Ross Wightman
f2086f51a0
Add mambaout builder support, pretrained weight remap
2024-10-09 14:11:40 -07:00
Ross Wightman
c6ef54eefa
Initial mambaout work
2024-10-09 14:11:40 -07:00
Ross Wightman
d9321b0e10
Add weights for fine-tuned siglip so400m. Add webli_i18n pretrained tags for the multi-lingual model variants (incl older base)
2024-10-09 09:04:44 -07:00
Ross Wightman
01b62264af
Add i18n variant of so400m model w/ weights. Add two in1k fine-tunes of original so400m 384x384 but at 378x378 (better matches patch14)
2024-10-08 23:40:24 -07:00
Ross Wightman
41a79e0fcb
Add overlapped stem convnext zepto weights
2024-10-08 11:26:34 -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
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
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
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
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
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
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
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
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
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
Ross Wightman
146c2fbe34
Add resnet50d and efficientnet_b1 ra4 (mnv4) hparam weights
2024-08-16 12:10:00 -07:00
Ross Wightman
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
Ross Wightman
f2cfb4c677
Add WIP HieraDet impl (SAM2 backbone support)
2024-08-15 17:58:15 -07:00
Ross Wightman
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
Ross Wightman
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
Ross Wightman
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
Ross Wightman
ac3470188b
Add mobilenetv1_125 weights from ra4 / mnv4 hparam series
2024-08-14 08:47:02 -07:00
Ross Wightman
a7b0bfc376
exception for unknown arg should have been TypeError
2024-08-12 16:09:36 -07:00
Ross Wightman
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
531215eded
Bring changelog up to current, back to dev version, 1.0.9.dev0
2024-08-08 09:17:23 -07:00
Ross Wightman
bf781bc3c2
Merge pull request #2245 from dhkim0225/feature/rdnet
...
Feature: Add RDNet
2024-08-07 16:19:22 -07:00
Ross Wightman
49f6e1da96
Remove eval to avoid safety concerns
2024-08-07 14:54:13 -07:00
Ross Wightman
2d5c9bf60d
Merge pull request #2253 from brendanartley/hgnet-grad-checkpointing
...
Add gradient checkpointing to hgnets
2024-08-07 12:45:14 -07:00
