Vijay Veerabadran
Vijay Veerabadran
Hi, if you are interested in my trained weights, I just uploaded their checkpoints. You should be able to reproduce my results with these checkpoints.
Has this functionality for visualizing custom tensorflow models been added? Thanks!
Sure, I shall check it out. Thanks! :dancing_men:
@ludwigschubert I did go through the notebook, it's great! Although it looks like I'm stuck at a point where tensorflow computes an output size that goes negative. I am trying...
Yes, I am sure my model takes an input of size [224,224,3]. I am able to render visualizations if I switch the size of my average pool from 7 to...
@ludwigschubert THAT FIXED IT! :dancer: I guess it would be neat if you could emphasize somewhere early in the [tutorial notebook](https://colab.research.google.com/drive/1PPzeZi5sBN2YRlBmKsdvZPbfYtZI-pHl#scrollTo=06q00d8zvwqc) about passing the custom model input size through param....
@JaspervDalen You could check [this](https://github.com/vijayvee/lucid/blob/master/notebooks/custom_model_visualization.ipynb) notebook for something close. This notebook will walk you through creating visualizations for all conv layers in a network, but you could swap this out...
What I get from your previous message is, your goal is to find out the layers through which gradients are passing. The easiest way to just do this would be...
The second parts of trick 2 and trick 6 do the same thing, but are applied during different updates. Trick 6 - flip labels _occasionally_ while training D and trick...
I think the discriminator got too strong relative to the generator. Beyond this point, the generator finds it almost impossible to fool the discriminator, hence the increase in it's loss....