tf.data.Dataset 对象作为 tf.Keras 模型的输入——ValueError答案

【问题标题】：tf.data.Dataset object as input to tf.Keras model -- ValueErrortf.data.Dataset 对象作为 tf.Keras 模型的输入——ValueError
【发布时间】：2018-12-06 01:11:55
【问题描述】：

我正在尝试训练一个简单的 3DCNN，用于对动力学数据集的一个子集进行动作分类。我正在传递一个 tf.data.Dataset.from_generator() 对象作为对 model.fit() 的调用的输入。

张量流版本：r1.12

初始化 tf.data.Dataset 的生成器产生一个 np.arrays 元组。第一个是形状为(50,45,80,3)的预处理视频，第二个是形状为(22,)的类的one-hot编码

代码：

import os
import numpy as np
import itertools

import tensorflow as tf
import tensorflow.data as data
from tensorflow.keras.models import Sequential 
from tensorflow.keras.layers import MaxPooling3D, Conv3D, BatchNormalization, Dense 
from tensorflow.keras.layers import Dropout, Activation, Flatten, Input


def train_generator():
    train_dir = '/home/kjd/Storage/kinetics-frames_proc_small'
    classes = os.listdir(train_dir)
    for index, label in enumerate(classes):
        clips = os.listdir(train_dir + '/' + label)
        for clip in clips:
            data = np.load(train_dir + '/' + label + '/' + clip)
            yield data, np.eye(22)[index].astype(int)


EPOCHS = 3
BATCH_SIZE = 32
dataset = data.Dataset.from_generator(train_generator, (tf.int64, tf.int64))



model = Sequential()
model.add(Conv3D(16, (3,3,3), strides=(1,1,1), padding='same', activation='relu',
                 input_shape=(50,45,80,3)))
model.add(Conv3D(32, (3,3,3), strides=(1,1,1), padding='same', activation='relu'))
model.add(MaxPooling3D(pool_size=(2,2,2), strides=(2,2,2)))
model.add(BatchNormalization())
model.add(Conv3D(64, (3,3,3), strides=(1,1,1), padding='same', activation='relu'))
model.add(Conv3D(128, (3,3,3), strides=(1,1,1), padding='same', activation='relu'))
model.add(MaxPooling3D(pool_size=(2,2,2), strides=(2,2,2)))
model.add(BatchNormalization())
model.add(Conv3D(256, (3,3,3), strides=(1,1,1), padding='same', activation='relu'))
model.add(Conv3D(512, (3,3,3), strides=(1,1,1), padding='same', activation='relu'))
model.add(MaxPooling3D(pool_size=(2,2,2), strides=(2,2,2)))
model.add(BatchNormalization())
model.add(Flatten())
model.add(Dense(4096, activation='relu'))
model.add(Dropout(0.3))
model.add(Dense(4096, activation='relu'))
model.add(Dropout(0.3))
model.add(Dense(22, activation='softmax'))


model.compile('adam', 'categorical_crossentropy', metrics=['accuracy'])
model.fit(dataset, batch_size=BATCH_SIZE, epochs=EPOCHS, shuffle=False,
          steps_per_epoch=1000)

错误：

Traceback (most recent call last):
  File "train.py", line 55, in <module>
    steps_per_epoch=1000)
  File "/home/kjd/anaconda3/lib/python3.6/site-packages/tensorflow/python/keras/engine/training.py", line 1683, in fit
    shuffle=shuffle)
  File "/home/kjd/anaconda3/lib/python3.6/site-packages/tensorflow/python/keras/engine/training.py", line 1200, in _standardize_user_data
    class_weight, batch_size)
  File "/home/kjd/anaconda3/lib/python3.6/site-packages/tensorflow/python/keras/engine/training.py", line 1328, in _standardize_weights
    exception_prefix='input')
  File "/home/kjd/anaconda3/lib/python3.6/site-packages/tensorflow/python/keras/engine/training_utils.py", line 294, in standardize_input_data
    data = [standardize_single_array(x) for x in data]
  File "/home/kjd/anaconda3/lib/python3.6/site-packages/tensorflow/python/keras/engine/training_utils.py", line 294, in <listcomp>
    data = [standardize_single_array(x) for x in data]
  File "/home/kjd/anaconda3/lib/python3.6/site-packages/tensorflow/python/keras/engine/training_utils.py", line 228, in standardize_single_array
    if x.shape is not None and len(x.shape) == 1:
  File "/home/kjd/anaconda3/lib/python3.6/site-packages/tensorflow/python/framework/tensor_shape.py", line 745, in __len__
    raise ValueError("Cannot take the length of shape with unknown rank.")
ValueError: Cannot take the length of shape with unknown rank.

似乎 tf.keras 不喜欢我输入数据的格式。我对 tf/keras 相当陌生，但并没有从这个错误消息中收集到很多信息。如果有人对问题所在有任何见解，您的想法将不胜感激。

【问题讨论】：

标签： python tensorflow keras tensorflow-datasets

【解决方案1】：

我刚刚遇到了类似的问题，试图分发我的

<DatasetV1Adapter shapes: <unknown>, types: tf.float32>" dataset using strategy.experimental_distribute_dataset() with tf.distribute.MirroredStrategy() as strategy. I got the same error as above (" raise ValueError("Cannot take the length of shape with unknown rank ValueError：无法获取未知等级的形状长度。 ") 对于遇到类似问题的任何人，我的解决方案是使用我的 DatasetV1Adapter 数据集并使用 data.Dataset.from_generator 创建一个新数据集，如下所示：

        def generator(dataset):
            # dataset of type DatasetV1Adapter 
            for datapoint in dataset:
                yield datapoint

    dataset = tf.data.Dataset.from_generator(generator, (tf.float32), output_shapes=([None, None, None, None]))

dataset_dist = strategy.experimental_distribute_dataset(dataset)

为我工作！

【讨论】：

【解决方案2】：

我最近遇到了这个问题；您可能需要提供 output_shapes 参数：

dataset = data.Dataset.from_generator(train_generator, (tf.int64, tf.int64), output_shapes=(tf.TensorShape([None, None, None, None]), tf.TensorShape([None])))

假设一个 4 维输入图像和一个 1 维输出数组。

【讨论】：