Ross Wightman
cf5ac2800c
BotNet models were still off, remove weights for bad configs. Add good SE-HaloNet33-TS weights.
3 years ago
Ross Wightman
24720abe3b
Merge branch 'master' into attn_update
3 years ago
Ross Wightman
1c9284c640
Add BeiT 'finetuned' 1k weights and pretrained 22k weights, pretraining specific (masked) model excluded for now
3 years ago
Ross Wightman
f8a215cfe6
A few more crossvit tweaks, fix training w/ no_weight_decay names, add crop option for scaling, adjust default crop_pct for large img size to 1.0 for better results
3 years ago
Ross Wightman
7ab2491ab7
Better handling of crossvit for tests / forward_features, fix torchscript regression in my changes
3 years ago
Ross Wightman
f1808e0970
Post crossvit merge cleanup, change model names to reflect input size, cleanup img size vs scale handling, fix tests
3 years ago
Ross Wightman
4027412757
Add resnet33ts weights, update resnext26ts baseline weights
3 years ago
Richard Chen
9fe5798bee
fix bug for reset classifier and fix for validating the dimension
3 years ago
Richard Chen
3718c5a5bd
fix loading pretrained model
3 years ago
Richard Chen
bb50b69a57
fix for torch script
3 years ago
nateraw
abf9d51bc3
🚧 wip
3 years ago
Ross Wightman
5bd04714e4
Cleanup weight init for byob/byoanet and related
3 years ago
Ross Wightman
8642401e88
Swap botnet 26/50 weights/models after realizing a mistake in arch def, now figuring out why they were so low...
3 years ago
Ross Wightman
5f12de4875
Add initial AttentionPool2d that's being trialed. Fix comment and still trying to improve reliability of sgd test.
3 years ago
Ross Wightman
76881d207b
Add baseline resnet26t @ 256x256 weights. Add 33ts variant of halonet with at least one halo in stage 2,3,4
3 years ago
Ross Wightman
484e61648d
Adding the attn series weights, tweaking model names, comments...
3 years ago
nateraw
28d2841acf
💄 apply isort
3 years ago
Ross Wightman
492c0a4e20
Update HaloAttn comment
3 years ago
nateraw
e72c989973
✨ add ability to push to hf hub
3 years ago
Richard Chen
7ab9d4555c
add crossvit
3 years ago
Ross Wightman
3b9032ea48
Use Tensor.unfold().unfold() for HaloAttn, fast like as_strided but more clarity
3 years ago
Ross Wightman
78933122c9
Fix silly typo
3 years ago
Ross Wightman
2568ffc5ef
Merge branch 'master' into attn_update
3 years ago
Ross Wightman
708d87a813
Fix ViT SAM weight compat as weights at URL changed to not use repr layer. Fix #825 . Tweak optim test.
3 years ago
Ross Wightman
8449ba210c
Improve performance of HaloAttn, change default dim calc. Some cleanup / fixes for byoanet. Rename resnet26ts to tfs to distinguish (extra fc).
3 years ago
Ross Wightman
a8b65695f1
Add resnet26ts and resnext26ts models for non-attn baselines
3 years ago
Ross Wightman
a5a542f17d
Fix typo
3 years ago
Ross Wightman
925e102982
Update attention / self-attn based models from a series of experiments:
...
* remove dud attention, involution + my swin attention adaptation don't seem worth keeping
* add or update several new 26/50 layer ResNe(X)t variants that were used in experiments
* remove models associated with dead-end or uninteresting experiment results
* weights coming soon...
3 years ago
Ross Wightman
01cb46a9a5
Add gc_efficientnetv2_rw_t weights (global context instead of SE attn). Add TF XL weights even though the fine-tuned ones don't validate that well. Change default arg for GlobalContext to use scal (mul) mode.
3 years ago
Ross Wightman
d3f7440650
Add EfficientNetV2 XL model defs
3 years ago
Ross Wightman
72b227dcf5
Merge pull request #750 from drjinying/master
...
