search

facebookresearch / sound-spaces

A first-of-its-kind acoustic simulation platform for audio-visual embodied AI research. It supports training and evaluating multiple tasks and applications.
https://soundspaces.org
Creative Commons Attribution 4.0 International
345 stars 55 forks source link

Question about the demo/gif video. #120

Open zszheng147 opened 1 year ago

zszheng147 commented 1 year ago

Hi Changan,

I have a question about the SoundSpace demo video. How can such a video clip be generated? Is it possible to do so using the code or something?

Because when i successfully ran the example command Generate demo video with audio, which is python ss_baselines/av_nav/run.py --run-type eval --exp-config ss_baselines/av_nav/config/audionav/replica/test_telephone/audiogoal_depth.yaml --model-dir data/models/replica/audiogoal_depth EVAL_CKPT_PATH_DIR data/models/replica/audiogoal_depth/data/ckpt.220.pth VIDEO_OPTION [\"disk\"] TASK_CONFIG.SIMULATOR.USE_RENDERED_OBSERVATIONS False TASK_CONFIG.TASK.SENSORS [\"POINTGOAL_WITH_GPS_COMPASS_SENSOR\",\"SPECTROGRAM_SENSOR\",\"AUDIOGOAL_SENSOR\"] SENSORS [\"RGB_SENSOR\",\"DEPTH_SENSOR\"] EXTRA_RGB True TASK_CONFIG.SIMULATOR.CONTINUOUS_VIEW_CHANGE True DISPLAY_RESOLUTION 512 TEST_EPISODE_COUNT 1 , the generated video was pretty long.

Thank you.

ChanganVR commented 1 year ago

@zszheng147 which demo video are you talking about? Are you talking about generating this video: https://www.youtube.com/watch?v=4uiptTUyq30&feature=youtu.be? This was made with a video editor rather than generated with code.