Akash Saravanan
Akash Saravanan
size_average=False returns a tensor containing individual SSIM scores instead of returning their sum
Hi, I'm not sure if this behavior is intended or not but for a batch of 64 images, when I set size_average=False, i get a tensor of size 64 with...
Hi, I came across this while looking for a PyTorch implementation of SSIM. On the Tensorflow page for SSIM it's mentioned that "Note: The true SSIM is only defined on...
Adding in a version of selfplay that's compatible with the new gym API. I've not used any actual RL libraries in (since I wanted to put a general purpose example),...
Title essentially. Every now and then during training I get this warning. I don't think it will really impact anything for me but just wanted to bring it up in...
Hi, I encountered an odd situation during training where `battle.opponent_active_pokemon` was None. I was wondering why this would be the case. Even more odd is that `battle.turn` returns 0 and...
Hi, So given the changes to poke-env, the old way of doing selfplay (`examples/experimental-self-play.py`) no longer works. I'm a little confused as to how I can do it now since...
So there's actually two bugs. The first is what I mentioned [here](https://github.com/hsahovic/poke-env/issues/292). Specifically, in the scenario where `battle.force_switch` is True and there are no Pokemon left on the bench, both...
Hi @hsahovic, I've been working on a reinforcement learning agent and had a question about the battle.available_switches. From `poke_env/environment/battle.py` I can see that `battle.available_switches` is based off this code snippet:...
Hi! I was wondering if there was any specific reason for having a different value returned in `battle.side_conditions` and `battle.opponent_side_conditions` for `SPIKES` and `TOXIC_SPIKES` alone. I understand that they are...
Hiya, I was wondering if there's any way to access the timer for weather and other effects like reflect etc. On Pokemon Showdown this is usually visible as a small...