Ross Wightman
|
0f2803de7a
|
Move ImageNet metadata (aka info) files to timm/data/_info. Add helper classes to make info available for labelling. Update inference.py for first use.
|
2 years ago |
Ross Wightman
|
89b0452171
|
Add PyTorch 1.13 inference benchmark numbers
|
2 years ago |
Fredo Guan
|
81ca323751
|
Davit update formatting and fix grad checkpointing (#7)
fixed head to gap->norm->fc as per convnext, along with option for norm->gap->fc
failed tests due to clip convnext models, davit tests passed
|
2 years ago |
Ross Wightman
|
8fca002c06
|
Add ImageNet22k and 12k subset sysnet/index maps
|
2 years ago |
Ross Wightman
|
c865028c34
|
Update benchmark with latest model adds
|
2 years ago |
Ross Wightman
|
30bd1746c5
|
Improve csv table result processing for better sort when updating
|
2 years ago |
Ross Wightman
|
e987e29036
|
Add convnext_nano and few cs3 models to existing results tables
|
2 years ago |
Ross Wightman
|
d7b55a9429
|
Add gmacs and macts columns to inference benchmark (missed profile in initial run)
|
2 years ago |
Ross Wightman
|
5e7d47ca10
|
Add pytorch 1.12 benchmark csv files w/ 0.6.6 code. Remove pytorch 1.10 results. Deciding whether to update 1.11 results or remove...
|
2 years ago |
Ross Wightman
|
326ade2999
|
Add updated validation / test set results, benchmarks still running...
|
2 years ago |
Ross Wightman
|
eac2df3d2c
|
Update PyTorch 1.10 benchmark numbers for latest code
|
3 years ago |
Ross Wightman
|
02b806e00a
|
Add PyTorch 1.11 train benchmark numbers
|
3 years ago |
Ross Wightman
|
c9f208f7f8
|
Update eval results and add latest PyTorch 1.11 inference benchmarks
|
3 years ago |
Ross Wightman
|
1331c145a3
|
Add train benchmark results, adjust name scheme for inference and train benchmark files.
|
3 years ago |
Ross Wightman
|
499c4749d7
|
Add update NCHW and NHWC inference benchmark numbers for current models. Flip name of 'sam' vit models in results files
|
3 years ago |
Ross Wightman
|
2d4b7e7080
|
Update results csvs for latest release
|
3 years ago |
Ross Wightman
|
135a48d024
|
Fix sam result again for imagenetv2
|
3 years ago |
Ross Wightman
|
aaff2d82d0
|
Add new 50ts attn models to benchmark/meta csv files
|
3 years ago |
Ross Wightman
|
1e17863b7b
|
Fixed botne*t26 model results, add some 50ts self-attn variants
|
3 years ago |
Ross Wightman
|
13178ba73a
|
Add benchmark and metadata csv files
|
3 years ago |
Ross Wightman
|
51f488b7f5
|
Update results.csv files with latest weights
|
3 years ago |
Ross Wightman
|
d10b071a28
|
Update results csvs w/ latest ViT, ResMLP, and NfNet-L2 weights present
|
4 years ago |
Ross Wightman
|
07fb05cc3d
|
Update results csv files
|
4 years ago |
Ross Wightman
|
c16d65a8a7
|
Update results.csv files with cait, mlp-mixer, resnetrs, miil imagenet21k pretrained, and my latest efficientnet v2s/b4 weights.
|
4 years ago |
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).
|
4 years ago |
Ross Wightman
|
95feb1da41
|
Update results csvs, run with PyTorch 1.7.1 cuda 10.2, some differences from prev run with older PT ver.
|
4 years ago |
Ross Wightman
|
59ec7e6a53
|
Merge branch 'master' into imagenet21k_datasets_more
|
4 years ago |
Ross Wightman
|
a7d0a8b5b2
|
Update results csv files with latest models, incl 101D, 152D, 200D, SE152D ResNets and yet to be merged BiT and ViT-R50 models.
|
4 years ago |
Ross Wightman
|
e553480b67
|
Add 21843 synset txt for google 21k models like BiT/ViT
|
4 years ago |
Ross Wightman
|
da1b90e5c9
|
Update results csvs with latest run
|
4 years ago |
Ross Wightman
|
b496b7bde9
|
Re-ran batch validation on all models across all sets
|
4 years ago |
Ross Wightman
|
ad150e7018
|
Update results csv file rank/diff script and small validate script tweak for batch validation
|
4 years ago |
Ross Wightman
|
c53ec33ae0
|
Add synset/label indices for results generation. Add 'valid labels' to validation script to support imagenet-a/r label subsets properly.
|
4 years ago |
Ross Wightman
|
4805dd1e79
|
Fix incorrect dataset name, add new datasets to results delta script
|
4 years ago |
Ross Wightman
|
6be878c22a
|
Update results README to include robustness and real labels tests. Include labels files used in results gen.
|
4 years ago |
KushajveerSingh
|
5699e8429f
|
set precision=2 in param_count
|
5 years ago |
KushajveerSingh
|
6526ccb4a7
|
set precision=3 in results
|
5 years ago |
KushajveerSingh
|
856f6181f7
|
add {rank,top1,top5}_diff in results
|
5 years ago |
Ross Wightman
|
b41b8d0108
|
Update results csv files
|
5 years ago |
Ross Wightman
|
31f4c126ec
|
Add EfficientNet pruned models to results files
|
5 years ago |
Ross Wightman
|
779cb0fcc0
|
Update results with new models
|
5 years ago |
Ross Wightman
|
91e2b33d72
|
Update results with latest NoisyStudent models and SelectiveKernel models
|
5 years ago |
Ross Wightman
|
5c85389e26
|
Update README.md
|
5 years ago |
Ross Wightman
|
820b73d280
|
Update README.md
|
5 years ago |
Ross Wightman
|
82c0a2ff12
|
Update README.md
Fix relative paths (I think)
|
5 years ago |
Ross Wightman
|
1ffd2d0694
|
Add results/README.md
|
5 years ago |
Ross Wightman
|
7c88356682
|
Add update results on ImageNet validation, ImageNetV2, ImageNet-A, and ImageNet-Sketch for all models
|
5 years ago |
Ross Wightman
|
82dd60b33c
|
Rename results files for more clarity
|
5 years ago |
Ross Wightman
|
00b93407c7
|
Update results-all.csv with latest models/weights
|
5 years ago |
Ross Wightman
|
3bef524f9c
|
Finish with HRNet, weights and models updated. Improve consistency in model classifier/global pool treatment.
|
5 years ago |