Ruoshi Liu

Yes, I installed version 0.1.2 of geeopt which is before the Stereographic update.

Please check the following tensorboard results, with orange being train curves and blue being valid curves. I obtained the following results with `python run.py --data_dir=./data --num_epochs=30 --log_dir=./logs --batch_size=1024 --num_layers=2 --cell_type=hyp_gru`...

Also new to the repo, but here the loss is composed of both intrinsic and extrinsic reward: https://github.com/jcwleo/curiosity-driven-exploration-pytorch/blob/bacbefdfbdbc4c4382ab67147c9c8410305a4978/agents.py#L144

@ferreirafabio What do you mean by "use the intrinsic rewards"? Can you point out which section in the paper stated that?

Thank you for the clarification. Let me make sure I understand your question. What you are saying is the code (referenced above) tries to minimize the loss function by **maximizing...

Good suggestion. We have thought about this but haven't found time to do it yet. It requires an estimate of the elevation (polar) angle of the input image. If you...

It's back online now! Not sure what was wrong with it in the past few days either ...

Apology for the downtime, the demo should be up and functional again... There was indeed a package incompatibility issue due to upgrade of pydantic.

Hi @kylesargent , I can double-check the code later today but I remember we used the first 20 scenes in the Google Scanned Objects split in RTMV for evaluation. We...

Hi @kylesargent , could you please share the evaluation code with me? I can take a look and see what might be the problem that's causing the discrepancy. Assuming you...