Ross Wightman
|
e7abc320f5
|
Improve bulk_runner for 'all resolution' mode
|
2023-11-23 12:44:59 -08:00 |
|
Ross Wightman
|
40d55ab4bc
|
Add `in_chans` to data config helper. Fix #2021
|
2023-11-23 12:44:59 -08:00 |
Dillon Laird
|
63ee54853c
|
fixed intermediate output indices
|
2023-11-22 16:32:41 -08:00 |
|
Ross Wightman
|
4d0737d5fa
|
Add PT 2.1 NCHW 3090 benchmark results
|
2023-11-21 16:49:20 -08:00 |
|
Ross Wightman
|
fa06f6c481
|
Merge branch 'seefun-efficientvit'
|
2023-11-21 14:06:27 -08:00 |
|
Ross Wightman
|
c6b0c98963
|
Upload weights to hub, tweak crop_pct, comment out SAM EfficientViTs for now (v2 weights comming)
|
2023-11-21 14:05:04 -08:00 |
|
Ross Wightman
|
975203a369
|
Version 0.9.12dev0
|
2023-11-21 10:18:45 -08:00 |
|
Ross Wightman
|
055522bf84
|
Going to stop supporting Python 3.7 soon
|
2023-11-21 09:48:03 -08:00 |
|
Ross Wightman
|
ada145b016
|
Literal use w/ python < 3.8 requires typing_extension, cach instead of check sys ver
|
2023-11-21 09:48:03 -08:00 |
|
Ross Wightman
|
dfaab97d20
|
More consistency in model arg/kwarg merge handling
|
2023-11-21 09:48:03 -08:00 |
|
Ross Wightman
|
3775e4984f
|
Merge branch 'efficientvit' of github.com:seefun/pytorch-image-models into seefun-efficientvit
|
2023-11-20 16:21:38 -08:00 |
|
Ross Wightman
|
3370053e71
|
Update README
|
2023-11-20 14:39:22 -08:00 |
|
Ross Wightman
|
25cf2c2dbb
|
Update bulk_runner with improved filtering options for benchmarking / val runs
|
2023-11-20 14:08:51 -08:00 |
|
Ross Wightman
|
dfb8658100
|
Fix a few missed model deprecations and one missed pretrained cfg
|
2023-11-20 12:41:49 -08:00 |
|
Ross Wightman
|
057fdb570b
|
Update model eval result csv files
|
2023-11-20 10:06:40 -08:00 |
|
Ross Wightman
|
c20f5fc385
|
Version 0.9.11
|
2023-11-19 17:18:48 -08:00 |
|
Ross Wightman
|
a604011935
|
Add support for passing model args via hf hub config
|
2023-11-19 15:16:01 -08:00 |
Laureηt
|
23e7f17724
|
replace inline latex syntax in hfdocs
|
2023-11-19 09:34:38 -08:00 |
方曦
|
c9d093a58e
|
update norm eps for efficientvit large
|
2023-11-18 17:46:47 +08:00 |
|
Laureηt
|
21647c0a0c
|
Add types to vision_transformers.py
|
2023-11-17 16:06:06 -08:00 |
|
方曦
|
87ba43a9bc
|
add efficientvit large series
|
2023-11-17 13:58:46 +08:00 |
Alex Cunha
|
a38c2b4475
|
fix bug
|
2023-11-16 20:27:59 -08:00 |
|
Alex Cunha
|
bbf0ab000c
|
return if cuda not available
|
2023-11-16 20:27:59 -08:00 |
|
Alex Cunha
|
e628ed7e67
|
device agnostic testing
|
2023-11-16 20:27:59 -08:00 |
|
Ross Wightman
|
7c685a4ef3
|
Fix openai quickgelu loading and add mnissing orig_in21k vit weights and remove zero'd classifier w/ matching hub update
|
2023-11-16 19:16:28 -08:00 |
LittleNyima
|
ef72c3cd47
|
Add warnings for duplicate registry names
|
