Resumen del modelo en pytorch

Question

Resumen del modelo en pytorch

¿Hay alguna manera, puedo imprimir el resumen de un modelo en PyTorch como lo hace el método model.summary() en Keras de la siguiente manera?

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

34

pytorch

Author: Wasi Ahmad, 2017-02-27

Source

5 answers

Esto mostrará los pesos y parámetros de un modelo (pero no la forma de salida).

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 tiene un PR pytorch para agregar un model.summary() que es exactamente como keras https://github.com/pytorch/pytorch/pull/3043/files

12

Author: wassname,
Warning: date(): Invalid date.timezone value 'Europe/Kyiv', we selected the timezone 'UTC' for now. in /var/www/agent_stack/data/www/ajaxhispano.com/template/agent.layouts/content.php on line 61
2018-02-15 02:21:28

Sí, puede obtener una representación exacta de Keras, usando el paquete pytorch-summary.

Ejemplo para VGG16

from torchvision import models
from torchsummary 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
----------------------------------------------------------------

12

Author: Shubham Chandel,
Warning: date(): Invalid date.timezone value 'Europe/Kyiv', we selected the timezone 'UTC' for now. in /var/www/agent_stack/data/www/ajaxhispano.com/template/agent.layouts/content.php on line 61
2018-07-25 22:18:13

AFAK no hay modelo.summary () como equivalente en pytorch

Mientras tanto, puedes referirte a script de szagoruyko, que da una buena visualización como en resnet18-example

Salud

1

Author: zoro,
Warning: date(): Invalid date.timezone value 'Europe/Kyiv', we selected the timezone 'UTC' for now. in /var/www/agent_stack/data/www/ajaxhispano.com/template/agent.layouts/content.php on line 61
2017-03-05 19:09:50

Más simple de recordar (no tan bonito como Keras):

print(model)

Esto también funciona:

repr(model)

Si solo desea el número de parámetros:

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

De: Hay una función de pytorch similar como modelo.summary() como keras? (forum.PyTorch.org)

1

Author: Punnerud,
Warning: date(): Invalid date.timezone value 'Europe/Kyiv', we selected the timezone 'UTC' for now. in /var/www/agent_stack/data/www/ajaxhispano.com/template/agent.layouts/content.php on line 61
2018-08-03 19:30:15

score 32 · Accepted Answer

Mientras que no obtendrá información tan detallada sobre el modelo como en el modelo de Keras.resumen, simplemente imprimiendo el modelo le dará alguna idea sobre las diferentes capas involucradas y sus especificaciones.

Por ejemplo:

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

La salida en este caso sería algo como sigue:

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)
  )
)

Ahora podría, como se menciona en Kashyap, usar el método state_dict para obtener los pesos de las diferentes capas. Pero el uso de esta lista de las capas tal vez proporcionar más dirección es la creación de una función de ayuda para obtener que Keras como resumen del modelo! Espero que esto ayude!