AttributeError:当模型为< class'keras.engine.training.Model'>时，“模型"对象没有属性"trainable_variables". [英] AttributeError: 'Model' object has no attribute 'trainable_variables' when model is <class 'keras.engine.training.Model'>

问题描述

我刚刚开始学习Tensorflow(2.1.0)，Keras(2.3.1)和Python 3.7.7.

I've just started to learn Tensorflow (2.1.0), Keras (2.3.1) and Python 3.7.7.

顺便说一句，我正在Windows 7 64bit的Anaconda环境上运行所有代码.我也在Linux上的Anaconda环境上尝试过，但出现了同样的错误.

By the way, I'm running all my code on an Anaconda Environment on Windows 7 64bit. I have also tried on an Anaconda Environment on Linux and I get the same error.

我正在关注Tensorflow的教程:"自定义培训:演练".

I'm following this Tensorflow's tutorial: "Custom training: walkthrough".

一切都很好，但是当我键入这段代码时:

Everything is ok, but when I typed this piece of code:

def grad(model, inputs, targets):
  with tf.GradientTape() as tape:
    loss_value = loss(model, inputs, targets, training=True)
  return loss_value, tape.gradient(loss_value, model.trainable_variables)

我得到了错误:

模型"的实例没有"trainable_variables"成员

Instance of 'Model' has no 'trainable_variables' member

这是我的模型，其中包含所有导入内容:

This is my model, with all of its imports:

import keras
from keras.models import Input, Model
from keras.layers import Dense, Conv2D, Conv2DTranspose, UpSampling2D, MaxPooling2D, Flatten, ZeroPadding2D
from keras.preprocessing.image import ImageDataGenerator
from keras.optimizers import Adam
import numpy as np
import tensorflow as tf

def vgg16_encoder_decoder(input_size = (200,200,1)):
    #################################
    # Encoder
    #################################
    inputs = Input(input_size, name = 'input')

    conv1 = Conv2D(64, (3, 3), activation = 'relu', padding = 'same', name ='conv1_1')(inputs)
    conv1 = Conv2D(64, (3, 3), activation = 'relu', padding = 'same', name ='conv1_2')(conv1)
    pool1 = MaxPooling2D(pool_size = (2,2), strides = (2,2), name = 'pool_1')(conv1)

    conv2 = Conv2D(128, (3, 3), activation = 'relu', padding = 'same', name ='conv2_1')(pool1)
    conv2 = Conv2D(128, (3, 3), activation = 'relu', padding = 'same', name ='conv2_2')(conv2)
    pool2 = MaxPooling2D(pool_size = (2,2), strides = (2,2), name = 'pool_2')(conv2)

    conv3 = Conv2D(256, (3, 3), activation = 'relu', padding = 'same', name ='conv3_1')(pool2)
    conv3 = Conv2D(256, (3, 3), activation = 'relu', padding = 'same', name ='conv3_2')(conv3)
    conv3 = Conv2D(256, (3, 3), activation = 'relu', padding = 'same', name ='conv3_3')(conv3)
    pool3 = MaxPooling2D(pool_size = (2,2), strides = (2,2), name = 'pool_3')(conv3)

    conv4 = Conv2D(512, (3, 3), activation = 'relu', padding = 'same', name ='conv4_1')(pool3)
    conv4 = Conv2D(512, (3, 3), activation = 'relu', padding = 'same', name ='conv4_2')(conv4)
    conv4 = Conv2D(512, (3, 3), activation = 'relu', padding = 'same', name ='conv4_3')(conv4)
    pool4 = MaxPooling2D(pool_size = (2,2), strides = (2,2), name = 'pool_4')(conv4)

    conv5 = Conv2D(512, (3, 3), activation = 'relu', padding = 'same', name ='conv5_1')(pool4)
    conv5 = Conv2D(512, (3, 3), activation = 'relu', padding = 'same', name ='conv5_2')(conv5)
    conv5 = Conv2D(512, (3, 3), activation = 'relu', padding = 'same', name ='conv5_3')(conv5)
    pool5 = MaxPooling2D(pool_size = (2,2), strides = (2,2), name = 'pool_5')(conv5)

