Subhojeet Pramanik

Hi, you can proceed with using this project for your projects, commercial or open-source using your choice of license. I'll update the current license to Apache for future developers.

Hi, Thanks for opening this issue. The model urls were moved and have now been fixed in the latest commit. Please, check and confirm.

Are you using the provided deep-tf conda environment during running the notebook? Generally, the parameters n_jobs not found is related to installed version of the xgboost library. > Thanks for...

Can you check and confirm whether all the images for COCO are stored in a single folder data/coco/train_val?

I figured a way to do this. Here is a sample code: ```python class LinearModule(torch.nn.Module): def __init__(self): super(LinearModule, self).__init__() self.model,params=functorch.make_functional(torch.nn.Linear(10,20)) self.params=torch.nn.ParameterList(params) def forward(self,inputs): return self.model(self.params,inputs) ```

The implementation is based on the following blog https://blog.heuritech.com/2016/01/20/attention-mechanism/ . The soft attention returns a weighted arithmetic mean of the y_i, and the weights are chosen according the relevance of...