Poda Dei comments

Results 7 comments of


                                            Poda Dei

RuntimeWarning

For me, it started popping up recently. Same issue.

Working code broke after deploying to new installation. ValueError: When using `stateful=True` in a RNN, the batch size must be static. Found dynamic batch size: sequence.shape=(None, xx, xx)

So that was the working code, but after I updated to latest in fresh ubuntu install, "batch_input_shape" not a recognized attribute. This is what I am getting ```ValueError: Unrecognized keyword...

Working code broke after deploying to new installation. ValueError: When using `stateful=True` in a RNN, the batch size must be static. Found dynamic batch size: sequence.shape=(None, xx, xx)

Looks like either it is a bug or they got rid of the function, but either way, it is like a bug in how they configure the shape internally for...

Working code broke after deploying to new installation. ValueError: When using `stateful=True` in a RNN, the batch size must be static. Found dynamic batch size: sequence.shape=(None, xx, xx)

Anyone?

Working code broke after deploying to new installation. ValueError: When using `stateful=True` in a RNN, the batch size must be static. Found dynamic batch size: sequence.shape=(None, xx, xx)

If I add a input layer before LSTM layer, I get this, File "/.local/lib/python3.11/site-packages/keras/src/utils/traceback_utils.py", line 122, in error_handler raise e.with_traceback(filtered_tb) from None File ".local/lib/python3.11/site-packages/tensorflow/python/eager/execute.py", line 53, in quick_execute tensors =...

"Official Tensorflow Implementation" link is broken

I was going to say the same. Is it PeepholeLSTM ? Not sure if the author is still actively in here.

Trust issues !!!

I hear you. Thanks for the update.