If you're using Colab and you feel like training your model on GPU is slow, switch to the TPU runtime and tune the "steps_per_execution" parameter in compile(). Seeing a 5-10x speedup is pretty common.
Show this thread
-
That's cool. However, it didn't worked with keras image generators the last time I tried
You have to use a http://tf.data Dataset, like this:https://keras.io/examples/vision/image_classification_from_scratch/#generate-a-dataset …
-
-
Thanks, I came to this conclusion. Yet it isn't always simple to migrate the data processing pipeline to the http://tf.data api.
-
Don't you all think it's amazing to receive direct answers to anybody's questions from
@fchollet ? That is true influence and leadership...
End of conversation
New conversation -
Loading seems to be taking a while.
Twitter may be over capacity or experiencing a momentary hiccup. Try again or visit Twitter Status for more information.