Harsh Nilesh Pathak

icon indicating a website link https://sites.google.com/view/harshnpathak/home icon indicating an email [email protected]

icon location Seattle icon location Data Science | Machine Learning | Deep Learning | AI

Results 8 comments of Harsh Nilesh Pathak

Issue training SRGAN with perceptual loss

Go to this commit in pull request: https://github.com/brade31919/SRGAN-tensorflow/pull/37/commits/61d0c25ae0ff298ab00f8ab324414073beb38b87 Thanks @ryancom16

results are super blurry

Yes, 1. You may try to change the crop size 2. Test intermediate results like after 2k iterations. 3. Analyze your PSNR plot and content loss plots

The output of conv2d should be updated after g and b are updated in data dependent initialization.

I have a simple question, what is the idea of having different weight normalization "flows" when init=True vs Init= False?

Weights returned as nan

https://github.com/harsh306/WeightNormalization

Active Learning

> This is for tracking interest in Active Learning, which is automatically annotating on new labels based on labels that have been done so far. Please 👍 if this is...

Sequential Model Save/Load Problems

I guess this is the issue. But this is also not resolved https://github.com/tensorflow/tensorflow/issues/31927

update slides

Corresponding Issue: https://github.com/dennybritz/reinforcement-learning/issues/232

support for simple 1d bifurcations

Currently, in this repo we have natural and pseudo arc-length continuation methods. It will be great if more types bifurcation points could be detected. Also above equations can be provided...