Aditya Arora

Hello, I am trying to replicate the results using keras 2.0. I have understood the part where we extract question features. I am stuck with image feature extraction part. It...

PANet takes a lot of time in multi-scale training. It would be great if @ShuLiu1993 could tell how I can optimize the training time.

For DVD dataset, the original authors test set contains 100 images in each folder and [here](https://github.com/shuochsu/DeepVideoDeblurring/issues/2#issuecomment-312954167) they explain that they use only 30 frames per folder for testing. However, on...

Adding instructions to install Detectron2 and other dependencies such as PyTorch, CocoAPI, and scikit-learn.

Details about Training Set

4

Hi Thank you for sharing your research and open-source code. I was able to replicate your results using the pre-trained weights. I wanted to train a model, for which I...

**Proposed Change:** `Dist_A_fake` is incorrect and should be `Disc_A_fake` which is passed to `BCE_loss(Disc_A_fake, real)`.

ValueError: Input contains NaN, infinity or a value too large for dtype('float64').

2

plz help me out

Having separate issue templates

2

Currently, this repo is used as a part of blogging assistance as well to solve issues within the repo. It would be nice to see separate `Issue Template` for separate...