    #################################
    # Decoder
    #################################
    #conv1 = Conv2DTranspose(512, (2, 2), strides = 2, name = 'conv1')(pool5)

    upsp1 = UpSampling2D(size = (2,2), name = 'upsp1')(pool5)
    conv6 = Conv2D(512, 3, activation = 'relu', padding = 'same', name = 'conv6_1')(upsp1)
    conv6 = Conv2D(512, 3, activation = 'relu', padding = 'same', name = 'conv6_2')(conv6)
    conv6 = Conv2D(512, 3, activation = 'relu', padding = 'same', name = 'conv6_3')(conv6)

    upsp2 = UpSampling2D(size = (2,2), name = 'upsp2')(conv6)
    conv7 = Conv2D(512, 3, activation = 'relu', padding = 'same', name = 'conv7_1')(upsp2)
    conv7 = Conv2D(512, 3, activation = 'relu', padding = 'same', name = 'conv7_2')(conv7)
    conv7 = Conv2D(512, 3, activation = 'relu', padding = 'same', name = 'conv7_3')(conv7)
    zero1 = ZeroPadding2D(padding =  ((1, 0), (1, 0)), data_format = 'channels_last', name='zero1')(conv7)

    upsp3 = UpSampling2D(size = (2,2), name = 'upsp3')(zero1)
    conv8 = Conv2D(256, 3, activation = 'relu', padding = 'same', name = 'conv8_1')(upsp3)
    conv8 = Conv2D(256, 3, activation = 'relu', padding = 'same', name = 'conv8_2')(conv8)
    conv8 = Conv2D(256, 3, activation = 'relu', padding = 'same', name = 'conv8_3')(conv8)

    upsp4 = UpSampling2D(size = (2,2), name = 'upsp4')(conv8)
    conv9 = Conv2D(128, 3, activation = 'relu', padding = 'same', name = 'conv9_1')(upsp4)
    conv9 = Conv2D(128, 3, activation = 'relu', padding = 'same', name = 'conv9_2')(conv9)

    upsp5 = UpSampling2D(size = (2,2), name = 'upsp5')(conv9)
    conv10 = Conv2D(64, 3, activation = 'relu', padding = 'same', name = 'conv10_1')(upsp5)
    conv10 = Conv2D(64, 3, activation = 'relu', padding = 'same', name = 'conv10_2')(conv10)

    conv11 = Conv2D(1, 3, activation = 'relu', padding = 'same', name = 'conv11')(conv10)

    model = Model(inputs = inputs, outputs = conv11, name = 'vgg-16_encoder_decoder')

    return model

我在 Tensorflow Keras模型文档.

在"将您的TensorFlow 1代码迁移到TensorFlow 2-2.使代码本机为2.0 "，说:

如果您需要汇总变量列表(例如 tf.Graph.get_collection(tf.GraphKeys.VARIABLES))，使用.variables 和模型对象的.trainable_variables属性.

If you need to aggregate lists of variables (like tf.Graph.get_collection(tf.GraphKeys.VARIABLES)), use the .variables and .trainable_variables attributes of the Layer and Model objects.

Tensorflow教程"自定义培训:演练"中的网络为:

The network in Tensorflow's tutorial "Custom training: walkthrough" is:

model = tf.keras.Sequential([
  tf.keras.layers.Dense(10, activation=tf.nn.relu, input_shape=(4,)),  # input shape required
  tf.keras.layers.Dense(10, activation=tf.nn.relu),
  tf.keras.layers.Dense(3)
])

当我这样做时:

print(type(model))

我得到:

<class 'tensorflow.python.keras.engine.sequential.Sequential'>

但是如果我打印网络类型vgg16_encoder_decoder，则会得到:

But if I print the type of my network, vgg16_encoder_decoder, I get:

<class 'keras.engine.training.Model'>

因此，问题是网络的类型.我以前没有说过上述课程'keras.engine.training.Model'.

So, the problem is the type of the network. I haven't say the above class, 'keras.engine.training.Model', before.

如何解决此问题以允许我使用属性trainable_variables?

How can I fix this problem to let me use the attribute trainable_variables?

推荐答案

问题是您使用的是keras库而不是tensorflow.keras. 当使用tensorflow时，强烈建议使用其自己的keras实现.

The problem is that you are using keras library instead of tensorflow.keras. When using tensorflow it is highly recommended to use its own keras implementation.

此代码应该有效

import tensorflow as tf
from tensorflow import keras
from tensorflow.keras.models import Model
from tensorflow.keras.layers import Input, Dense, Conv2D, Conv2DTranspose, UpSampling2D, MaxPooling2D, Flatten, ZeroPadding2D
from tensorflow.keras.preprocessing.image import ImageDataGenerator
from tensorflow.keras.optimizers import Adam
import numpy as np


def vgg16_encoder_decoder(input_size = (200,200,1)):
    # Your code here (no change needed)


model = vgg16_encoder_decoder()
model.trainable_variables

这篇关于AttributeError:当模型为< class'keras.engine.training.Model'>时，“模型"对象没有属性"trainable_variables".的文章就介绍到这了，希望我们推荐的答案对大家有所帮助，也希望大家多多支持IT屋！