Pawan Sasanka Ammanamanchi
Pawan Sasanka Ammanamanchi
We have started work on collecting bounding box annotations for our dataset, while our bounding-box labeled dataset maybe small. I think we should start thinking about implementing Object segmentation networks...
Fixes #236
Although we do our level best to find papers and add them to our reading list, if anyone else finds a paper interesting they can add the arxiv/conference paper link...
So when I trained the model initially with coverage off for 500k iterations, now what i would like to do is use this same model and further fine tune it...
Now that we support a multitude of basic layers, I'd like this issue to serve as the discussion for supporting advanced layers. While #54 tracked basic layers and most have...
Just a small-ish roadmap to different Optimizers and losses we can look at to add : Optimizers:- - [x] Adam - [x] Adagrad - [x] SGD - [x] RMSprop -...
There are a lot of layers which dont have test cases. I will start with adding test cases for Global Average Pooling and Global Max pooling, yet many are left....
The bug can be viewed [here](https://bugs.swift.org/browse/TF-499?jql=labels%20%3D%20StarterBug). This is the first step in solving #111. You can view the discussion [here](https://github.com/tensorflow/swift-apis/issues/111#issuecomment-486106358). This issue is for discussion of the same. CC :...
Currently, we define all layers assuming everything to be true by default. For example, `bias` within a variety of layers could be added as a boolean option, and initialization of...