Specify "interpolation" mode in vision_transformer's resize_pos_embed
3 years ago
Ross Wightman
748ab852ca
Allow act_layer switch for xcit, fix in_chans for some variants
3 years ago
Ying Jin
20b2d4b69d
Use bicubic interpolation in resize_pos_embed()
3 years ago
Ross Wightman
d3255adf8e
Merge branch 'xcit' of https://github.com/alexander-soare/pytorch-image-models into alexander-soare-xcit
3 years ago
Ross Wightman
f8039c7492
Fix gc effv2 model cfg name
4 years ago
Alexander Soare
3a55a30ed1
add notes from author
4 years ago
Alexander Soare
899cf84ccc
bug fix - missing _dist postfix for many of the 224_dist models
4 years ago
Alexander Soare
623e8b8eb8
wip xcit
4 years ago
Ross Wightman
392368e210
Add efficientnetv2_rw_t defs w/ weights, and gc variant, as well as gcresnet26ts for experiments. Version 0.4.13
4 years ago
Ross Wightman
6d8272e92c
Add SAM pretrained model defs/weights for ViT B16 and B32 models.
4 years ago
Ross Wightman
ee4d8fc69a
Remove unecessary line from nest post refactor
4 years ago
Ross Wightman
8165cacd82
Realized LayerNorm2d won't work in all cases as is, fixed.
4 years ago
Ross Wightman
81cd6863c8
Move aggregation (convpool) for nest into NestLevel, cleanup and enable features_only use. Finalize weight url.
4 years ago
Ross Wightman
6ae0ac6420
Merge branch 'nested_transformer' of https://github.com/alexander-soare/pytorch-image-models into alexander-soare-nested_transformer
4 years ago
Alexander Soare
7b8a0017f1
wip to review
4 years ago
Alexander Soare
b11d949a06
wip checkpoint with some feature extraction work
4 years ago
Alexander Soare
23bb72ce5e
nested_transformer wip
4 years ago
Ross Wightman
766b4d3262
Fix features for resnetv2_50t
4 years ago
Ross Wightman
e8045e712f
Fix BatchNorm for ResNetV2 non GN models, add more ResNetV2 model defs for future experimentation, fix zero_init of last residual for pre-act.
4 years ago
Ross Wightman
20a2be14c3
Add gMLP-S weights, 79.6 top-1
4 years ago
Ross Wightman
85f894e03d
Fix ViT in21k representation (pre_logits) layer handling across old and new npz checkpoints
4 years ago
Ross Wightman
b41cffaa93
Fix a few issues loading pretrained vit/bit npz weights w/ num_classes=0 __init__ arg. Missed a few other small classifier handling detail on Mlp, GhostNet, Levit. Should fix #713
4 years ago
Ross Wightman
9c9755a808
AugReg release
4 years ago
Ross Wightman
381b279785
Add hybrid model fwds back
4 years ago
Ross Wightman
26f04a8e3e
Fix a weight link
4 years ago
Ross Wightman
8f4a0222ed
Add GMixer-24 MLP model weights, trained w/ TPU + PyTorch XLA
4 years ago
Ross Wightman
b319eb5b5d
Update ViT weights, more details to be added before merge.
4 years ago
Ross Wightman
8257b86550
Fix up resnetv2 bit/bitm model default res
4 years ago
Ross Wightman
1228f5a3d8
Add BiT distilled 50x1 and teacher 152x2 models from 'A good teacher is patient and consistent' paper.
4 years ago
Ross Wightman
511a8e8c96
Add official ResMLP weights.
4 years ago
Ross Wightman
b9cfb64412
Support npz custom load for vision transformer hybrid models. Add posembed rescale for npz load.
4 years ago
Ross Wightman
8319e0c373
Add file docstring to std_conv.py
4 years ago
Ross Wightman
4d96165989
Merge branch 'master' into cleanup_xla_model_fixes
4 years ago
Ross Wightman
8880f696b6
Refactoring, cleanup, improved test coverage.
...
