Gustavo Hylander

i can try to implement the feature visualization itself for caffe and maybe keras models, but i lack the knowledge to do the front end stuff (select file, show activations...

ah i see, yes, it wouldn't be possible to have it runing in the browser, since deconvolution/gradient ascent operations are required i'm developing the feature visualization for keras models using...

either install old versions of scipy, or in the scripts replace imsave with `imageio.imwrite`

real shame, I used to use hyperdash a lot > Probably Optuna may be an option: https://github.com/optuna/optuna @Xtaltec from what i could gather, optuna runs on localhost and you would...

The code I posted is executable top to bottom (given you meet the dependency, tensorflow). While it uses the cats and dogs tensorflow dataset, it mimics exactly my real code,...

While I'm at this, I'd also like to inquire about using individual datasets, instead of a zipped one I tried to do: ``` history = model.fit([train_dataset1, train_dataset2, train_dataset3], epochs=epochs, callbacks=callbacks,...

Hi Any progress on this matter? I know it's possible to write custom training loops, but this seems like something the built-in training loop should be able to handle

thanks for the input @gowthamkpr, but that's my very own SO issue I opened before I figured out: 1) How to approach/implement what I wanted to do (use 3 separate...

Thanks for the reply, I think it made things clearer. If I'm not mistaken, the diagram below is the full "tensor-flow" (heh, no pun intended) of the CSRA module implemented...

As an update to this, I managed to implement almost all of CSRA in my MobileNetV3 model. Had to dive deep into both the pytorch and tensorflow docs to fully...