Tensorflow 2.0 中 KerasLayer 的 TimeDistributed

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

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()

这是我得到的：

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

有什么建议么？ 是否可以将 KerasLayer 转换为 Conv2D...层？

看来你不能使用TimeDistributed层来解决这个问题。但是，由于您不希望 Resnet 进行训练而只需要输出，因此您可以执行以下操作来避免TimeDistributed layer.

代替model.add(TimeDistributed(base_model, input_shape=(15, 244, 244, 3))), do

Option 1

# 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))
)

Option 2

如果您不想过多依赖输出形状（但这会牺牲性能）。

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))
)