torchvision import models
from torchsummary import summary

vgg = models.vgg16()
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
----------------------------------------------------------------
于 2018-04-23T20:26:57.510 回答
187

虽然您不会像 Keras 的 model.summary 那样获得关于模型的详细信息，但只需打印模型即可让您对所涉及的不同层及其规格有所了解。

例如：

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

在这种情况下，输出将如下所示：

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，您可以使用该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方向，即创建一个辅助函数来获得类似 Keras 的模型摘要！希望这可以帮助！

于 2017-03-06T02:55:05.703 回答
45

为了使用 torchsummary 类型：

from torchsummary import summary

如果没有，请先安装它。

pip install torchsummary

然后你可以尝试它，但由于某种原因它不起作用，除非我将模型设置为 cuda alexnet.cuda：

from torchsummary import summary
help(summary)
import torchvision.models as models
alexnet = models.alexnet(pretrained=False)
alexnet.cuda()
summary(alexnet, (3, 224, 224))
print(alexnet)

必须将summary输入大小和批处理大小设置为 -1，这意味着我们提供的任何批处理大小。

如果我们设置summary(alexnet, (3, 224, 224), 32)这意味着使用bs=32.

summary(model, input_size, batch_size=-1, device='cuda')

出去：

Help on function summary in module torchsummary.torchsummary:

summary(model, input_size, batch_size=-1, device='cuda')

----------------------------------------------------------------
        Layer (type)               Output Shape         Param #
================================================================
            Conv2d-1           [32, 64, 55, 55]          23,296
              ReLU-2           [32, 64, 55, 55]               0
         MaxPool2d-3           [32, 64, 27, 27]               0
            Conv2d-4          [32, 192, 27, 27]         307,392
              ReLU-5          [32, 192, 27, 27]               0
         MaxPool2d-6          [32, 192, 13, 13]               0
            Conv2d-7          [32, 384, 13, 13]         663,936
              ReLU-8          [32, 384, 13, 13]               0
            Conv2d-9          [32, 256, 13, 13]         884,992
             ReLU-10          [32, 256, 13, 13]               0
           Conv2d-11          [32, 256, 13, 13]         590,080
             ReLU-12          [32, 256, 13, 13]               0
        MaxPool2d-13            [32, 256, 6, 6]               0
AdaptiveAvgPool2d-14            [32, 256, 6, 6]               0
          Dropout-15                 [32, 9216]               0
           Linear-16                 [32, 4096]      37,752,832
             ReLU-17                 [32, 4096]               0
          Dropout-18                 [32, 4096]               0
           Linear-19                 [32, 4096]      16,781,312
             ReLU-20                 [32, 4096]               0
           Linear-21                 [32, 1000]       4,097,000
================================================================
Total params: 61,100,840
Trainable params: 61,100,840
Non-trainable params: 0
----------------------------------------------------------------
Input size (MB): 18.38
Forward/backward pass size (MB): 268.12
Params size (MB): 233.08
Estimated Total Size (MB): 519.58
----------------------------------------------------------------
AlexNet(
  (features): Sequential(
    (0): Conv2d(3, 64, kernel_size=(11, 11), stride=(4, 4), padding=(2, 2))
    (1): ReLU(inplace)
    (2): MaxPool2d(kernel_size=3, stride=2, padding=0, dilation=1, ceil_mode=False)
    (3): Conv2d(64, 192, kernel_size=(5, 5), stride=(1, 1), padding=(2, 2))
    (4): ReLU(inplace)
    (5): MaxPool2d(kernel_size=3, stride=2, padding=0, dilation=1, ceil_mode=False)
    (6): Conv2d(192, 384, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
    (7): ReLU(inplace)
    (8): Conv2d(384, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
    (9): ReLU(inplace)
    (10): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
    (11): ReLU(inplace)
    (12): MaxPool2d(kernel_size=3, stride=2, padding=0, dilation=1, ceil_mode=False)
  )
  (avgpool): AdaptiveAvgPool2d(output_size=(6, 6))
  (classifier): Sequential(
    (0): Dropout(p=0.5)
    (1): Linear(in_features=9216, out_features=4096, bias=True)
    (2): ReLU(inplace)
    (3): Dropout(p=0.5)
    (4): Linear(in_features=4096, out_features=4096, bias=True)
    (5): ReLU(inplace)
    (6): Linear(in_features=4096, out_features=1000, bias=True)
  )
)
于 2019-06-25T21:43:16.177 回答
25

