Marco Ancona

I don't see an obvious problem with your code. Seems you have some disconnected operations on the graph but that should not happen with within that snipped of code. Could...

Hi there! What is normally done for NLP, is to *sum up* attributions over the embedding dimensions. In your case, you would do `np.sum(attributions, -1)` and end up with an...

Hi! I think it is easier to create and train the model within the DeepExplain context from the beginning. Here is an example: ``` with DeepExplain(session=current_session) as de: #

Can you share the code you use to reload the weights?

No, the input shape should be the same. Just to double check, are you sure `model.layers[4].input` is the input of the `concat` layer? Can you try targeting `model.layers[4].output` instead? We...

Hi all, although we have planned support for PyTorch, we have not started implementing it nor gave a lot of thought about possible technical challenges. However, gradient-override in PyTorch should...

I see. Then I will have to continue relying on the "classic" Google Analytics with Measurement Protocol. Hopefully, Google Analytics web+apps will support that as a data source at some...

What about Measurement Protocol? If Firebase Analytics is based on the same underlying data of the classic Google Analytics, what prevents simply sending raw hit data?

Same here. Doc says  Unfortunately, it does not seem to work.

The tricky think is the authentication (Basic, OAuth, NLTM). What’s the easiest to use the already configured XHRApi module?