Remove obsolete modules and rename config parameters.
This version is a small increment over v1.0 with only cosmetic changes and obsolete code removals. The final results of models rained from this codebase would remain unchanged.
Removed feature extraction support:
-
Removed
virtex.downstream.FeatureExtractorand its usage inscripts/clf_voc07.py. By default, the script will only evaluate on global average pooled features (2048-d), as with the CVPR 2021 paper version. -
Removed
virtex.modules.visual_backbones.BlindVisualBackbone. I introduced it a long time ago for debugging, it is not much useful anymore.
Two config-related changes:
-
Renamed config parameters: (
OPTIM.USE_LOOKAHEAD—>OPTIM.LOOKAHEAD.USE), (OPTIM.LOOKAHEAD_ALPHA—>OPTIM.LOOKAHEAD_ALPHA) and (OPTIM.LOOKAHEAD_STEPS—>OPTIM.LOOKAHEAD.STEPS). -
Renamed
TransformerTextualHeadtoTransformerDecoderTextualHeadfor clarity. Model names in config also change accordingly:"transformer_postnorm"—>"transdec_postnorm"(same for prenorm).
These changes may be breaking if you wrote your own config and explicitly added these arguments.