9067be6a30
Add weights for new tiny test models
2024-09-22 07:59:23 -07:00
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
65564f7da5
Fix reversed H & W padding for swin patch merging
2024-09-21 16:51:02 -07:00
a2f539f055
Add a few more test model defs in prep for weight upload
2024-09-21 11:38:38 -07:00
6ab2af610d
Adding some more tiny test models to train
2024-09-06 15:35:57 -07:00
ee5b1e8217
Add missing nhwc bm for 4090
2024-09-05 07:30:24 -07:00
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
ef570e266d
Remove some of the older benchmark files
2024-09-04 15:38:31 -07:00
5c33776aa5
Add a bunch more benchmark sets
2024-09-04 15:35:26 -07:00
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
6c42299b3e
Back to dev version
2024-09-03 10:29:05 -07:00
a50713ce6e
Fix #2272
2024-09-02 13:20:05 -07:00
ebbe530ee4
Add MobileNetV3 RA4 (mnv4 recipe) weights
2024-09-02 13:10:34 -07:00
fa4a1e597f
Better all res resolution for bulk runner
2024-08-26 22:28:01 -07:00
b3f3a005a0
Add RTX4090 inference benchmark numbers for latest models
2024-08-26 17:15:05 -07:00
072783331f
Version 1.0.9
2024-08-23 11:47:42 -07:00
76b0e9931a
Placeholder for new mnv3 model
2024-08-23 10:11:20 -07:00
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
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
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
b9f020a509
Allow group_size override for more efficientnet and mobilenetv3 based models
2024-08-21 16:51:38 -07:00
26ed96b052
Create UPGRADING.md
2024-08-21 15:58:54 -07:00
29d69e8734
Update README.md
2024-08-21 15:53:04 -07:00
9f228b7fc4
Update README.md
2024-08-21 15:41:54 -07:00
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
17923a66bb
Add layer scale to hieradet
2024-08-21 11:23:39 -07:00
47e6958263
Add hierdet_small (non sam) model def
2024-08-21 11:05:54 -07:00
076efef73b
Merge pull request #2263 from andravin/fix-docs-install-dir
...
Fix install directory in hfdocs.
2024-08-21 10:24:16 -07:00
9fcbf39cdc
Add remaining sbb vit betwixt/mediumd fine-tunes
2024-08-21 10:09:38 -07:00
dc94cca0e5
Remaining Hiera sbb weights uploaded
2024-08-21 10:06:27 -07:00
3970558e0d
Fix install directory in hfdocs.
...
Change from "timm" to "pytorch-image-models"
2024-08-21 09:27:52 -07:00
a256e50457
Move padding back in front of windowing
2024-08-17 11:22:53 -07:00
7d83749207
pool size test fixes
2024-08-17 08:27:13 -07:00
1bd92bca0e
Add fused_attn flag to HieraDet attn block
2024-08-16 22:57:49 -07:00
691bb54443
Larger min input size needed
2024-08-16 17:09:19 -07:00
de3a91a7a0
Add min_input_size of 128 for hieradet/sam2
2024-08-16 15:13:56 -07:00
0b05122cda
Fixing hieradet (sam2) tests
2024-08-16 14:33:40 -07:00
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
146c2fbe34
Add resnet50d and efficientnet_b1 ra4 (mnv4) hparam weights
2024-08-16 12:10:00 -07:00
962958723c
More Hiera updates. Add forward_intermediates to hieradat/sam2 impl. Make both use same classifier module. Add coarse bool to intermediates.
2024-08-16 11:10:04 -07:00
f2cfb4c677
Add WIP HieraDet impl (SAM2 backbone support)
2024-08-15 17:58:15 -07:00
a50e53d41f
Rename global pos embed for Hiera abswin, factor out commonly used vit weight init fns to layers. Add a channels-last ver of normmlp head.
2024-08-15 17:46:36 -07:00
2f3fed43b8
Fix hiera init with num_classes=0, fix weight tag names for sbb2 hiera/vit weights, add LayerScale/LayerScale2d to layers
2024-08-15 11:14:38 -07:00
fee91fdd41
Update Hiera model for abswin, more stable weight init, layer-scale. ImageNet-12k weights for hiera_small_abswin, and two of the sbb vits with improved reg4 init.
2024-08-14 12:22:40 -07:00
ac3470188b
Add mobilenetv1_125 weights from ra4 / mnv4 hparam series
2024-08-14 08:47:02 -07:00
907555fda6
Update model img-size/crop expansion for bulk runner
2024-08-13 10:42:09 -07:00
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
2df9f2869d
Merge pull request #2257 from huggingface/weights_only
...
Add weights only flag to avoid warning, try to keep bwd compat.
2024-08-12 18:09:36 -07:00
a7b0bfc376
exception for unknown arg should have been TypeError
2024-08-12 16:09:36 -07:00
bd0f79153b
Add weights only flag to avoid warning, try to keep bwd compat. Default to True for remote load of pretrained weights, keep False for local checkpoing load to avoid training checkpoint breaks.. fix #2249
2024-08-12 11:41:41 -07:00
Ross Wightman
Ross Wightman
alias pillar1989
Andrew Lavin