mirrors
/
pytorch-image-models
mirror of https://github.com/huggingface/pytorch-image-models.git
1
0
Fork 0
Code Issues Projects Releases Wiki Activity
946 Commits
136 Branches
65 Tags
47 MiB
Commit Graph

946 Commits (17dc47c8e64e1452a0f2be7883a55b2f618229eb)
 

Author SHA1 Message Date
Ross Wightman a0492e3b48 A few miil weights naming tweaks to improve compat with model registry and filtering wildcards. 2021-04-28 10:33:02 -07:00
talrid 8c1f03e56c comment 2021-04-28 09:04:10 +03:00
talrid 19e1b67a84 old spaces 2021-04-28 09:01:29 +03:00
talrid a443865876 update naming and scores 2021-04-28 08:57:06 +03:00
talrid cf0e371594 84_0 2021-04-27 22:33:55 +03:00
talrid 0968bdeca3 vit, tresnet and mobilenetV3 ImageNet-21K-P weights 2021-04-27 20:54:06 +03:00
mrT23 b81cd75eea
Merge pull request #3 from rwightman/master 
merge base
 2021-04-27 18:49:25 +03:00
morizin 1e3b6d4dfc
Update __init__.py 2021-04-24 18:22:59 +05:30
morizin fd022fd6a2
Update __init__.py 2021-04-24 18:22:36 +05:30
morizin 06841427cd
Add files via upload 2021-04-24 18:11:28 +05:30
morizin c2d5087eae
Add files via upload 2021-04-24 17:47:57 +05:30
Ross Wightman 9a1bd358c7
Merge pull request #571 from normster/augmix-fix 
Enable uniform augmentation magnitude sampling and set AugMix default
 2021-04-19 16:18:36 -07:00
Norman Mu 79640fcc1f Enable uniform augmentation magnitude sampling and set AugMix default 2021-04-19 14:21:12 -07:00
Ross Wightman c1cf9712fc Add updated EfficientNet-V2S weights, 83.8 @ 384x384 test. Add PyTorch trained EfficientNet-B4 weights, 83.4 @ 384x384 test. Tweak non TF EfficientNet B1-B4 train/test res scaling. 2021-04-19 10:42:56 -07:00
Ross Wightman e8a64fb881 Test input size for efficientnet_v2s was wrong in last results run 2021-04-17 16:17:41 -07:00
Ross Wightman a04427d8ce Add _in22k to bulk validate filter 2021-04-17 12:18:03 -07:00
Ross Wightman af647c10b3 Update results csv, includes latest transformer models, swin, pit, tnt... run on pytorch 1.8.1 cuda 10.2 (11.x rel crashes). 2021-04-17 12:18:03 -07:00
Ross Wightman e15e68d881 Fix #566, summary.csv writing to pwd on local_rank != 0. Tweak benchmark mem handling to see if it reduces likelihood of 'bad' exceptions on OOM. 2021-04-15 23:03:56 -07:00
Ross Wightman 1b0c8e7b01 Merge branch 'iamhankai-master' 2021-04-15 10:22:42 -07:00
Ross Wightman 2df77ee5cb Fix torchscript compat and features_only behaviour in GhostNet PR. A few minor formatting changes. Reuse existing layers. 2021-04-15 10:20:26 -07:00
Ross Wightman d793deb51a Merge branch 'master' of https://github.com/iamhankai/pytorch-image-models into iamhankai-master 2021-04-15 09:30:25 -07:00
Ross Wightman e685618f45
Merge pull request #550 from amaarora/wandb 
Wandb Support
 2021-04-15 09:26:35 -07:00
Ross Wightman 277a9a78f9 Fix unit test filter update. 2021-04-13 22:15:20 -07:00
Ross Wightman 858728799c Update README again. Add 101x3 BiT-M model to CI ignore since it's starting to fail in GitHub runners. 2021-04-13 13:36:24 -07:00
Ross Wightman f606c45c38 Add Swin Transformer models from https://github.com/microsoft/Swin-Transformer 2021-04-13 12:17:21 -07:00
iamhankai de445e7827 Add GhostNet 2021-04-13 23:19:51 +08:00
Ross Wightman 5a196dddf6 Update README.md with latest, bump version to 0.4.8 2021-04-12 13:15:00 -07:00
Ross Wightman ce6585f533
Merge pull request #556 from rwightman/byoanet-self_attn 
ByoaNet - Self Attn Networks - Bottleneck Transformers, Lambda ResNet, HaloNet
 2021-04-12 13:04:24 -07:00
Ross Wightman b3d7580df1 Update ByoaNet comments. Fix first Steam feat chs for ByobNet. 2021-04-12 12:11:35 -07:00
Ross Wightman 16f7aa9f54 Add default_cfg options for min_input_size / fixed_input_size, queries in model registry, and use for testing self-attn models 2021-04-12 11:54:22 -07:00
Ross Wightman 4e4b863b15 Missed norm.py 2021-04-12 09:57:56 -07:00
Ross Wightman 7c97e66f7c Remove commented code, add more consistent seed fn 2021-04-12 09:51:36 -07:00
Ross Wightman 364dd6a58e Merge branch 'master' into byoanet-self_attn 2021-04-12 09:38:59 -07:00
Ross Wightman ce62f96d4d ByoaNet with bottleneck transformer, lambda resnet, and halo net experiments 2021-04-12 09:38:02 -07:00
Ross Wightman cd3dc4979f Fix adabelief imports, remove prints, preserve memory format is the default arg for zeros_like 2021-04-12 08:25:31 -07:00
Ross Wightman 21812d33aa Add prelim efficientnet_v2s weights from 224x224 train, eval 83.3 @ 288. Add eca_nfnet_l1 weights, train at 256, eval 84 @ 320. 2021-04-11 23:26:13 -07:00
Michael Monashev 0be1fa4793
Argument description fixed 2021-04-11 18:08:43 +03:00
Aman Arora 5772c55c57 Make wandb optional 2021-04-10 01:34:20 -04:00
Aman Arora f54897cc0b make wandb not required but rather optional as huggingface_hub 2021-04-10 01:27:23 -04:00
Aman Arora f13f7508a9 Keep changes to minimal and use args.experiment as wandb project name if it exists 2021-04-10 00:50:52 -04:00
Aman Arora f8bb13f640 Default project name to None 2021-04-10 00:44:05 -04:00
Aman Arora 8db8ff346f add wandb to requirements.txt 2021-04-08 03:52:14 -04:00
Aman Arora 3f028ebc0f import wandb in summary.py 2021-04-08 03:48:51 -04:00
Aman Arora a9e5d9e5ad log loss as before 2021-04-08 03:41:40 -04:00
Aman Arora 624c9b6949 log to wandb only if using using wandb 2021-04-08 03:40:22 -04:00
Aman Arora 00c8e0b8bd Make use of wandb configurable 2021-04-08 03:35:59 -04:00
Aman Arora 8e6fb861e4 Add wandb support 2021-04-08 03:22:29 -04:00
Ross Wightman 779107b693
Merge pull request #542 from juntang-zhuang/adabelief 
Add Adabelief Optimizer
 2021-04-05 16:34:54 -07:00
Juntang Zhuang 74366f733c
Delete distributed_train_adabelief.sh 2021-04-05 15:11:45 -04:00
Juntang Zhuang 1d848f409a
Delete args.yaml 2021-04-05 15:11:35 -04:00