* Add eca_nfnet_l2 weights, 84.7 @ 384x384
* All 'non-std' (ie transformer / mlp) models have classifier / default_cfg test added
* Fix #694 reset_classifer / num_features / forward_features / num_classes=0 consistency for transformer / mlp models
* Add direct loading of npz to vision transformer (pure transformer so far, hybrid to come)
* Rename vit_deit* to deit_*
* Remove some deprecated vit hybrid model defs
* Clean up classifier flatten for conv classifiers and unusual cases (mobilenetv3/ghostnet)
* Remove explicit model fns for levit conv, just pass in arg
4 years ago
Ross Wightman
ba2ca4b464
One codepath for stdconv, switch layernorm to batchnorm so gain included. Tweak epsilon values for nfnet, resnetv2, vit hybrid.
4 years ago
Ross Wightman
b7a568f065
Fix torchscript issue in bat
4 years ago
Ross Wightman
d17b374f0f
Minimum input_size needed to be higher
4 years ago
Ross Wightman
b3b90d944d
Add min_input_size to bat_resnext to prevent test breakage.
4 years ago
Ross Wightman
d413eef1bf
Add ResMLP-24 model weights that I trained in PyTorch XLA on TPU-VM. 79.2 top-1.
4 years ago
Ross Wightman
10d8fa4620
Add gc and bat attention resnext26ts variants to byob for test.
4 years ago
Ross Wightman
2f5ed2dec1
Update `init_values` const for 24 and 36 layer ResMLP models
4 years ago
Ross Wightman
8e4ac3549f
All ScaledStdConv and StdConv uses default to using F.layernorm so that they work with PyTorch XLA. eps value tweaking is a WIP.
4 years ago
Ross Wightman
2a63d0246b
Post merge cleanup
4 years ago
Ross Wightman
45dec179e5
Merge pull request #681 from lmk123568/master
...
Update convit.py
4 years ago
Dongyoon Han
ded1671483
Fix stochastic depth working only with a shortcut
4 years ago
Mike
b87d98b238
Update convit.py
...
Cut out the duplicates
4 years ago
Ross Wightman
bda8ab015a
Remove min channels for SelectiveKernel, divisor should cover cases well enough.
4 years ago
Ross Wightman
a27f4aec4a
Missed args for skresnext w/ refactoring.
4 years ago
Ross Wightman
307a935b79
Add non-local and BAT attention. Merge attn and self-attn factories into one. Add attention references to README. Add mlp 'mode' to ECA.
4 years ago
Ross Wightman
8bf63b6c6c
Able to use other attn layer in EfficientNet now. Create test ECA + GC B0 configs. Make ECA more configurable.
4 years ago
Ross Wightman
bcec14d3b5
Bring EfficientNet SE layer in line with others, pull se_ratio outside of blocks. Allows swapping w/ other attn layers.
4 years ago
Ross Wightman
9611458e19
Throw in some FBNetV3 code I had lying around, some refactoring of SE reduction channel calcs for all EffNet archs.
4 years ago
Ross Wightman
01b9108619
Merge branch 'master' into more_attn
4 years ago
Ross Wightman
d7bab8a6c5
Fix strict flag change for checkpoint load.
4 years ago
Ross Wightman
02f9d4bc34
Add weights for resnet51q model, add 61q def.
4 years ago
Ross Wightman
f615474be3
Fix broken test, repvgg block doesn't have attn_last attr.
4 years ago
Ross Wightman
742c2d5247
Add Gather-Excite and Global Context attn modules. Refactor existing SE-like attn for consistency and refactor byob/byoanet for less redundancy.
4 years ago
Ross Wightman
9c78de8c02
Fix #661 , move hardswish out of default args for LeViT. Enable native torch support for hardswish, hardsigmoid, mish if present.
4 years ago
Ross Wightman
5db7452173
Fix visformer in_chans stem handling
4 years ago
Ross Wightman
11ae795e99
Redo LeViT attention bias caching in a way that works with both torchscript and DataParallel
4 years ago
Ross Wightman
d400f1dbdd
Filter test models before creation for backward/torchscript tests
4 years ago
Ross Wightman
c4572cc5aa
Add Visformer-small weighs, tweak torchscript jit test img size.
