嵌套模型时没有提供渐变 Keras Tensorflow

Question

我开始稍微使用 Keras，但我遇到了这个问题，它告诉我没有提供渐变。我知道这个问题之前已经发布了 100 次，但解决方案总是在谈论使用 GradientTape 但我不明白我为什么要这样做（我什至不明白它的作用）

import tensorflow as tf
from tensorflow import keras
from tensorflow.keras import layers
import matplotlib.pyplot as plt

physical_devices = tf.config.list_physical_devices('GPU')
tf.config.experimental.set_memory_growth(physical_devices[0], True)

class AutoEncoder:

    def create_encoder(self):
        encoder_input = keras.Input(shape=self.input_shape, name="original_img")
        encoder_output = layers.Conv2D(3, 3, activation="relu")(encoder_input)
        encoder = keras.Model(encoder_input, encoder_output)
        return encoder_input, encoder_output, encoder

    def create_decoder(self, eager_execution=False):
        decoder_input = keras.Input(shape=self.encoder_output.type_spec.shape[1:], batch_size=self.batch_size, name="encoded_img")
        decoder_output = layers.Conv2DTranspose(3, 3, activation="relu")(decoder_input)
        decoder = keras.Model(decoder_input, decoder_output)
        return decoder_input, decoder_output, decoder


    def create_autoencoder(self):
        auto_input = keras.Input(shape=self.input_shape, batch_size=self.batch_size, name="AutoEncoder Input")
        encoded = self.encoder(auto_input)
        auto_output = self.decoder(encoded)
        autoencoder = keras.Model(auto_input, auto_output, name="AutoEncoder")
        return auto_input, auto_output, autoencoder

    def __init__(self, input_shape=(256, 256, 3), batch_size=32, eager_execution=False):
        self.input_shape = input_shape
        self.batch_size = batch_size
        self.encoder_input, self.encoder_output, self.encoder = self.create_encoder()
        self.decoder_input, self.decoder_output, self.decoder = self.create_decoder()
        self.autoencoder_input, self.autoencoder_output, self.autoencoder = self.create_autoencoder()
        self.__call__ = self.autoencoder.predict
        self.fit = self.autoencoder.fit
        self.fit_generator = self.autoencoder.fit_generator

        # Compiling models

        self.autoencoder.compile(
            optimizer=keras.optimizers.Adagrad(),
            loss=keras.losses.SparseCategoricalCrossentropy(),
            metrics=keras.metrics.Accuracy(),
            run_eagerly=True,
        )


autoenc = AutoEncoder()
autoenc.autoencoder.fit(train_x)

对于培训，我使用一些来自 Microsoft 的数据集和 PetImages。但这不应该太重要。

我已经尝试重新排列所有内容，但是每次调用模型然后使用该模型的输出创建另一个模型时都会弹出错误。

Traceback (most recent call last):
  File "/home/user/PycharmProjects/pythonProject1/main.py", line 148, in <module>
    autoenc.autoencoder.fit(train_x)
  File "/home/user/miniconda3/envs/tf/lib/python3.8/site-packages/tensorflow/python/keras/engine/training.py", line 1100, in fit
    tmp_logs = self.train_function(iterator)
  File "/home/user/miniconda3/envs/tf/lib/python3.8/site-packages/tensorflow/python/keras/engine/training.py", line 805, in train_function
    return step_function(self, iterator)
  File "/home/user/miniconda3/envs/tf/lib/python3.8/site-packages/tensorflow/python/keras/engine/training.py", line 795, in step_function
    outputs = model.distribute_strategy.run(run_step, args=(data,))
  File "/home/user/miniconda3/envs/tf/lib/python3.8/site-packages/tensorflow/python/distribute/distribute_lib.py", line 1259, in run
    return self._extended.call_for_each_replica(fn, args=args, kwargs=kwargs)
  File "/home/user/miniconda3/envs/tf/lib/python3.8/site-packages/tensorflow/python/distribute/distribute_lib.py", line 2730, in call_for_each_replica
    return self._call_for_each_replica(fn, args, kwargs)
  File "/home/user/miniconda3/envs/tf/lib/python3.8/site-packages/tensorflow/python/distribute/distribute_lib.py", line 3417, in _call_for_each_replica
    return fn(*args, **kwargs)
  File "/home/user/miniconda3/envs/tf/lib/python3.8/site-packages/tensorflow/python/autograph/impl/api.py", line 572, in wrapper
    return func(*args, **kwargs)
  File "/home/user/miniconda3/envs/tf/lib/python3.8/site-packages/tensorflow/python/keras/engine/training.py", line 788, in run_step
    outputs = model.train_step(data)
  File "/home/user/miniconda3/envs/tf/lib/python3.8/site-packages/tensorflow/python/keras/engine/training.py", line 757, in train_step
    self.optimizer.minimize(loss, self.trainable_variables, tape=tape)
  File "/home/user/miniconda3/envs/tf/lib/python3.8/site-packages/tensorflow/python/keras/optimizer_v2/optimizer_v2.py", line 498, in minimize
    return self.apply_gradients(grads_and_vars, name=name)
  File "/home/user/miniconda3/envs/tf/lib/python3.8/site-packages/tensorflow/python/keras/optimizer_v2/optimizer_v2.py", line 598, in apply_gradients
    grads_and_vars = optimizer_utils.filter_empty_gradients(grads_and_vars)
  File "/home/user/miniconda3/envs/tf/lib/python3.8/site-packages/tensorflow/python/keras/optimizer_v2/utils.py", line 78, in filter_empty_gradients
    raise ValueError("No gradients provided for any variable: %s." %
ValueError: No gradients provided for any variable: ['conv2d/kernel:0', 'conv2d/bias:0', 'conv2d_transpose/kernel:0', 'conv2d_transpose/bias:0'].