2023-11-08 10:18:59 -08:00 |
Ross Wightman
|
0bc9a63ee5
|
Update README.md
|
2023-11-07 11:28:23 -08:00 |
|
Ross Wightman
|
205d8ad37c
|
version 0.9.10
|
2023-11-04 02:33:04 -07:00 |
|
Ross Wightman
|
9fab8d8f58
|
Fix break of 2 years old torchvision installs :/
|
2023-11-04 02:32:09 -07:00 |
|
Ross Wightman
|
d3e83a190f
|
Add in12k fine-tuned convnext_xxlarge
|
2023-11-03 14:35:01 -07:00 |
|
Ross Wightman
|
855719fca6
|
Prep for 0.9.9 release
|
2023-11-03 11:38:09 -07:00 |
|
Ross Wightman
|
f7762fee78
|
Consistency handling None / empty string inputs to norm / act create fns
|
2023-11-03 11:01:41 -07:00 |
|
Ross Wightman
|
dcfdba1f5f
|
Make quickgelu models appear in listing
|
2023-11-03 11:01:41 -07:00 |
|
Ross Wightman
|
96bd162ddb
|
Add cc-by-nc-4.0 license for metaclip, make note in quickgelu model def about pretrained_cfg mapping
|
2023-11-03 11:01:41 -07:00 |
|
Ross Wightman
|
6894ec7edc
|
Forgot about datcomp b32 models
|
2023-11-03 11:01:41 -07:00 |
|
Ross Wightman
|
a2e4a4c148
|
Add quickgelu vit clip variants, simplify get_norm_layer and allow string args in vit norm/act. Add metaclip CLIP weights
|
2023-11-03 11:01:41 -07:00 |
|
Ross Wightman
|
c55bc41a42
|
DFN CLIP ViT support
|
2023-10-31 12:16:21 -07:00 |
a-r-r-o-w
|
d5f1525334
|
include suggestions from review
Co-Authored-By: Ross Wightman <rwightman@gmail.com>
|
2023-10-30 13:47:54 -07:00 |
|
a-r-r-o-w
|
5f14bdd564
|
include typing suggestions by @rwightman
|
2023-10-30 13:47:54 -07:00 |
|
a-r-r-o-w
|
05b0aaca51
|
improvement: add typehints and docs to timm/models/resnet.py
|
2023-10-30 13:47:54 -07:00 |
|
a-r-r-o-w
|
564db019f6
|
fix: typo in CONTRIBUTING.md
|
2023-10-30 13:47:54 -07:00 |
|
a-r-r-o-w
|
c2fe0a2268
|
improvement: add typehints and docs to timm/models/mobilenetv3.py
|
2023-10-30 13:47:54 -07:00 |
Laureηt
|
d023154bb5
|
Update swin_transformer.py
make `SwimTransformer`'s `patch_embed` customizable through the constructor
|
2023-10-30 13:47:14 -07:00 |
|
Ross Wightman
|
68a121402f
|
Added hub weights for dinov2 register models
|
2023-10-29 23:03:48 -07:00 |
|
Ross Wightman
|
3f02392488
|
Add DINOv2 models with register tokens. Convert pos embed to non-overlapping for consistency.
|
2023-10-29 23:03:48 -07:00 |
|
Laureηt
|
fe92fd93e5
|
fix adaptive_avgmax_pool.py
remove extra whitespace in `SelectAdaptivePool2d`'s `__repr__`
|
2023-10-29 23:03:36 -07:00 |
Patrick Labatut
|
97450d618a
|
Update DINOv2 license to Apache 2.0
|
2023-10-27 09:12:51 -07:00 |
mjamroz
|
7a6369156f
|
avoid getting undefined
|
2023-10-22 21:36:23 -07:00 |
Tush9905
|
89ba0da910
|
Fixed Typos
Fixed the typos in helpers.py and CONTRIBUTING.md
|
2023-10-21 21:46:31 -07:00 |
|
Ross Wightman
|
9afe0bb78e
|
Update README, prep for 0.9.8 release
|
2023-10-20 13:57:23 -07:00 |