Sotiris Gkouzias

Set the `input_shape` argument of your Dense layer equal to `(sequence_length * raw_data.shape[-1],)`

TensorFlow version `2.8` works as well!

Could you save and load the model having TensorFlow==2.11.0? I ultimately installed TensorFlow==2.8.1 and everything worked (mixed precision was utilized as well).

It is really frustrating indeed. The silly thing is that with JAX as the Keras backend GPU is utilized smoothly (still my RTX3060 GPU is not in the list of...

@haifeng-jin , @MarkDaoust, @8bitmp3 I await any suggestions or revisions if needed. Do we have any updates?

> As I remembered, the current recommended way to install TF is to use `pip`. I do not have further info on this. @MarkDaoust may comment on this. @haifeng-jin it...

> configure manually the environment variables as appropriate @mihaimaruseac shouldn't we explain/specify how to configure manually the environment variables as appropriate?

> Why is conda mentioned in this patch? It makes the install guide more convoluted and seems unnecessary to me. @Tachi107 I agree. Should I proceed to erase everything related...

> Note that I'm not a tensorflow maintainer, just a casual user who happened to stumble upon this patch. But yeah, if I were you I would just show how...

@haifeng-jin , @MarkDaoust, @8bitmp3 I await any suggestions or revisions if needed. Do we have any updates?