# PyTorch Image Models, etc
## What's New
### April 5, 2020
* Add some newly trained MobileNet-V2 models trained with latest h-params, rand augment. They compare quite favourably to EfficientNet-Lite
* 3.5M param MobileNet-V2 100 @ 73%
* 4.5M param MobileNet-V2 110d @ 75%
* 6.1M param MobileNet-V2 140 @ 76.5%
* 5.8M param MobileNet-V2 120d @ 77.3%
### March 18, 2020
* Add EfficientNet-Lite models w/ weights ported from [Tensorflow TPU](https://github.com/tensorflow/tpu/tree/master/models/official/efficientnet/lite)
* Add RandAugment trained ResNeXt-50 32x4d weights with 79.8 top-1. Trained by [Andrew Lavin](https://github.com/andravin) (see Training section for hparams)
### Feb 29, 2020
* New MobileNet-V3 Large weights trained from stratch with this code to 75.77% top-1
* IMPORTANT CHANGE - default weight init changed for all MobilenetV3 / EfficientNet / related models
* overall results similar to a bit better training from scratch on a few smaller models tried
* performance early in training seems consistently improved but less difference by end
* set `fix_group_fanout=False` in `_init_weight_goog` fn if you need to reproducte past behaviour
* Experimental LR noise feature added applies a random perturbation to LR each epoch in specified range of training
### Feb 18, 2020
* Big refactor of model layers and addition of several attention mechanisms. Several additions motivated by 'Compounding the Performance Improvements...' (https://arxiv.org/abs/2001.06268):
* Move layer/module impl into `layers` subfolder/module of `models` and organize in a more granular fashion
* ResNet downsample paths now properly support dilation (output stride != 32) for avg_pool ('D' variant) and 3x3 (SENets) networks
* Add Selective Kernel Nets on top of ResNet base, pretrained weights
* skresnet18 - 73% top-1
* skresnet34 - 76.9% top-1
* skresnext50_32x4d (equiv to SKNet50) - 80.2% top-1
* ECA and CECA (circular padding) attention layer contributed by [Chris Ha](https://github.com/VRandme)
* CBAM attention experiment (not the best results so far, may remove)
* Attention factory to allow dynamically selecting one of SE, ECA, CBAM in the `.se` position for all ResNets
* Add DropBlock and DropPath (formerly DropConnect for EfficientNet/MobileNetv3) support to all ResNet variants
* Full dataset results updated that incl NoisyStudent weights and 2 of the 3 SK weights
### Feb 12, 2020
* Add EfficientNet-L2 and B0-B7 NoisyStudent weights ported from [Tensorflow TPU](https://github.com/tensorflow/tpu/tree/master/models/official/efficientnet)
### Feb 6, 2020
* Add RandAugment trained EfficientNet-ES (EdgeTPU-Small) weights with 78.1 top-1. Trained by [Andrew Lavin](https://github.com/andravin) (see Training section for hparams)
### Feb 1/2, 2020
* Port new EfficientNet-B8 (RandAugment) weights, these are different than the B8 AdvProp, different input normalization.
* Update results csv files on all models for ImageNet validation and three other test sets
* Push PyPi package update
### Jan 31, 2020
* Update ResNet50 weights with a new 79.038 result from further JSD / AugMix experiments. Full command line for reproduction in training section below.
### Jan 11/12, 2020
* Master may be a bit unstable wrt to training, these changes have been tested but not all combos
* Implementations of AugMix added to existing RA and AA. Including numerous supporting pieces like JSD loss (Jensen-Shannon divergence + CE), and AugMixDataset
* SplitBatchNorm adaptation layer added for implementing Auxiliary BN as per AdvProp paper
* ResNet-50 AugMix trained model w/ 79% top-1 added
* `seresnext26tn_32x4d` - 77.99 top-1, 93.75 top-5 added to tiered experiment, higher img/s than 't' and 'd'
### Jan 3, 2020
* Add RandAugment trained EfficientNet-B0 weight with 77.7 top-1. Trained by [Michael Klachko](https://github.com/michaelklachko) with this code and recent hparams (see Training section)
* Add `avg_checkpoints.py` script for post training weight averaging and update all scripts with header docstrings and shebangs.