4 years ago
Ross Wightman
bfc72f75d3
Expand scope of testing for non-std vision transformer / mlp models. Some related cleanup and create fn cleanup for all vision transformer and mlp models. More CoaT weights.
4 years ago
Ross Wightman
18bf520ad1
Add eca_nfnet_l2/l3 defs for future training
4 years ago
Ross Wightman
f45de37690
Merge branch 'master' into levit_visformer_rednet
4 years ago
Ross Wightman
23c18a33e4
Add efficientnetv2_rw_m weights trained in PyTorch. 84.8 top-1 @ 416 test. 53M params.
4 years ago
Ross Wightman
c2ba229d99
Prep for effcientnetv2_rw_m model weights that started training before official release..
4 years ago
Ross Wightman
30b9880d06
Minor adjustment, mutable default arg, extra check of valid len...
4 years ago
Ross Wightman
be0abfbcce
Merge branch 'master' of https://github.com/alexander-soare/pytorch-image-models into alexander-soare-master
4 years ago
Ross Wightman
b7de82e835
ConViT cleanup, fix torchscript, bit of reformatting, reuse existing layers.
4 years ago
Ross Wightman
306c86b668
Merge branch 'convit' of https://github.com/amaarora/pytorch-image-models into amaarora-convit
4 years ago
Ross Wightman
a569635045
Update twin weights to a copy in GitHub releases for faster dl. Tweak model class comment.
4 years ago
Ross Wightman
be99eef9c1
Remove redundant code, cleanup, fix torchscript.
4 years ago
Ross Wightman
5ab372a3ec
Merge branch 'master' of https://github.com/abcdvzz/pytorch-image-models into abcdvzz-master
4 years ago
Aman Arora
5db1eb6ba5
Add defaults
4 years ago
Aman Arora
8b1f2e8e1f
remote unused matplotlib import
4 years ago
Aman Arora
40c506ba1e
Add ConViT
4 years ago
Alexander Soare
7976019864
extend positional embedding resizing functionality to tnt
4 years ago
Alexander Soare
8086943b6f
allow resize positional embeddings to non-square grid
4 years ago
talrid
dc1a4efd28
mixer_b16_224_miil, mixer_b16_224_miil_in21k models
4 years ago
李鑫杰
7b799c4e79
add latest code
4 years ago
Ross Wightman
d5af752117
Add preliminary gMLP and ResMLP impl to Mlp-Mixer
4 years ago
李鑫杰
00548b8427
Add Twins
4 years ago
Ross Wightman
e7f0db8664
Fix drop/drop_path arg on MLP-Mixer model. Fix #641
4 years ago
Ross Wightman
9a3ae97311
Another set of byoanet models w/ ECA channel + SA + groups
4 years ago
Ross Wightman
7077f16c6a
Change 21k model naming from _21k to _in21k for consistency with existing 21k models.
4 years ago
Ross Wightman
94d4b53352
Add temporary default_cfgs to visformer models so they pass tests
4 years ago
Ross Wightman
3bffc701f1
Merge branch 'master' into levit_visformer_rednet
4 years ago
Ross Wightman
ecc7552c5c
Add levit, levit_c, and visformer model defs. Largely untested and not finished cleanup.
4 years ago
Ross Wightman
165fb354b2
Add initial RedNet model / Involution layer impl for testing
4 years ago
Ross Wightman
328249f11a
Update README, tweak fine-tune effv2 model names.
4 years ago
Ross Wightman
c4f482a08b
EfficientNetV2 official impl w/ weights ported from TF. Cleanup/refactor of related EfficientNet classes and models.
4 years ago
Ross Wightman
4fbc32d3d0
Fix crop_pct for cait models.
4 years ago
Ross Wightman
715519a5ef
Rethink name of patch embed grid info
4 years ago
Ross Wightman
b2c305c2aa
Move Mlp and PatchEmbed modules into layers. Being used in lots of models now...
