Skip to content

Conversation

rwightman
Copy link
Collaborator

  • Bring EfficienetNet and MobilenetV3 up to date with CondConv, AdvProp, official TF MobileNetV3 weights and definitions
  • Add 'Feature' modules for EfficientNet and MobilenetV3 hook based feature extraction. The first part of making models in this repo usable for segmentation / obj detection backbones.
  • Add beginning of HRNet model from MS impl
  • Remove redundant GluonResNet code (use compatible ResNet base and blocks instead)

…t repo

* Split MobileNetV3 and EfficientNet model files and put builder and blocks in own files (getting too large)
* Finalize CondConv EfficientNet variant
* Add the AdvProp weights files and B8 EfficientNet model
* Refine the feature extraction module for EfficientNet and MobileNetV3
* remove redundant GluonResNet model/blocks and use the code in ResNet for Gluon weights
* change SEModules back to using AdaptiveAvgPool instead of mean, PyTorch issue long fixed
…ory arg checks, bump PyTorch version req to 1.2
@rwightman rwightman merged commit 3ceeedc into master Nov 29, 2019
@rwightman rwightman deleted the condconvs_and_features branch February 21, 2020 19:53
guoriyue pushed a commit to guoriyue/pytorch-image-models that referenced this pull request May 24, 2024
Major model merge (EfficientNet-CondConv, EfficientNet-AdvProp, TF MobileNetV3, HRNet, more)
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

Successfully merging this pull request may close these issues.

1 participant