### Dec 30, 2019
* Merge [Dushyant Mehta's](https://github.com/mehtadushy) PR for SelecSLS (Selective Short and Long Range Skip Connections) networks. Good GPU memory consumption and throughput. Original: https://github.com/mehtadushy/SelecSLS-Pytorch
### Dec 28, 2019
* Add new model weights and training hparams (see Training Hparams section)
* `efficientnet_b3` - 81.5 top-1, 95.7 top-5 at default res/crop, 81.9, 95.8 at 320x320 1.0 crop-pct
* trained with RandAugment, ended up with an interesting but less than perfect result (see training section)
* `seresnext26d_32x4d`- 77.6 top-1, 93.6 top-5
* deep stem (32, 32, 64), avgpool downsample
* stem/dowsample from bag-of-tricks paper
* `seresnext26t_32x4d`- 78.0 top-1, 93.7 top-5
* deep tiered stem (24, 48, 64), avgpool downsample (a modified 'D' variant)
* stem sizing mods from Jeremy Howard and fastai devs discussing ResNet architecture experiments
### Dec 23, 2019
* Add RandAugment trained MixNet-XL weights with 80.48 top-1.
* `--dist-bn` argument added to train.py, will distribute BN stats between nodes after each train epoch, before eval
### Dec 4, 2019
* Added weights from the first training from scratch of an EfficientNet (B2) with my new RandAugment implementation. Much better than my previous B2 and very close to the official AdvProp ones (80.4 top-1, 95.08 top-5).
### Nov 29, 2019
* Brought EfficientNet and MobileNetV3 up to date with my https://github.com/rwightman/gen-efficientnet-pytorch code. Torchscript and ONNX export compat excluded.
* AdvProp weights added
* Official TF MobileNetv3 weights added
* EfficientNet and MobileNetV3 hook based 'feature extraction' classes added. Will serve as basis for using models as backbones in obj detection/segmentation tasks. Lots more to be done here...
* HRNet classification models and weights added from https://github.com/HRNet/HRNet-Image-Classification
* Consistency in global pooling, `reset_classifer`, and `forward_features` across models
* `forward_features` always returns unpooled feature maps now
* Reasonable chance I broke something... let me know
### Nov 22, 2019
* Add ImageNet training RandAugment implementation alongside AutoAugment. PyTorch Transform compatible format, using PIL. Currently training two EfficientNet models from scratch with promising results... will update.
* `drop-connect` cmd line arg finally added to `train.py`, no need to hack model fns. Works for efficientnet/mobilenetv3 based models, ignored otherwise.
## Introduction
For each competition, personal, or freelance project involving images + Convolution Neural Networks, I build on top of an evolving collection of code and models. This repo contains a (somewhat) cleaned up and paired down iteration of that code. Hopefully it'll be of use to others.
