python - Tensorflow Autoencoder ValueError：没有为任何变量提供梯度
问题描述
我正在尝试使用 tensorflow 创建一个自动编码器，用于分析大学项目的汽车数据集。但是，代码在开始训练时会输出一个错误，我似乎找不到解决方案。
首先，我尝试阅读该fit函数的 tensorflow 文档，但没有提及此错误。接下来，我尝试在 StackOverflow 上搜索类似的错误，但找不到任何相关的内容。
import os
import pathlib
import cv2
import numpy as np
import tensorflow as tf
from tensorflow import keras
from tensorflow.keras import backend as K
from tensorflow.keras.layers import (Activation, BatchNormalization, Conv2D,
Conv2DTranspose, Dense, Flatten, Input,
LeakyReLU, Reshape)
from tensorflow.keras.models import Model
from tensorflow.keras.optimizers import Adam
# Configuration
HEIGHT = 28
WIDTH = 32
NUM_CHANNELS = 3
BATCH_SIZE = 32
LATENT_SPACE_DIM = 20
EPOCHS = 25
AUTOTUNE = tf.data.experimental.AUTOTUNE
# Download dataset
dataset_url = "http://ai.stanford.edu/~jkrause/car196/car_ims.tgz"
data_dir = tf.keras.utils.get_file(origin=dataset_url,
fname='car_ims',
untar=True)
data_dir = pathlib.Path(data_dir)
normalization_layer = tf.keras.layers.experimental.preprocessing.Rescaling(1./255)
# Load dataset
dataset = tf.keras.preprocessing.image_dataset_from_directory(
data_dir,
labels=None,
image_size=(WIDTH, HEIGHT),
seed=123,
validation_split=0.3,
subset="training",
smart_resize=True,
batch_size=BATCH_SIZE)
dataset = dataset.map(normalization_layer)
dataset = dataset.cache()
dataset = dataset.prefetch(buffer_size=AUTOTUNE)
# Load testset
testset = tf.keras.preprocessing.image_dataset_from_directory(
data_dir,
labels=None,
image_size=(WIDTH, HEIGHT),
seed=123,
validation_split=0.3,
subset="validation",
smart_resize=True,
batch_size=BATCH_SIZE)
testset = testset.map(normalization_layer)
testset = testset.cache()
testset = testset.prefetch(buffer_size=AUTOTUNE)
# Encoder
inputs = Input(shape =(WIDTH, HEIGHT, NUM_CHANNELS))
x = Conv2D(32, (3, 3), strides=2, padding="same")(inputs)
x = LeakyReLU(alpha=0.2)(x)
x = BatchNormalization()(x)
x = Conv2D(64, (3, 3), strides=2, padding="same")(x)
x = LeakyReLU(alpha=0.2)(x)
x = BatchNormalization()(x)
volumeSize = K.int_shape(x)
x = Flatten()(x)
# Latent space
latent = Dense(LATENT_SPACE_DIM, name="latent")(x)
#decoder
latentInputs = Input(shape=(LATENT_SPACE_DIM,))
y = Dense(np.prod(volumeSize[1:]))(latentInputs)
y = Reshape((volumeSize[1], volumeSize[2], volumeSize[3]))(y)
y = Conv2DTranspose(64, (3, 3), strides=2, padding="same")(y)
y = LeakyReLU(alpha=0.2)(y)
y = BatchNormalization()(y)
y = Conv2DTranspose(32, (3, 3), strides=2, padding="same")(y)
y = LeakyReLU(alpha=0.2)(y)
y = BatchNormalization()(y)
y = Conv2DTranspose(NUM_CHANNELS, (3, 3), padding="same")(y)
outputs = Activation("sigmoid", name="decoded")(y)
encoder = Model(inputs, latent, name="encoder")
decoder = Model(latentInputs, outputs, name="decoder")
autoencoder = Model(inputs=inputs, outputs=decoder(encoder(inputs)))
encoder.summary()
decoder.summary()
autoencoder.summary()
# Prepare model
autoencoder.compile(loss="mse", optimizer=Adam(learning_rate=1e-3))
# train the convolutional autoencoder
history = autoencoder.fit(
dataset,
validation_data=testset,
epochs=EPOCHS,
batch_size=BATCH_SIZE)
有错误的输出部分：
Epoch 1/25
Traceback (most recent call last):
File "/home/mightymime/repos/TA-2021/src/main.py", line 111, in <module>
history = autoencoder.fit(
File "/home/mightymime/.local/lib/python3.9/site-packages/tensorflow/python/keras/engine/training.py", line 1183, in fit
tmp_logs = self.train_function(iterator)
File "/home/mightymime/.local/lib/python3.9/site-packages/tensorflow/python/eager/def_function.py", line 889, in __call__
result = self._call(*args, **kwds)
File "/home/mightymime/.local/lib/python3.9/site-packages/tensorflow/python/eager/def_function.py", line 933, in _call
self._initialize(args, kwds, add_initializers_to=initializers)
File "/home/mightymime/.local/lib/python3.9/site-packages/tensorflow/python/eager/def_function.py", line 763, in _initialize
self._stateful_fn._get_concrete_function_internal_garbage_collected( # pylint: disable=protected-access
File "/home/mightymime/.local/lib/python3.9/site-packages/tensorflow/python/eager/function.py", line 3050, in _get_concrete_function_internal_garbage_collected
graph_function, _ = self._maybe_define_function(args, kwargs)
