model.summary() 的输出与预期的 tensorflow 2 不同

Question

我已经定义了一个复杂的深度学习模型，但出于这个问题的目的，我将使用一个简单的模型。

考虑以下几点：

import tensorflow as tf
from tensorflow.keras import layers, models


def simpleMLP(in_size, hidden_sizes, num_classes, dropout_prob=0.5):
    in_x = layers.Input(shape=(in_size,))
    hidden_x = models.Sequential(name="hidden_layers")
    for i, num_h in enumerate(hidden_sizes):
        hidden_x.add(layers.Dense(num_h, input_shape=(in_size,) if i == 0 else []))
        hidden_x.add(layers.Activation('relu'))
        hidden_x.add(layers.Dropout(dropout_prob))
    out_x = layers.Dense(num_classes, activation='softmax', name='baseline')
    return models.Model(inputs=in_x, outputs=out_x(hidden_x(in_x)))

我会以如下方式调用函数：

mdl = simpleMLP(28*28, [500, 300], 10)

现在当我执行mdl.summary() 时，我得到以下信息：

Model: "functional_1"
_________________________________________________________________
Layer (type)                 Output Shape              Param #   
=================================================================
input_1 (InputLayer)         [(None, 784)]             0         
_________________________________________________________________
hidden_layers (Sequential)   (None, 300)               542800    
_________________________________________________________________
baseline (Dense)             (None, 10)                3010      
=================================================================
Total params: 545,810
Trainable params: 545,810
Non-trainable params: 0
_________________________________________________________________

问题是Sequential块被压缩了，只显示最后一层，但参数的总和。

在我的复杂模型中，我有多个 Sequential 块全部隐藏。

有没有办法让它更冗长？我在模型定义中做错了吗？

编辑

使用pytorch 时，我看不到相同的行为，给出以下示例（取自here）：

import torch
import torch.nn as nn


class MyCNNClassifier(nn.Module):
    def __init__(self, in_c, n_classes):
        super().__init__()
        self.conv_block1 = nn.Sequential(
            nn.Conv2d(in_c, 32, kernel_size=3, stride=1, padding=1),
            nn.BatchNorm2d(32),
            nn.ReLU()
        )

        self.conv_block2 = nn.Sequential(
            nn.Conv2d(32, 64, kernel_size=3, stride=1, padding=1),
            nn.BatchNorm2d(64),
            nn.ReLU()
        )

        self.decoder = nn.Sequential(
            nn.Linear(32 * 28 * 28, 1024),
            nn.Sigmoid(),
            nn.Linear(1024, n_classes)
        )

    def forward(self, x):
        x = self.conv_block1(x)
        x = self.conv_block2(x)

        x = x.view(x.size(0), -1)  # flat

        x = self.decoder(x)

        return x

打印时我得到：

MyCNNClassifier(
  (conv_block1): Sequential(
    (0): Conv2d(1, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
    (1): BatchNorm2d(32, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
    (2): ReLU()
  )
  (conv_block2): Sequential(
    (0): Conv2d(32, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
    (1): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
    (2): ReLU()
  )
  (decoder): Sequential(
    (0): Linear(in_features=25088, out_features=1024, bias=True)
    (1): Sigmoid()
    (2): Linear(in_features=1024, out_features=10, bias=True)
  )
)

Answer 1

Tensorflow 2.x 中的模型总结没有错。

import tensorflow as tf
from tensorflow.keras import layers, models

def simpleMLP(in_size, hidden_sizes, num_classes, dropout_prob=0.5):
    in_x = layers.Input(shape=(in_size,))
    hidden_x = models.Sequential(name="hidden_layers")
    for i, num_h in enumerate(hidden_sizes):
        hidden_x.add(layers.Dense(num_h, input_shape=(in_size,) if i == 0 else []))
        hidden_x.add(layers.Activation('relu'))
        hidden_x.add(layers.Dropout(dropout_prob))
    out_x = layers.Dense(num_classes, activation='softmax', name='baseline')
    return models.Model(inputs=in_x, outputs=out_x(hidden_x(in_x)))

mdl = simpleMLP(28*28, [500, 300], 10)
mdl.summary()

输出：

Model: "functional_1"
_________________________________________________________________
Layer (type)                 Output Shape              Param #   
=================================================================
input_1 (InputLayer)         [(None, 784)]             0         
_________________________________________________________________
hidden_layers (Sequential)   (None, 300)               542800    
_________________________________________________________________
baseline (Dense)             (None, 10)                3010      
=================================================================
Total params: 545,810
Trainable params: 545,810
Non-trainable params: 0
_________________________________________________________________

您可以使用get_layer 根据图层的名称或索引检索图层。

如果同时提供名称和索引，则索引优先。 索引基于水平图遍历的顺序（自下而上）。

这里获取Sequential层（即mdl中索引为1）的详细信息，你可以试试

mdl.get_layer(index=1).summary()

输出：

Model: "hidden_layers"
_________________________________________________________________
Layer (type)                 Output Shape              Param #   
=================================================================
dense_2 (Dense)              (None, 500)               392500    
_________________________________________________________________
activation_2 (Activation)    (None, 500)               0         
_________________________________________________________________
dropout_2 (Dropout)          (None, 500)               0         
_________________________________________________________________
dense_3 (Dense)              (None, 300)               150300    
_________________________________________________________________
activation_3 (Activation)    (None, 300)               0         
_________________________________________________________________
dropout_3 (Dropout)          (None, 300)               0         
=================================================================
Total params: 542,800
Trainable params: 542,800
Non-trainable params: 0
_________________________________________________________________