python - tutorial - Resumen del modelo en pytorch
pytorch udacity (7)
¿Hay alguna manera, puedo imprimir el resumen de un modelo en PyTorch como
model.summary()
método hace 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
AFAK no hay model.summary () como equivalente en pytorch
Mientras tanto, puede consultar el script de szagoruyko, que ofrece una buena visualización como en resnet18-example
Aclamaciones
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 RP de pytorch para agregar un
model.summary()
que es exactamente como keras
https://github.com/pytorch/pytorch/pull/3043/files
Más sencillo de recordar (no tan bonito como Keras):
print(model)
Esto también funciona:
repr(model)
Si solo quieres la cantidad de parámetros:
sum([param.nelement() for param in model.parameters()])
De: ¿Hay una función similar de pytorch como model.summary () como keras? (forum.PyTorch.org)
Para usar el tipo torchsummary:
from torchsummary import summary
Instálalo primero si no lo tienes.
pip install torchsummary
Y luego puede probarlo, pero tenga en cuenta que por alguna razón no funciona a menos que configure el modelo en 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)
El
summary
debe tomar el tamaño de entrada y el tamaño del lote se establece en -1, es decir, cualquier tamaño de lote que proporcionemos.
Si establecemos
summary(alexnet, (3, 224, 224), 32)
esto significa usar
bs=32
.
summary(model, input_size, batch_size=-1, device=''cuda'')
Fuera:
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)
)
)
Sí, puede obtener la representación exacta de Keras, utilizando 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 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
----------------------------------------------------------------
Si bien no obtendrá información tan detallada sobre el modelo como en el resumen del modelo de Keras, simplemente imprimiendo el modelo le dará una idea de 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 así:
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 lo menciona
Kashyap
, usar el método
state_dict
para obtener los pesos de las diferentes capas.
Pero el uso de esta lista de capas tal vez proporcione más dirección es crear una función de ayuda para que Keras tenga un resumen del modelo.
¡Espero que esto ayude!
Simplemente imprima el modelo después de definir un objeto para la clase de 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)