File "/home/mightymime/.local/lib/python3.9/site-packages/tensorflow/python/eager/function.py", line 3444, in _maybe_define_function
graph_function = self._create_graph_function(args, kwargs)
File "/home/mightymime/.local/lib/python3.9/site-packages/tensorflow/python/eager/function.py", line 3279, in _create_graph_function
func_graph_module.func_graph_from_py_func(
File "/home/mightymime/.local/lib/python3.9/site-packages/tensorflow/python/framework/func_graph.py", line 999, in func_graph_from_py_func
func_outputs = python_func(*func_args, **func_kwargs)
File "/home/mightymime/.local/lib/python3.9/site-packages/tensorflow/python/eager/def_function.py", line 672, in wrapped_fn
out = weak_wrapped_fn().__wrapped__(*args, **kwds)
File "/home/mightymime/.local/lib/python3.9/site-packages/tensorflow/python/framework/func_graph.py", line 986, in wrapper
raise e.ag_error_metadata.to_exception(e)
ValueError: in user code:
/home/mightymime/.local/lib/python3.9/site-packages/tensorflow/python/keras/engine/training.py:855 train_function *
return step_function(self, iterator)
/home/mightymime/.local/lib/python3.9/site-packages/tensorflow/python/keras/engine/training.py:845 step_function **
outputs = model.distribute_strategy.run(run_step, args=(data,))
/home/mightymime/.local/lib/python3.9/site-packages/tensorflow/python/distribute/distribute_lib.py:1285 run
return self._extended.call_for_each_replica(fn, args=args, kwargs=kwargs)
/home/mightymime/.local/lib/python3.9/site-packages/tensorflow/python/distribute/distribute_lib.py:2833 call_for_each_replica
return self._call_for_each_replica(fn, args, kwargs)
/home/mightymime/.local/lib/python3.9/site-packages/tensorflow/python/distribute/distribute_lib.py:3608 _call_for_each_replica
return fn(*args, **kwargs)
/home/mightymime/.local/lib/python3.9/site-packages/tensorflow/python/keras/engine/training.py:838 run_step **
outputs = model.train_step(data)
/home/mightymime/.local/lib/python3.9/site-packages/tensorflow/python/keras/engine/training.py:799 train_step
self.optimizer.minimize(loss, self.trainable_variables, tape=tape)
/home/mightymime/.local/lib/python3.9/site-packages/tensorflow/python/keras/optimizer_v2/optimizer_v2.py:530 minimize
return self.apply_gradients(grads_and_vars, name=name)
/home/mightymime/.local/lib/python3.9/site-packages/tensorflow/python/keras/optimizer_v2/optimizer_v2.py:630 apply_gradients
grads_and_vars = optimizer_utils.filter_empty_gradients(grads_and_vars)
/home/mightymime/.local/lib/python3.9/site-packages/tensorflow/python/keras/optimizer_v2/utils.py:75 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', 'batch_normalization/gamma:0', 'batch_normalization/beta:0', 'conv2d_1/kernel:0', 'conv2d_1/bias:0', 'batch_normalization_1/gamma:0', 'batch_normalization_1/beta:0', 'latent/kernel:0', 'latent/bias:0', 'dense/kernel:0', 'dense/bias:0', 'conv2d_transpose/kernel:0', 'conv2d_transpose/bias:0', 'batch_normalization_2/gamma:0', 'batch_normalization_2/beta:0', 'conv2d_transpose_1/kernel:0', 'conv2d_transpose_1/bias:0', 'batch_normalization_3/gamma:0', 'batch_normalization_3/beta:0', 'conv2d_transpose_2/kernel:0', 'conv2d_transpose_2/bias:0'].
谁能帮我调试一下？提前致谢
解决方案
问题在于数据集加载。显然，数据集是一种结构，应该包含自动编码器的输入和预期输出（标签）。但是，我加载的方式不包括标签。
将加载更改为这样解决了问题：
listset = tf.data.Dataset.list_files(str(data_dir / "*"))
def convert_path_to_image(file_path):
# load the raw data from the file as a string
img = tf.io.read_file(file_path)
img = tf.image.decode_png(img, channels=3)
img = tf.image.convert_image_dtype(img, tf.float32)
img = tf.keras.preprocessing.image.smart_resize(img, [WIDTH,HEIGHT])
return img, img
dataset = listset.map(convert_path_to_image, num_parallel_calls = AUTOTUNE)
dataset = dataset.cache()
dataset = dataset.batch(batch_size=BATCH_SIZE)
dataset = dataset.prefetch(buffer_size=AUTOTUNE)
推荐阅读
- javascript - 我想用 javascript 创建一个图像滑块
- python - Moviepy - 带有 TextClip 的 CompositeVideoClip 错误
- vba - 将 PostMessage WM_KEYDOWN/UP 发送到记事本编辑控件适用于 VK_F5，但不适用于普通字母
- python - 图像相似度的连体网络
- django - 如何知道用户点击注销后是否到达登录页面？姜戈
- javascript - 在 Popup 加载时从 Magnific Popup 的调用按钮访问属性
- c++ - Boost.Python 不是 .lib
- azure - 警告： foo 的数据已达到每日 0.0323 GB 的上限，并且您的应用遥测数据的收集将停止，直到 UTC 时间 2018 年 6 月 23 日上午 9:00
- java - 如何从源代码中获取使用 Gradle 构建的工件版本
- python-3.x - 如何保存和恢复 tf.estimator 模型