我正试图在动力学数据集的一个子集上训练一个简单的3DCNN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((.调用的输入
tensorflow版本：r1.12
tf.data.Dataset初始化的生成器生成一个np.array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(22，(的类的一个热编码
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.
tf.keras似乎不喜欢我输入数据的格式。我对tf/keras还很陌生，但并没有从这个错误消息中收集到很多信息。如果有人对问题有任何见解，我们将不胜感激。
我在分发时遇到了类似的问题
<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 rankValueError:无法获取列组未知的形状的长度。"(对于遇到类似问题的人，我的解决方案是使用我的DatasetV1Adapter数据集，并使用data.dataset.from_generator创建一个新的数据集，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！
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4维输入图像和1维输出阵列。