Releases: huggingface/pytorch-image-models
Releases · huggingface/pytorch-image-models
v0.4.5. Lots of models. NFNets (& NF-ResNet, NF-RegNet), GPU-Efficient Nets, RepVGG, VGG.
Merge pull request #475 from rwightman/pre-release/0.4.5 Prep for PyPi release. Tweak NFNet, ResNetV2, RexNet feature extraction, use pre-act features. Also, add act args to RexNet #202
DeepMind NFNet-F* weights
Weights converted from DeepMind Haiku impl of NFNets (https://github.com/deepmind/deepmind-research/tree/master/nfnets)
RepVGG checkpoints remapped from official repo
Checkpoints remapped from official repository at https://github.com/DingXiaoH/RepVGG
GPU-Efficient (Residual) Networks checkpoints
Checkpoints remapped from official repo at https://github.com/idstcv/GPU-Efficient-Networks
v0.3.4. Minor release. Conda setup.cfg added
Version 0.3.4. Tweak setup.cfg and update setup.py metadata
v0.3.3. ResNet-101D/152D/200D and SE-ResNet-152D models w/ weights.
Update README.md
Ported weights from official JAX impl of Vision Transformers and MLP-Mixer
Feature Maps, More Models, CutMix
Aug 12, 2020
- New/updated weights from training experiments
- EfficientNet-B3 - 82.1 top-1 (vs 81.6 for official with AA and 81.9 for AdvProp)
- RegNetY-3.2GF - 82.0 top-1 (78.9 from official ver)
- CSPResNet50 - 79.6 top-1 (76.6 from official ver)
- Add CutMix integrated w/ Mixup. See pull request for some usage examples
- Some fixes for using pretrained weights with
in_chans
!= 3 on several models.
Aug 5, 2020
Universal feature extraction, new models, new weights, new test sets.
- All models support the
features_only=True
argument forcreate_model
call to return a network that extracts feature maps from the deepest layer at each stride. - New models
- CSPResNet, CSPResNeXt, CSPDarkNet, DarkNet
- ReXNet
- (Modified Aligned) Xception41/65/71 (a proper port of TF models)
- New trained weights
- SEResNet50 - 80.3 top-1
- CSPDarkNet53 - 80.1 top-1
- CSPResNeXt50 - 80.0 top-1
- DPN68b - 79.2 top-1
- EfficientNet-Lite0 (non-TF ver) - 75.5 (submitted by @hal-314)
- Add 'real' labels for ImageNet and ImageNet-Renditions test set, see
results/README.md
- Test set ranking/top-n diff script by @KushajveerSingh
- Train script and loader/transform tweaks to punch through more aug arguments
- README and documentation overhaul. See initial (WIP) documentation at https://rwightman.github.io/pytorch-image-models/
- adamp and sgdp optimizers added by @hellbell
RexNet remapped weights
ReXNet weights from https://github.com/clovaai/rexnet#pretrained remapped for timm
model changes
Mirror of ResNeSt weights
These are a mirror of weights from the official repository (https://github.com/zhanghang1989/ResNeSt ) to avoid issues with hosting changes/relocation