The work of many others is present here. I've tried to make sure all source material is acknowledged:
* Training/validation scripts evolved from early versions of the [PyTorch Imagenet Examples](https://github.com/pytorch/examples)
* CUDA specific performance enhancements have been pulled from [NVIDIA's APEX Examples](https://github.com/NVIDIA/apex/tree/master/examples)
* LR scheduler ideas from [AllenNLP](https://github.com/allenai/allennlp/tree/master/allennlp/training/learning_rate_schedulers), [FAIRseq](https://github.com/pytorch/fairseq/tree/master/fairseq/optim/lr_scheduler), and SGDR: Stochastic Gradient Descent with Warm Restarts (https://arxiv.org/abs/1608.03983)
* Random Erasing from [Zhun Zhong](https://github.com/zhunzhong07/Random-Erasing/blob/master/transforms.py) (https://arxiv.org/abs/1708.04896)
* Optimizers:
* RAdam by [Liyuan Liu](https://github.com/LiyuanLucasLiu/RAdam) (https://arxiv.org/abs/1908.03265)
* NovoGrad by [Masashi Kimura](https://github.com/convergence-lab/novograd) (https://arxiv.org/abs/1905.11286)
* Lookahead adapted from impl
没有合适的资源?快使用搜索试试~ 我知道了~
资源推荐
资源详情
资源评论
收起资源包目录
PyTorch_image_models,_scripts,_pretrained_weights_ (105个子文件)
results-sketch.csv 13KB
results-imagenet-a.csv 12KB
results-imagenet.csv 12KB
results-imagenetv2-matched-frequency.csv 11KB
.gitattributes 31B
.gitignore 1KB
GeneralizationToImageNetV2.ipynb 17.14MB
EffResNetComparison.ipynb 379KB
LICENSE 11KB
README.md 36KB
README.md 2KB
efficientnet.py 69KB
resnet.py 44KB
train.py 30KB
auto_augment.py 29KB
nasnet.py 29KB
sotabench.py 27KB
hrnet.py 27KB
senet.py 19KB
dla.py 18KB
mobilenetv3.py 18KB
pnasnet.py 17KB
gluon_xception.py 17KB
efficientnet_builder.py 17KB
gluon_resnet.py 16KB
efficientnet_blocks.py 15KB
utils.py 12KB
inception_resnet_v2.py 12KB
dpn.py 12KB
tresnet.py 11KB
validate.py 11KB
inception_v4.py 10KB
selecsls.py 10KB
sknet.py 9KB
densenet.py 9KB
res2net.py 9KB
tf_preprocessing.py 9KB
xception.py 8KB
dataset.py 7KB
loader.py 7KB
transforms_factory.py 6KB
radam.py 6KB
rmsprop_tf.py 5KB
transforms.py 5KB
selective_kernel.py 5KB
eca.py 5KB
cond_conv2d.py 5KB
inception_v3.py 5KB
inference.py 5KB
adamw.py 5KB
nvnovograd.py 5KB
scheduler.py 5KB
avg_checkpoints.py 4KB
activations.py 4KB
drop.py 4KB
helpers.py 4KB
random_erasing.py 4KB
optim_factory.py 4KB
convert_from_mxnet.py 4KB
tanh_lr.py 4KB
cosine_lr.py 4KB
lookahead.py 4KB
nadam.py 4KB
config.py 3KB
split_batchnorm.py 3KB
cbam.py 3KB
registry.py 3KB
clean_checkpoint.py 3KB
adaptive_avgmax_pool.py 3KB
pool2d_same.py 3KB
novograd.py 3KB
scheduler_factory.py 3KB
factory.py 2KB
padding.py 2KB
anti_aliasing.py 2KB
distributed_sampler.py 2KB
mixup.py 2KB
plateau_lr.py 2KB
test_time_pool.py 2KB
mixed_conv2d.py 2KB
space_to_depth.py 2KB
step_lr.py 2KB
median_pool.py 2KB
setup.py 2KB
jsd.py 2KB
conv2d_same.py 1KB
create_conv2d.py 1KB
feature_hooks.py 1KB
conv_bn_act.py 1KB
create_attn.py 1KB
cross_entropy.py 1KB
__init__.py 932B
se.py 716B
__init__.py 706B
__init__.py 422B
helpers.py 420B
constants.py 303B
__init__.py 252B
__init__.py 206B
__init__.py 121B
共 105 条
- 1
- 2
资源评论
好家伙VCC
- 粉丝: 1452
- 资源: 5926
上传资源 快速赚钱
- 我的内容管理 展开
- 我的资源 快来上传第一个资源
- 我的收益 登录查看自己的收益
- 我的积分 登录查看自己的积分
- 我的C币 登录后查看C币余额
- 我的收藏
- 我的下载
- 下载帮助
最新资源
资源上传下载、课程学习等过程中有任何疑问或建议,欢迎提出宝贵意见哦~我们会及时处理!
点击此处反馈
安全验证
文档复制为VIP权益,开通VIP直接复制
信息提交成功