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
8efdc38213
Fix #2242 add checks for out indices with intermediate getter mode
2024-07-23 08:19:09 -07:00
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
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
2b3f1a4633
Make channels for classic resnet configurable
2024-07-22 10:47:40 -07:00
9b2b8014e8
Add weights for test models
2024-07-22 10:08:57 -07:00
a1996ec0f4
Merge pull request #2238 from huggingface/fix_mnv4_query_strides
...
Fix mnv4 query strides
2024-07-19 16:32:08 -07:00
7e0caa1ba3
Padding helpers work if tuples/lists passed
2024-07-19 14:28:03 -07:00
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
1a05ed29a1
Add to 'abswin' hiera models for train trials
2024-07-19 11:05:31 -07:00
0cbf4fa586
_orig_mod still causing issues even though I thought it was fixed in pytorch, add unwrap / clean helpers
2024-07-19 11:03:45 -07:00
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
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
3a8a965891
Implement absolute+window pos embed for hiera, resizable but needs new weights
2024-07-18 21:43:37 -07:00
7160af4a24
Merge pull request #2229 from Promisery/reg_token
...
Initialize weights of reg_token for ViT
2024-07-18 09:25:29 -07:00
392b78aee7
set_input_size initial impl for vit & swin v1. Move HybridEmbed to own location in timm/layers
2024-07-17 15:25:48 -07:00
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
3196d6b131
Merge pull request #2230 from TianyiFranklinWang/main
...
Avoid zero division error
2024-07-14 21:35:24 -07:00
d3ce5a8665
Avoid zero division error
2024-07-15 12:45:46 +10:00
417cf7f871
Initialize weights of reg_token for ViT
2024-07-13 11:11:42 +08:00
f920119f3b
Fixing tests
2024-07-09 14:53:20 -07:00
644abf9588
Fix default_cfg test for mobilenet_100
2024-07-09 12:52:24 -07:00
d5afe106dc
Merge remote-tracking branch 'origin/tiny_test_models' into small_things
2024-07-09 12:49:57 -07:00
55101028bb
Rename test_tiny* -> test*. Fix ByobNet BasicBlock attn location and add test_byobnet model.
2024-07-09 11:53:11 -07:00
1334598462
Add support back to EfficientNet to disable head_conv / bn2 so mobilnetv1 can be implemented properly
2024-07-08 13:51:26 -07:00
800405d941
Add conv_large mobilenetv3 aa/blur model defs
2024-07-08 13:50:05 -07:00
f81b094aaa
Add 'qkv_bias_separate' flag for EVA/beit/swinv2 attn modules to allow an override for easy quantization wrappers. Fix #2098
2024-07-08 13:48:38 -07:00
83c2c2f0c5
Add 'Maybe' PIL / image tensor conversions in case image alread in tensor format
2024-07-08 13:43:51 -07:00
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
c01a47c9e7
Fix typo in type annotations in timm.models.hrnet
2024-07-08 00:53:16 +02:00
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
197c10463b
Fix jit.script breaking with features_fx
2024-06-28 03:58:51 +00:00
d4ef0b4d58
Update README.md
2024-06-25 08:48:16 -07:00
b751da692d
Add latest ix (xavier init for mqa) hybrid medium & large weights for MobileNetV4
2024-06-24 13:49:55 -07:00
d4d4d84fda
Dev version 1.0.8.dev0
2024-06-24 11:34:13 -07:00
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
e7b4ab6a8d
Merge pull request #2214 from Sejik/main
...
Fix typo
2024-06-24 09:23:25 -07:00
c33a001397
Fix typo
2024-06-24 21:54:38 +09:00
02d0f27721
cleanup davit padding
2024-06-22 12:06:46 -07:00
c715c724e7
Fix tracing by removing float cast, should end up float anyways
2024-06-22 08:35:30 -07:00
fb58a73033
Fix #2212 map florence2 image tower to davit with a few changes
2024-06-21 15:31:29 -07:00
b28945ff05
Version 1.0.7, prep for release
2024-06-18 16:19:43 -07:00
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
427b3e46bd
Update README.md
2024-06-17 11:09:55 -07:00
16e082e1c2
Add mobilenetv4 hybrid-large weights
2024-06-17 11:08:31 -07:00
e41125cc83
Merge pull request #2209 from huggingface/fcossio-vit-maxpool
...
ViT pooling refactor
2024-06-17 07:51:12 -07:00
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
a22466852d
Add 2400 epoch mobilenetv4 small weights, almost at paper, rounds to 73.8
2024-06-16 10:51:00 -07:00
b1a6f4a946
Some missed reset_classifier() type annotations
2024-06-16 10:39:27 -07:00
71101ebba0
Refactor vit pooling to add more reduction options, separately callable
2024-06-14 23:16:58 -07:00
Ross Wightman
Ross Wightman
Zirunis
Feraidoon Mehri
Tianyi Wang
Promisery
Steffen Schneider
Daniel Suess
Sejik