Obs register fix - #199
Merged
Merged
Obs register fix#199
Conversation
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
#190 introduced a bug into how we create observation backbones in
obs_core.pyby mistakenly referencingOBS_ENCODER_CORESdefined inobs_utils.py.However, we do need a new registry for users to define their own obs encoder backbones such asResNet18Conv. So here is a fix that does that.Changes to
utils/obs_utils.pyandmodels/obs_cores.pyregister_encoder_backbonefunction inrobomimic/utils/obs_utils.pyto register observation encoder backbones.OBS_ENCODER_BACKBONESdictionary inrobomimic/utils/obs_utils.pyto store mappings of observation encoder network names to classes.backbone_kwargsextraction inrobomimic/models/obs_core.pyto useOBS_ENCODER_BACKBONESinstead ofOBS_ENCODER_CORES.Class Initialization Updates:
__init_subclass__method toConvBaseclass inrobomimic/models/base_nets.pyto automatically register subclasses as valid observation encoders.