4 years ago
Ross Wightman
3ba6b55cb2
More adjustments to ByoaNet models for further experiments.
4 years ago
Ross Wightman
5fcddb96a8
Merge branch 'master' into cait
4 years ago
Ross Wightman
3db12b4b6a
Finish CaiT cleanup
4 years ago
Ross Wightman
2d8b09fe8b
Add official pretrained weights to MLP-Mixer, complete model cfgs.
4 years ago
Ross Wightman
12efffa6b1
Initial MLP-Mixer attempt...
4 years ago
Ross Wightman
0721559511
Improved (hopefully) init for SA/SA-like layers used in ByoaNets
4 years ago
Ross Wightman
d5473c17f7
Fix incorrect name of shortcut/identity paths in many residual nets. Inherited from naming in old old torchvision, long fixed there.
4 years ago
Ross Wightman
0d87650fea
Remove filter hack from BlurPool w/ non-persistent buffer. Use BlurPool2d instead of AntiAliasing.. for TResNet. Breaks PyTorch < 1.6.
4 years ago
Ross Wightman
ddc743fdf8
Update ResNet-RS models to EMA weights
4 years ago
Ross Wightman
08d60f4a9a
resnetrs50 pool sizing wrong
4 years ago
Ross Wightman
1daa15ecc3
Initial Cait commit. Still some cleanup to do.
4 years ago
Ross Wightman
67d0665b46
Post ResNet-RS merge cleanup. Add weight urls, adjust train/test/crop pct.
4 years ago
Aman Arora
560eae38f5
[WIP] Add ResNet-RS models ( #554 )
...
* Add ResNet-RS models
* Only include resnet-rs changes
* remove whitespace diff
* EOF newline
* Update time
* increase time
* Add first conv
* Try running only resnetv2_101x1_bitm on Linux runner
* Add to exclude filter
* Run test_model_forward_features for all
* Add to exclude ftrs
* back to defaults
* only run test_forward_features
* run all tests
* Run all tests
* Add bigger resnetrs to model filters to fix Github CLI
* Remove resnetv2_101x1_bitm from exclude feat features
* Remove hardcoded values
* Make sure reduction ratio in resnetrs is 0.25
* There is no bias in replaced maxpool so remove it
4 years ago
Ross Wightman
9cc7dda6e5
Fixup byoanet configs to pass unit tests. Add swin_attn and swinnet26t model for testing.
4 years ago
Ross Wightman
e15c3886ba
Defaul lambda r=7. Define '26t' stage 4/5 256x256 variants for all of bot/halo/lambda nets for experiment. Add resnet50t for exp. Fix a few comments.
4 years ago
Ross Wightman
e5e15754c9
Fix coat first conv ident
4 years ago
Ross Wightman
76739a7589
CoaT merge. Bit of formatting, fix torchscript (for non features), remove einops/einsum dep, add pretrained weight hub (url) support.
4 years ago
Ross Wightman
026430c083
Merge branch 'master' of https://github.com/morizin/pytorch-image-models-1 into morizin-master
4 years ago
Ross Wightman
a0492e3b48
A few miil weights naming tweaks to improve compat with model registry and filtering wildcards.
4 years ago
talrid
8c1f03e56c
comment
4 years ago
talrid
19e1b67a84
old spaces
4 years ago
talrid
a443865876
update naming and scores
4 years ago
talrid
cf0e371594
84_0
4 years ago
talrid
0968bdeca3
vit, tresnet and mobilenetV3 ImageNet-21K-P weights
4 years ago
morizin
1e3b6d4dfc
Update __init__.py
4 years ago
morizin
fd022fd6a2
Update __init__.py
4 years ago
morizin
c2d5087eae
Add files via upload
4 years ago
Ross Wightman
c1cf9712fc
Add updated EfficientNet-V2S weights, 83.8 @ 384x384 test. Add PyTorch trained EfficientNet-B4 weights, 83.4 @ 384x384 test. Tweak non TF EfficientNet B1-B4 train/test res scaling.
