Aritra Roy Gosthipaty
Aritra Roy Gosthipaty
Will do!
Implementing cauchy-schwarz divergence and negative log likelihood as custom loss functions in Keras
Could you share a colab notebook with us with demo inputs? That would help us use the functions and also debug. TIA!
Implementing cauchy-schwarz divergence and negative log likelihood as custom loss functions in Keras
Hey @sivaramakrishnan-rajaraman Thanks for the colab, unfortunately I could not load the data and was not able to run the code. I saw that you were using scipy and numpy...
I have the same issue.
This is not a fix for this plugin, but i did this to overcome the problem: ~~~ child: WebView( initialUrl:'https://www.youtube.com/embed/jG2_TN-jfH4?autoplay=0&rel=0', javaScriptMode: JavaScriptMode.unrestricted, )
> > This is not a fix for this plugin, but i did this to overcome the problem: > > ``` > > child: WebView( > > initialUrl:'https://www.youtube.com/embed/jG2_TN-jfH4?autoplay=0&rel=0', > >...
Hey @osanseviero @merveenoyan I was successful in uploading the custom objects with `push_to_hub_keras` API. The main steps are: - Have a `get_config` method for all the custom layers. - Serialization...
> Worst case, we could throw some warning when there are custom layers being saved and pointing to documentation. WDYT? Yep. This is the only way to go. Even TensorFlow...
Hey @gante I love the insights that you bring to the table. I think https://github.com/huggingface/huggingface_hub/issues/598 covers the issue that you are talking about. Do let me know what you think.
I have tried hosting a `tf.Module` on the hub. These were the steps: - Build the `tf.Module` - Create a hub repo - Move the serialized and saved `tf.Module` into...