Ross Wightman
8b14fc7bb6
Merge pull request #2240 from Zirunis/Zirunis-patch-1
...
Fix LR scheduler help in train.py
2024-07-23 11:04:18 -07:00
Ross Wightman
f3c11dc3a5
Merge pull request #2239 from huggingface/fix_out_indices_order
...
Fix issue where feature out_indices out of order after wrapping with FeatureGetterNet
2024-07-23 11:02:42 -07:00
Ross Wightman
8efdc38213
Fix #2242 add checks for out indices with intermediate getter mode
2024-07-23 08:19:09 -07:00
Zirunis
4ed93fce93
Fix LR scheduler help in train.py
...
The default is and always has been the cosine scheduler, yet the help states that the default would be the step scheduler. Whatever the intended one was, for backwards compatibility the default should definitely remain cosine, which is why I changed the help comment to reflect that.
2024-07-22 23:04:00 +02:00
Ross Wightman
d2240745d3
Fix issue where feature out_indices out of order after wrapping with FeatureGetterNet due to use of set()
2024-07-22 13:33:30 -07:00
Ross Wightman
a1996ec0f4
Merge pull request #2238 from huggingface/fix_mnv4_query_strides
...
Fix mnv4 query strides
2024-07-19 16:32:08 -07:00
Ross Wightman
7e0caa1ba3
Padding helpers work if tuples/lists passed
2024-07-19 14:28:03 -07:00
Ross Wightman
2180800646
MQA query_strides bugs fix #2237 . No padding for avg_pool2d if not 'same', use scale_factor for Upsample.
2024-07-19 14:26:54 -07:00
Ross Wightman
474c9cf768
Merge pull request #2236 from NightMachinery/patch-1
...
eva.py: fixed bug in applying attention mask
2024-07-19 08:09:56 -07:00
Feraidoon Mehri
4cca568bd8
eva.py: fixed bug in applying attention mask
...
The mask should be applied before the softmax.
2024-07-19 15:12:04 +03:30
Ross Wightman
7160af4a24
Merge pull request #2229 from Promisery/reg_token
...
Initialize weights of reg_token for ViT
2024-07-18 09:25:29 -07:00
Ross Wightman
34c9fee554
Fix pass through of input / target keys so ImageDataset readers so args work with hfds instead of just hfids (iterable)
2024-07-17 10:11:46 -07:00
Ross Wightman
3196d6b131
Merge pull request #2230 from TianyiFranklinWang/main
...
Avoid zero division error
2024-07-14 21:35:24 -07:00
Tianyi Wang
d3ce5a8665
Avoid zero division error
2024-07-15 12:45:46 +10:00
Promisery
417cf7f871
Initialize weights of reg_token for ViT
2024-07-13 11:11:42 +08:00
Ross Wightman
648aaa4123
Merge pull request #2223 from stes/patch-1
...
Fix typo in type annotations in timm.models.hrnet
2024-07-08 07:34:47 -07:00
Steffen Schneider
c01a47c9e7
Fix typo in type annotations in timm.models.hrnet
2024-07-08 00:53:16 +02:00
Ross Wightman
20fe56bd90
Merge pull request #2217 from dsuess/2216_fix_script_on_features_fx
...
Fix jit.script breaking with features_fx
2024-06-28 16:13:02 -07:00
Daniel Suess
197c10463b
Fix jit.script breaking with features_fx
2024-06-28 03:58:51 +00:00
Ross Wightman
d4ef0b4d58
Update README.md
2024-06-25 08:48:16 -07:00
Ross Wightman
b751da692d
Add latest ix (xavier init for mqa) hybrid medium & large weights for MobileNetV4
2024-06-24 13:49:55 -07:00
Ross Wightman
d4d4d84fda
Dev version 1.0.8.dev0
2024-06-24 11:34:13 -07:00
Ross Wightman
f8342a045a
Merge pull request #2213 from huggingface/florence2
...
Fix #2212 map florence2 image tower to davit with a few changes
2024-06-24 11:01:08 -07:00
Ross Wightman
e7b4ab6a8d
Merge pull request #2214 from Sejik/main
...