这将显示模型的权重和参数（但不显示输出形状）。

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 添加一个model.summary()与 keras 完全一样的https://github.com/pytorch/pytorch/pull/3043/files

于 2017-08-06T04:33:58.830 回答
17

torchinfo（以前的torchsummary）包产生与 Keras 1类似的输出（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
==========================================================================================

笔记：

  1. Torchinfo 提供的信息与 PyTorch 中提供的信息相辅相成print(your_model)，类似于 Tensorflow 的model.summary()...

  2. 与 Keras 不同，PyTorch 有一个动态计算图，它可以适应多个调用中的任何兼容输入形状，例如任何足够大的图像尺寸（对于完全卷积网络）。

    因此，它不能为每一层呈现一组固有的输入/输出形状，因为它们是依赖于输入的，以及为什么在上述包中必须指定输入尺寸。
于 2021-04-07T10:41:01.463 回答
13

最容易记住（不如 Keras 漂亮）：

print(model)

这也有效：

repr(model)

如果您只想要参数的数量：

sum([param.nelement() for param in model.parameters()])

来自：是否有与 keras 中的 model.summary() 类似的 pytorch 函数？（论坛.PyTorch.org）

于 2018-02-07T08:39:25.967 回答
13

您可以使用

from torchsummary import summary

您可以指定设备

device = torch.device("cuda" if torch.cuda.is_available() else "cpu")

您可以创建一个网络，如果您使用的是 MNIST 数据集，那么以下命令将起作用并向您显示摘要

model = Network().to(device)
summary(model,(1,28,28))
于 2020-01-11T17:03:02.947 回答
4

Keras 喜欢使用 torchsummary 进行模型摘要：

from torchsummary import summary
summary(model, input_size=(3, 224, 224))
于 2020-08-12T08:15:30.567 回答
1

为模型类定义对象后简单地打印模型

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)
于 2019-02-07T19:50:57.440 回答
0

summary(my_model, (3, 224, 224), device = 'cpu')将解决问题。

于 2021-04-09T10:29:39.737 回答
0

我更喜欢这个简单的片段 -

net = model
modules = [module for module in net.modules()]
params = [param.shape for param in net.parameters()]

# Print Model Summary
print(modules[0])
total_params=0
for i in range(1,len(modules)):
   j = 2*i
   param = (params[j-2][1]*params[j-2][0])+params[j-1][0]
   total_params += param
   print("Layer",i,"->\t",end="")
   print("Weights:", params[j-2][0],"x",params[j-2][1],
         "\tBias: ",params[j-1][0], "\tParameters: ", param)
print("\nTotal Params: ", total_params)

这打印了我需要的一切 -

Net(
  (hLayer1): Linear(in_features=1024, out_features=256, bias=True)
  (hLayer2): Linear(in_features=256, out_features=128, bias=True)
  (hLayer3): Linear(in_features=128, out_features=64, bias=True)
  (outLayer): Linear(in_features=64, out_features=10, bias=True)
)
Layer 1 ->  Weights: 256 x 1024     Bias:  256  Parameters:  262400
Layer 2 ->  Weights: 128 x 256      Bias:  128  Parameters:  32896
Layer 3 ->  Weights: 64 x 128       Bias:  64   Parameters:  8256
Layer 4 ->  Weights: 10 x 64        Bias:  10   Parameters:  650

Total Parameters:  304202
于 2022-02-28T02:19:01.967 回答