ericchen321

I added this to write the reconstructed image to out.png: ``` ref_image = read_image(args.scene) image = testbed.render(ref_image.shape[1], ref_image.shape[0], 1, True) write_image("out.png", image) ```

Hi Erik, thanks for the quick response! That makes sense.

Sorry for asking help on this again - I have fixed the environment's random seed to `0`, but still I'm having the discrepency. I suspect this being the agent's problem...

Hi Erik, again thanks for looking into this issue. I will look into the doc and see if I can find the source of non-determinism.

Hi Erik, thanks for the suggestions! **I have set `normalize_visual_inputs` to `True` and I got the following error:** ``Traceback (most recent call last): File "habitat_baselines/agents/ppo_agents.py", line 171, in main() File...

Hi Arif, installing these dependencies before running `setup.py` worked for me: ``` # install apache-beam dependencies !pip install avro-python3==1.9.2.1 !pip install dill==0.3.1.1 !pip install future==0.18.2 !pip install pyarrow==2.0.0 !pip install...

Hi Lawson, Thank you so much for the quick and detailed reply! And thanks for pointing us to that paper; I'll look into it to see if I can get...

Hey Lawson, sorry about the late reply from our side as well... Yes we got it working finally! Eventually we got everything working with Tensorflow 1.8 + CUDA 9.2. You...

Hi @SepMJ I think the error's probably due to a racing condition with command setting/reading (such that linear velocity is a ``NULL`` object when passed to the velocity control structure)....

`data/scene_datasets/mp3d/` is where you place scene definitions and `data/datasets/pointnav/mp3d/v1/` is where you place episode definitions. It would be necessary if you want to reproduce our experiments that use the MP3D...