Commit Graph

64 Commits (5c33776aa59f0f05bfb8008ff546ed4c09083f1a)

Author SHA1 Message Date
Ross Wightman 5c33776aa5 Add a bunch more benchmark sets 2024-09-04 15:35:26 -07:00
Ross Wightman b3f3a005a0 Add RTX4090 inference benchmark numbers for latest models 2024-08-26 17:15:05 -07:00
Ross Wightman bef0c124cc Add re-run of imagenet val/ood test set results. Fixed wrong crop for models w/ diff test sizes. Add latest sbb2 and ra4 weights. 2024-08-22 11:56:05 -07:00
Ross Wightman 4515a435e4 Update imagenet & OOD test set eval results with current weights. Now have both test & train resolution results in tables. 2024-08-13 10:25:25 -07:00
Ross Wightman 111fad1a9f Add first CPU inference benchmark, using torch.compile 2024-03-20 08:43:29 -07:00
Ross Wightman 79548b542f Update PT 2.1 inference benchmarks w/ full profile info 2023-11-25 10:52:03 -08:00
Ross Wightman 4d0737d5fa Add PT 2.1 NCHW 3090 benchmark results 2023-11-21 16:49:20 -08:00
Ross Wightman 057fdb570b Update model eval result csv files 2023-11-20 10:06:40 -08:00
Ross Wightman 049b133253 Add 0.9 imagenet and ood test set results files 2023-05-24 09:02:25 -07:00
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. 2023-02-06 17:45:03 -08:00
Ross Wightman 89b0452171 Add PyTorch 1.13 inference benchmark numbers 2023-02-06 09:09:04 -08:00
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
2023-01-15 14:34:56 -08:00
Ross Wightman 8fca002c06 Add ImageNet22k and 12k subset sysnet/index maps 2022-12-05 10:21:34 -08:00
Ross Wightman c865028c34 Update benchmark with latest model adds 2022-07-27 12:40:22 -07:00
Ross Wightman 30bd1746c5 Improve csv table result processing for better sort when updating 2022-07-27 12:26:52 -07:00
Ross Wightman e987e29036 Add convnext_nano and few cs3 models to existing results tables 2022-07-27 12:26:34 -07:00
Ross Wightman d7b55a9429 Add gmacs and macts columns to inference benchmark (missed profile in initial run) 2022-07-22 12:12:37 -07:00
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... 2022-07-19 15:46:03 -07:00
Ross Wightman 326ade2999 Add updated validation / test set results, benchmarks still running... 2022-07-16 16:15:28 -07:00
Ross Wightman eac2df3d2c Update PyTorch 1.10 benchmark numbers for latest code 2022-04-04 09:03:27 -07:00
Ross Wightman 02b806e00a Add PyTorch 1.11 train benchmark numbers 2022-04-01 16:34:23 -07:00
Ross Wightman c9f208f7f8 Update eval results and add latest PyTorch 1.11 inference benchmarks 2022-03-29 16:37:41 -07:00
Ross Wightman 1331c145a3 Add train benchmark results, adjust name scheme for inference and train benchmark files. 2022-01-23 14:08:30 -08:00
Ross Wightman 499c4749d7 Add update NCHW and NHWC inference benchmark numbers for current models. Flip name of 'sam' vit models in results files 2022-01-20 10:40:04 -08:00
Ross Wightman 2d4b7e7080 Update results csvs for latest release 2022-01-18 22:56:45 -08:00
Ross Wightman 135a48d024 Fix sam result again for imagenetv2 2021-10-28 14:46:45 -07:00
Ross Wightman aaff2d82d0 Add new 50ts attn models to benchmark/meta csv files 2021-10-28 14:32:47 -07:00
Ross Wightman 1e17863b7b Fixed botne*t26 model results, add some 50ts self-attn variants 2021-10-28 13:55:24 -07:00
Ross Wightman 13178ba73a Add benchmark and metadata csv files 2021-10-26 10:50:46 -07:00
Ross Wightman 51f488b7f5 Update results.csv files with latest weights 2021-10-24 14:48:33 -07:00
Ross Wightman d10b071a28 Update results csvs w/ latest ViT, ResMLP, and NfNet-L2 weights present 2021-06-30 09:11:31 -07:00
Ross Wightman 07fb05cc3d Update results csv files 2021-06-09 22:33:29 -07:00
Ross Wightman c16d65a8a7 Update results.csv files with cait, mlp-mixer, resnetrs, miil imagenet21k pretrained, and my latest efficientnet v2s/b4 weights. 2021-05-11 10:50:46 -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 95feb1da41 Update results csvs, run with PyTorch 1.7.1 cuda 10.2, some differences from prev run with older PT ver. 2021-02-28 17:43:22 -08:00
Ross Wightman 59ec7e6a53 Merge branch 'master' into imagenet21k_datasets_more 2021-01-04 12:11:05 -08:00
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. 2021-01-03 12:42:43 -08:00
Ross Wightman e553480b67 Add 21843 synset txt for google 21k models like BiT/ViT 2020-12-28 16:59:15 -08:00
Ross Wightman da1b90e5c9 Update results csvs with latest run 2020-10-29 07:55:13 -07:00
Ross Wightman b496b7bde9 Re-ran batch validation on all models across all sets 2020-07-31 18:15:55 -07:00
Ross Wightman ad150e7018 Update results csv file rank/diff script and small validate script tweak for batch validation 2020-07-31 17:51:22 -07:00
Ross Wightman c53ec33ae0 Add synset/label indices for results generation. Add 'valid labels' to validation script to support imagenet-a/r label subsets properly. 2020-07-29 00:58:57 -07:00
Ross Wightman 4805dd1e79 Fix incorrect dataset name, add new datasets to results delta script 2020-07-27 19:06:02 -07:00
Ross Wightman 6be878c22a Update results README to include robustness and real labels tests. Include labels files used in results gen. 2020-07-27 14:08:44 -07:00
KushajveerSingh 5699e8429f set precision=2 in param_count 2020-07-09 16:43:11 +05:30
KushajveerSingh 6526ccb4a7 set precision=3 in results 2020-07-09 16:38:49 +05:30
KushajveerSingh 856f6181f7 add {rank,top1,top5}_diff in results 2020-07-09 03:48:26 +05:30
Ross Wightman b41b8d0108 Update results csv files 2020-06-09 14:36:24 -07:00
Ross Wightman 31f4c126ec Add EfficientNet pruned models to results files 2020-05-03 20:15:11 -07:00
Ross Wightman 779cb0fcc0 Update results with new models 2020-05-01 17:29:29 -07:00