Tensorflow 2.0中KerasLayer的时间分布 [英] TimeDistributed of a KerasLayer in Tensorflow 2.0

问题描述

我正在尝试使用来自tensorflow-hub的预训练模型构建CNN + RNN:

I'm trying to build a CNN + RNN using a pre-trained model from tensorflow-hub:

base_model = hub.KerasLayer('https://tfhub.dev/google/imagenet/resnet_v2_50/feature_vector/4', input_shape=(244, 244, 3)
base_model.trainable = False

model = Sequential()
model.add(TimeDistributed(base_model, input_shape=(15, 244, 244, 3)))
model.add(LSTM(512))
model.add(Dense(256, activation='relu'))
model.add(Dense(3, activation='softmax'))

adam = Adam(learning_rate=learning_rate)
model.compile(loss='categorical_crossentropy' , optimizer=adam , metrics=['accuracy'])
model.summary()

这就是我得到的:

2020-01-29 16:1

2020-01-29 16:1

6:37.585888: I tensorflow/core/platform/profile_utils/cpu_utils.cc:94] CPU Frequency: 2494000000 Hz
2020-01-29 16:16:37.586205: I tensorflow/compiler/xla/service/service.cc:168] XLA service 0x3b553f0 executing computations on platform Host. Devices:
2020-01-29 16:16:37.586231: I tensorflow/compiler/xla/service/service.cc:175]   StreamExecutor device (0): Host, Default Version
Traceback (most recent call last):
  File "./RNN.py", line 45, in <module>
    model.add(TimeDistributed(base_model, input_shape=(None, 244, 244, 3)))
  File "/usr/local/lib/python3.6/dist-packages/tensorflow_core/python/training/tracking/base.py", line 457, in _method_wrapper
    result = method(self, *args, **kwargs)
  File "/usr/local/lib/python3.6/dist-packages/tensorflow_core/python/keras/engine/sequential.py", line 178, in add
    layer(x)
  File "/usr/local/lib/python3.6/dist-packages/tensorflow_core/python/keras/engine/base_layer.py", line 842, in __call__
    outputs = call_fn(cast_inputs, *args, **kwargs)
  File "/usr/local/lib/python3.6/dist-packages/tensorflow_core/python/keras/layers/wrappers.py", line 256, in call
    output_shape = self.compute_output_shape(input_shape).as_list()
  File "/usr/local/lib/python3.6/dist-packages/tensorflow_core/python/keras/layers/wrappers.py", line 210, in compute_output_shape
    child_output_shape = self.layer.compute_output_shape(child_input_shape)
  File "/usr/local/lib/python3.6/dist-packages/tensorflow_core/python/keras/engine/base_layer.py", line 639, in compute_output_shape
    raise NotImplementedError
NotImplementedError

有什么建议吗? 是否可以将KerasLayer转换为Conv2D，...图层?

any suggestions? Is it possible to convert a KerasLayer to Conv2D,... layers?

推荐答案

看来您不能使用TimeDistributed层来解决此问题.但是，由于您不希望Resnet训练而只需要输出，因此可以执行以下操作以避免TimeDistributed层.

It doesn't seem like you can use the TimeDistributed layer for this problem. However, as you don't want Resnet to train and just need the output, you can do the following to avoid the TimeDistributed layer.

执行而不是model.add(TimeDistributed(base_model, input_shape=(15, 244, 244, 3)))

# 2048 is the output size
model.add(
    Lambda(
        lambda x: tf.reshape(base_model(tf.reshape(x, [-1, 244, 244,3])),[-1, 15, 2048])
    , input_shape=(15, 244, 244, 3))
)

选项2

如果您不想过分依赖输出形状(尽管这会牺牲性能).

Option 2

If you don't want to depend too much on the output shape (this sacrifices performance though).

model.add(
    Lambda(
        lambda x: tf.stack([base_model(xx) for xx in tf.unstack(x, axis=1) ], axis=1)
    , input_shape=(15, 244, 244, 3))
)

这篇关于Tensorflow 2.0中KerasLayer的时间分布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！