Ross Wightman
95907e69c2
Further reduce atol for model comparison, move python 3.11 + torch 2.2 -> python 3.12 + torch 2.4.1
2024-10-02 10:05:27 -07:00
Ross Wightman
fde6719403
relax tolerance on inference test
2024-10-02 09:53:17 -07:00
Ross Wightman
0e27f302a0
Do full inference test against test vectors for test_* models
2024-10-02 09:39:26 -07:00
Ross Wightman
44f1a343e7
Merge pull request #2281 from huggingface/convnext_zepto
...
convnext zepto, rmsnorm experiments
2024-09-30 15:37:31 -07:00
Ross Wightman
545bd4056c
Tag along test_vit3 weights
2024-09-30 12:03:32 -07:00
Ross Wightman
69b687d4cc
Add zepto weights
2024-09-30 11:43:23 -07:00
Ross Wightman
c6e5557a5a
Mismatch pretrained_cfg
2024-09-30 11:43:23 -07:00
Ross Wightman
5d7bd2973e
convnext zepto, rmsnorm experiments
2024-09-30 11:43:23 -07:00
Ross Wightman
e3242a5258
Merge pull request #2277 from huggingface/more_tiny_test_models
...
Adding some more tiny test models to train...
2024-09-22 10:28:29 -07:00
Ross Wightman
305a360f08
Merge branch 'baorepo-patch-1'
2024-09-22 10:27:35 -07:00
Ross Wightman
c1cb5641c7
Add weight fore mobilenetv4 small 0.5, change 0.25 -> 0.35
2024-09-22 10:27:01 -07:00
Ross Wightman
a22ce0a329
Merge branch 'patch-1' of https://github.com/baorepo/pytorch-image-models into baorepo-patch-1
2024-09-22 10:14:35 -07:00
Ross Wightman
9067be6a30
Add weights for new tiny test models
2024-09-22 07:59:23 -07:00
Ross Wightman
93374637c6
Merge pull request #2285 from huggingface/fix_swin_pad
...
Fix reversed H & W padding for swin patch merging
2024-09-21 17:00:49 -07:00
Ross Wightman
65564f7da5
Fix reversed H & W padding for swin patch merging
2024-09-21 16:51:02 -07:00
Ross Wightman
a2f539f055
Add a few more test model defs in prep for weight upload
2024-09-21 11:38:38 -07:00
Ross Wightman
6ab2af610d
Adding some more tiny test models to train
2024-09-06 15:35:57 -07:00
Ross Wightman
ee5b1e8217
Add missing nhwc bm for 4090
2024-09-05 07:30:24 -07:00
alias pillar1989
d6b8816eda
MobilenetV4: add two more lightweight models
...
Mobilenetv4 is very fast and ideal for embedded devices. However, for many low-cost, low-power embedded MCU devices, smaller models are required. Hopefully this PR will merge.
2024-09-05 02:34:11 +00:00
Ross Wightman
ef570e266d
Remove some of the older benchmark files
2024-09-04 15:38:31 -07:00
Ross Wightman
5c33776aa5
Add a bunch more benchmark sets
2024-09-04 15:35:26 -07:00
Ross Wightman
f81cbdcca9
Merge pull request #2274 from huggingface/bulk_runner_tweaks
...
Better all res resolution for bulk runner
2024-09-03 12:11:56 -07:00
Ross Wightman
6c42299b3e
Back to dev version
2024-09-03 10:29:05 -07:00
Ross Wightman
a50713ce6e
Fix #2272
2024-09-02 13:20:05 -07:00
Ross Wightman
ebbe530ee4
Add MobileNetV3 RA4 (mnv4 recipe) weights
2024-09-02 13:10:34 -07:00
Ross Wightman
fa4a1e597f
Better all res resolution for bulk runner
2024-08-26 22:28:01 -07:00
Ross Wightman
b3f3a005a0
Add RTX4090 inference benchmark numbers for latest models
2024-08-26 17:15:05 -07:00
Ross Wightman
072783331f
Version 1.0.9
2024-08-23 11:47:42 -07:00
Ross Wightman
76b0e9931a
Placeholder for new mnv3 model
2024-08-23 10:11:20 -07:00
Ross Wightman
ed7aaf8d6d
Merge pull request #2264 from huggingface/group_size_eff
...
Allow group_size override for more efficientnet and mobilenetv3 based…
2024-08-22 15:24:02 -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
39e92f0c0d
mobilenet_edgetpu can use group_size override, more consistency in arg wrap/sadface w/ extra group_size arg
2024-08-22 11:44:02 -07:00
Ross Wightman
b9f020a509
Allow group_size override for more efficientnet and mobilenetv3 based models
2024-08-21 16:51:38 -07:00
Ross Wightman
26ed96b052
Create UPGRADING.md
2024-08-21 15:58:54 -07:00
Ross Wightman
29d69e8734
Update README.md
2024-08-21 15:53:04 -07:00
Ross Wightman
9f228b7fc4
Update README.md
2024-08-21 15:41:54 -07:00
Ross Wightman
00c5be7656
Merge pull request #2258 from huggingface/sbb2_vit_hiera_weights
...
Update Hiera model for abswin & add more in12k weights for hiera & vit
2024-08-21 12:50:15 -07:00
Ross Wightman
17923a66bb
Add layer scale to hieradet
2024-08-21 11:23:39 -07:00
Ross Wightman
47e6958263
Add hierdet_small (non sam) model def
2024-08-21 11:05:54 -07:00
Ross Wightman
076efef73b
Merge pull request #2263 from andravin/fix-docs-install-dir
...
Fix install directory in hfdocs.
2024-08-21 10:24:16 -07:00
Ross Wightman
9fcbf39cdc
Add remaining sbb vit betwixt/mediumd fine-tunes
2024-08-21 10:09:38 -07:00
Ross Wightman
dc94cca0e5
Remaining Hiera sbb weights uploaded
2024-08-21 10:06:27 -07:00
Andrew Lavin
3970558e0d
Fix install directory in hfdocs.
...
Change from "timm" to "pytorch-image-models"
2024-08-21 09:27:52 -07:00
Ross Wightman
a256e50457
Move padding back in front of windowing
2024-08-17 11:22:53 -07:00
Ross Wightman
7d83749207
pool size test fixes
2024-08-17 08:27:13 -07:00
Ross Wightman
1bd92bca0e
Add fused_attn flag to HieraDet attn block
2024-08-16 22:57:49 -07:00
Ross Wightman
691bb54443
Larger min input size needed
2024-08-16 17:09:19 -07:00
Ross Wightman
de3a91a7a0
Add min_input_size of 128 for hieradet/sam2
2024-08-16 15:13:56 -07:00
Ross Wightman
0b05122cda
Fixing hieradet (sam2) tests
2024-08-16 14:33:40 -07:00
Ross Wightman
e035381171
Move padding out of windowing code for hieradet, fix torchscript typing issues, make pooling MaxPool unique instances across two modules
2024-08-16 13:36:33 -07:00
