Nobu

I am just learning how to implement PPO for continuous action spaces and this repo has been a godsend except one point. If we assume that the output of the...

@lijiannuist Can you confirm that you did not append the dataset with additional Asian faces?

@vlad3996 Can you please clarify where to put `torch.no_grad` in `demo.py`? I don't see it in your code nor do I see it in this repo's `demo.py`

in the repo's `demo.py`, I put it in the first line of `def infer()` but it didn't help.

@yihongXU This did not help. I also put `with torch.no_grad():` at the beginning of `def infer()` but neither worked. I also commented out parts for `det_b` and `det_s` and just...

@lijiannuist Can you clarify where to put `torch.no_grad()` in `demo.py`? I am getting the same error.

@ethanyhzhang Do you think we can build a Tensorflow/Keras version using this: https://github.com/microsoft/MMdnn?

it fills up the terminal so wondering how much of a slowdown this is for an already slow algo. ``` /tmp/pip-req-build-p5q91txh/torch/csrc/autograd/python_function.cpp:638: UserWarning: Legacy autograd function with non-static forward method is...

I am actually looking for the "in-the-wild" images with gender labels. Ie. with different poses, not just frontal. I can detect faces using MTCNN or other so just need gender...

@kamathhrishi @mpatacchiola are these notebooks to be run in Python 2 or 3? I have it running in Colab for Python 3 but getting errors. Here is my issue: https://github.com/mpatacchiola/deepgaze/issues/81