Resumo do modelo em pytorch

Existe alguma maneira, eu posso imprimir o resumo de um modelo em PyTorch como o model.summary()método faz em Keras como segue?

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

Embora você não obtenha informações tão detalhadas sobre o modelo como no resumo do modelo de Keras, a simples impressão do modelo lhe dará uma ideia sobre as diferentes camadas envolvidas e suas especificações.

Por exemplo:

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

A saída, neste caso, seria algo como a seguir:

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)
  )
)

Agora você poderia, como mencionado por Kashyap , usar o state_dictmétodo para obter os pesos das diferentes camadas. Mas usar essa lista de camadas talvez forneça mais direção, é criar uma função auxiliar para obter o resumo do modelo de Keras! Espero que isto ajude!

Sim, você pode obter a representação exata de Keras, usando o pacote pytorch-summary .

Exemplo para VGG16

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
----------------------------------------------------------------

Para usar o tipo de resumo da tocha:

from torchsummary import summary

Instale-o primeiro, se não o tiver.

pip install torchsummary 

E então você pode tentar, mas observe por algum motivo que não está funcionando a menos que eu defina o modelo como 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)

O summarydeve ter o tamanho de entrada e o tamanho do lote é definido como -1, o que significa qualquer tamanho de lote que fornecemos.

Se definirmos summary(alexnet, (3, 224, 224), 32)isso significa usar o bs=32.

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

Fora:

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)
  )
)

Isso mostrará os pesos e parâmetros de um modelo (mas não a forma de saída).

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
# )

Editar: isaykatsman tem um PR pytorch para adicionar um model.summary()que é exatamente como keras https://github.com/pytorch/pytorch/pull/3043/files

Mais simples de lembrar (não tão bonita quanto Keras):

print(model)

Isso também funciona:

repr(model)

Se você quiser apenas o número de parâmetros:

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

De: Existe uma função pytorch semelhante a model.summary () as keras? (forum.PyTorch.org)

Você pode usar

from torchsummary import summary

Você pode especificar o dispositivo

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

Você pode criar uma rede e, se estiver usando conjuntos de dados MNIST, os seguintes comandos funcionarão e mostrarão um resumo

model = Network().to(device)
summary(model,(1,28,28))

AFAK não há model.summary () como equivalente em pytorch

Enquanto isso, você pode consultar o script de szagoruyko, que oferece uma boa visualização como em resnet18-example

Felicidades

Basta imprimir o modelo após definir um objeto para a classe do modelo

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)

Você pode apenas usar x.shape, a fim de medir as xdimensões do tensor

Para visualização e resumo dos PyTorchmodelos, tensorboardX também pode ser utilizado.