Fix typo
2024-06-24 09:23:25 -07:00
Sejik
c33a001397
Fix typo
2024-06-24 21:54:38 +09:00
Ross Wightman
02d0f27721
cleanup davit padding
2024-06-22 12:06:46 -07:00
Ross Wightman
c715c724e7
Fix tracing by removing float cast, should end up float anyways
2024-06-22 08:35:30 -07:00
Ross Wightman
fb58a73033
Fix #2212 map florence2 image tower to davit with a few changes
2024-06-21 15:31:29 -07:00
Ross Wightman
b28945ff05
Version 1.0.7, prep for release
2024-06-18 16:19:43 -07:00
Ross Wightman
fb13e6385e
Merge pull request #2203 from huggingface/more_mobile
...
Add mobilenet edgetpu defs for exp, add ol mobilenet v1 back for comp…
2024-06-18 15:20:01 -07:00
Ross Wightman
427b3e46bd
Update README.md
2024-06-17 11:09:55 -07:00
Ross Wightman
16e082e1c2
Add mobilenetv4 hybrid-large weights
2024-06-17 11:08:31 -07:00
Ross Wightman
e41125cc83
Merge pull request #2209 from huggingface/fcossio-vit-maxpool
...
ViT pooling refactor
2024-06-17 07:51:12 -07:00
Ross Wightman
6254dfaece
Add numpy<2.0 to requirements until tests are sorted out for pytorch 2.3 vs older
2024-06-16 11:24:45 -07:00
Ross Wightman
a22466852d
Add 2400 epoch mobilenetv4 small weights, almost at paper, rounds to 73.8
2024-06-16 10:51:00 -07:00
Ross Wightman
b1a6f4a946
Some missed reset_classifier() type annotations
2024-06-16 10:39:27 -07:00
Ross Wightman
71101ebba0
Refactor vit pooling to add more reduction options, separately callable
2024-06-14 23:16:58 -07:00
Ross Wightman
a0bb5b4a44
Missing stem_kernel_size argument in EfficientNetFeatures
2024-06-14 13:39:31 -07:00
Fernando Cossio
9567cf6d84
Feature: add option global_pool='max' to VisionTransformer
...
Most of the CNNs have a max global pooling option. I would like to extend ViT to have this option.
2024-06-14 15:24:54 +02:00
Ross Wightman
9613c76844
Add mobilenet edgetpu defs for exp, add ol mobilenet v1 back for completeness / comparison
2024-06-13 17:33:04 -07:00
Ross Wightman
22de845add
Prepping for final MobileCLIP weight locations ( #2199 )
...
* Prepping for final MobileCLIP weight locations
* Update weight locations to coreml-projects
* Update mobileclip weight locations with final apple org location
2024-06-13 16:55:49 -07:00
Ross Wightman
575978ba55
Add mnv4_conv_large 384x384 weight location
2024-06-13 12:58:04 -07:00
Ross Wightman
832d3618a5
Update README.md
2024-06-12 23:26:05 -07:00
Ross Wightman
7b5f17d1bd
Update README.md, bump dev version 1.0.6
2024-06-12 12:35:44 -07:00
Ross Wightman
e42e453128
Fix mmnv4 conv_large weight link, reorder mnv4 pretrained cfg for proper precedence
2024-06-12 11:16:49 -07:00
Ross Wightman
7b0a5321cb
Merge pull request #2198 from huggingface/openai_clip_resnet
...
Mapping OpenAI CLIP Modified ResNet weights -> ByobNet.
2024-06-12 09:33:30 -07:00
Ross Wightman
57adc1acc8
Fix rotary embed version of attn pool. Bit of cleanup/naming
2024-06-11 23:49:17 -07:00
Ross Wightman
5aa49d56bf
Merge pull request #2202 from huggingface/mnv4_first_weights
...
First set of MobileNetV4 weights trained in timm
2024-06-11 23:06:22 -07:00
Ross Wightman
cdc7bcea69
Make 2d attention pool modules compatible with head interface. Use attention pool in CLIP ResNets as head. Make separate set of GAP models w/ avg pool instead of attn pool.
2024-06-11 21:32:07 -07:00
Ross Wightman
c63da1405c
Pretrained cfg name mismatch
2024-06-11 21:16:54 -07:00