Process finished with exit code 1

所有版本

# Name                    Version                   Build  Channel
tensorflow                2.2.0           gpu_py38hb782248_0  
tensorflow-base           2.2.0           gpu_py38h83e3d50_0  
tensorflow-datasets       4.1.0                    pypi_0    pypi
tensorflow-estimator      2.4.0                    pypi_0    pypi
tensorflow-gpu            2.4.0                    pypi_0    pypi
tensorflow-metadata       0.26.0                   pypi_0    pypi
tensorflow-probability    0.12.0                   pypi_0    pypi
tensorflow-serving-api    2.3.0                    pypi_0    pypi

System 
    Archlinux 
    linux-5.10.3.arch1-1
    cuda-11.2.0-2
    cudnn-8.0.5.39-1

我希望有人知道我应该改变什么才能让它发挥作用。

最好的问候， 潜水先生

Answer 1

我修复了你的代码。当您收到该错误时，您的损失函数和可训练变量之间的图表中没有路径，这在您的情况下是正确的。

1. 您没有标签来训练您的自动编码器。我添加了 train_x 作为你的标签。
2. 我认为 SparseCategoricalCrossentropy 不适用于您定义的架构。所以，我把它改成了 BinaryCrossEntropy
3. 当您为向量分配名称时，不允许使用空格，因此我将“AutoEncoder Input”更改为“AutoEncoder_Input”

这里是代码

import tensorflow as tf
from tensorflow import keras
from tensorflow.keras import layers
import matplotlib.pyplot as plt
from tensorflow.keras.preprocessing.image import ImageDataGenerator

#physical_devices = tf.config.list_physical_devices('GPU')
#tf.config.experimental.set_memory_growth(physical_devices[0], True)

class AutoEncoder:

    def create_encoder(self):
        encoder_input = keras.Input(shape=self.input_shape, name="original_img")
        encoder_output = layers.Conv2D(3, 3, activation="relu")(encoder_input)
        encoder = keras.Model(encoder_input, encoder_output)
        return encoder_input, encoder_output, encoder

    def create_decoder(self, eager_execution=False):
        decoder_input = keras.Input(shape=self.encoder_output.shape[1:], batch_size=self.batch_size, name="encoded_img")
        decoder_output = layers.Conv2DTranspose(3, 3, activation="relu")(decoder_input)
        decoder = keras.Model(decoder_input, decoder_output)
        return decoder_input, decoder_output, decoder


    def create_autoencoder(self):
        auto_input = keras.Input(shape=self.input_shape, batch_size=self.batch_size, name="AutoEncoder_Input")
        encoded = self.encoder(auto_input)
        auto_output = self.decoder(encoded)
        autoencoder = keras.Model(auto_input, auto_output, name="AutoEncoder")
        return auto_input, auto_output, autoencoder

    def __init__(self, input_shape=(256, 256, 3), batch_size=32, eager_execution=False):
        self.input_shape = input_shape
        self.batch_size = batch_size
        self.encoder_input, self.encoder_output, self.encoder = self.create_encoder()
        self.decoder_input, self.decoder_output, self.decoder = self.create_decoder()
        self.autoencoder_input, self.autoencoder_output, self.autoencoder = self.create_autoencoder()
        self.__call__ = self.autoencoder.predict
        self.fit = self.autoencoder.fit
        self.fit_generator = self.autoencoder.fit_generator

        # Compiling models

        self.autoencoder.compile(
            optimizer=keras.optimizers.Adagrad(),
            loss=keras.losses.BinaryCrossentropy(),
            metrics=keras.metrics.Accuracy(),
            run_eagerly=True,
        )
        



train_x = tf.random.normal(shape=(100,256,256,3),dtype=tf.float32)
autoenc = AutoEncoder()
print(autoenc.autoencoder.summary())
autoenc.autoencoder.fit(train_x,train_x)