问题
I am trying to use tf.distribute.MirroredStrategy() for multi GPU training in Tensorflow 2, on a model with CTC loss.
Problem is that model needs defining target_tensors in order to compile. What can be the cause of that? Is there some workaround and compile model without defining target_tensors?
If I do not pass the targets I get the following:
TypeError: Value passed to parameter 'indices' has DataType float32 not in list of allowed values: uint8, int32, int64
The model is defined using Keras functional API by using something like:
model = Model(name ='Joined_Model_2',inputs=self.inp, outputs=[self.network.outp, self.network.outp_stt])
The model must be compiled as:
self.model_joined.compile(optimizer=optimizer_stt,
loss=losses,
loss_weights= lossWeights,
target_tensors=[target1, target2]
)
The model has 2 outputs, but the CTC loss used on the second one is causing the problem.
回答1:
This is solved by using tf-nightly version.
Tf-nightly doesn't allow using target_tensors in eager execution mode. With nightly version my model successfully compiled without target tensors (no changes in implementation), so the problem is solved.
来源:https://stackoverflow.com/questions/61441798/how-to-avoid-defining-target-tensors-in-tensorflow-2-for-ctc-loss-model