Ross Wightman
2b3f1a4633
Make channels for classic resnet configurable
2024-07-22 10:47:40 -07:00
Ross Wightman
9b2b8014e8
Add weights for test models
2024-07-22 10:08:57 -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
1a05ed29a1
Add to 'abswin' hiera models for train trials
2024-07-19 11:05:31 -07:00
Ross Wightman
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
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
3a8a965891
Implement absolute+window pos embed for hiera, resizable but needs new weights
2024-07-18 21:43:37 -07:00
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
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
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
Promisery
417cf7f871
Initialize weights of reg_token for ViT
2024-07-13 11:11:42 +08:00
Ross Wightman
f920119f3b
Fixing tests
2024-07-09 14:53:20 -07:00
Ross Wightman
644abf9588
Fix default_cfg test for mobilenet_100
2024-07-09 12:52:24 -07:00
Ross Wightman
d5afe106dc
Merge remote-tracking branch 'origin/tiny_test_models' into small_things
2024-07-09 12:49:57 -07:00
Ross Wightman
55101028bb
Rename test_tiny* -> test*. Fix ByobNet BasicBlock attn location and add test_byobnet model.
2024-07-09 11:53:11 -07:00
Ross Wightman
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
Ross Wightman
800405d941
Add conv_large mobilenetv3 aa/blur model defs
2024-07-08 13:50:05 -07:00
Ross Wightman
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
Ross Wightman
83c2c2f0c5
Add 'Maybe' PIL / image tensor conversions in case image alread in tensor format
2024-07-08 13:43:51 -07:00
Steffen Schneider
c01a47c9e7
Fix typo in type annotations in timm.models.hrnet
2024-07-08 00:53:16 +02:00
Daniel Suess
197c10463b
Fix jit.script breaking with features_fx
2024-06-28 03:58:51 +00:00
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
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
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
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
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
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
Ross Wightman
88efca1be2
First set of MobileNetV4 weights trained in timm
2024-06-11 18:53:01 -07:00
Ross Wightman
30ffa152de
Fix load of larger ResNet CLIP models, experimenting with making AttentionPool *the* head, seems to fine-tune better, one less layer.
2024-06-10 12:07:14 -07:00
Ross Wightman
5e9ff5798f
Adding pos embed resize fns to FX autowrap exceptions
2024-06-10 12:06:47 -07:00