4 years ago
Ross Wightman
e8a64fb881
Test input size for efficientnet_v2s was wrong in last results run
4 years ago
Ross Wightman
2df77ee5cb
Fix torchscript compat and features_only behaviour in GhostNet PR. A few minor formatting changes. Reuse existing layers.
4 years ago
Ross Wightman
d793deb51a
Merge branch 'master' of https://github.com/iamhankai/pytorch-image-models into iamhankai-master
4 years ago
Ross Wightman
f606c45c38
Add Swin Transformer models from https://github.com/microsoft/Swin-Transformer
4 years ago
iamhankai
de445e7827
Add GhostNet
4 years ago
Ross Wightman
b3d7580df1
Update ByoaNet comments. Fix first Steam feat chs for ByobNet.
4 years ago
Ross Wightman
16f7aa9f54
Add default_cfg options for min_input_size / fixed_input_size, queries in model registry, and use for testing self-attn models
4 years ago
Ross Wightman
4e4b863b15
Missed norm.py
4 years ago
Ross Wightman
7c97e66f7c
Remove commented code, add more consistent seed fn
4 years ago
Ross Wightman
ce62f96d4d
ByoaNet with bottleneck transformer, lambda resnet, and halo net experiments
4 years ago
Ross Wightman
21812d33aa
Add prelim efficientnet_v2s weights from 224x224 train, eval 83.3 @ 288. Add eca_nfnet_l1 weights, train at 256, eval 84 @ 320.
4 years ago
Ross Wightman
fb896c0b26
Update some comments re preliminary EfficientNet-V2 assumptions
4 years ago
Ross Wightman
2b49ab7a36
Fix ResNetV2 pretrained classifier issue. Fixes #540
4 years ago
Ross Wightman
de9dff933a
EfficientNet-V2S preliminary model def (for experimentation)
4 years ago
Ross Wightman
2bb65bd875
Wrong default_cfg pool_size for L1
4 years ago
Ross Wightman
bf2ca6bdf4
Merge jax and original weight init
4 years ago
Ross Wightman
acbd698c83
Update README.md with updates. Small tweak to head_dist handling.
4 years ago
Ross Wightman
9071568f0e
Add weights for SE NFNet-L0 model, rename nfnet_l0b -> nfnet_l0. 82.75 top-1 @ 288. Add nfnet_l1 model def for training.
4 years ago
Ross Wightman
c468c47a9c
Add regnety_160 weights from DeiT teacher model, update that and my regnety_032 weights to use higher test size.
4 years ago
Ross Wightman
288682796f
Update benchmark script to add precision arg. Fix some downstream (DeiT) compat issues with latest changes. Bump version to 0.4.7
4 years ago
Ross Wightman
ea9c9550b2
Fully move ViT hybrids to their own file, including embedding module. Remove some extra DeiT models that were for benchmarking only.
4 years ago
Ross Wightman
a5310a3451
Merge remote-tracking branch 'origin/benchmark-fixes-vit_hybrids' into pit_and_vit_update
4 years ago
Ross Wightman
7953e5d11a
Fix pos_embed scaling for ViT and num_classes != 1000 for pretrained distilled deit and pit models. Fix #426 and fix #433
4 years ago
Ross Wightman
a760a4c3f4
Some ViT cleanup, merge distilled model with main, fixup torchscript support for distilled models
4 years ago
Ross Wightman
0dfc5a66bb
Add PiT model from https://github.com/naver-ai/pit
4 years ago
Ross Wightman
51febd869b
Small tweak to tests for tnt model, reorder model imports.
4 years ago
contrastive
de86314655
Update TNT
4 years ago
contrastive
cfc15283a4
Update TNT url
4 years ago
contrastive
4a09bc851e
Add TNT model
4 years ago
Ross Wightman
cf5fec5047
Cleanup experimental vit weight init a bit
4 years ago
Ross Wightman
cbcb76d72c
Should have included Conv2d layers in original weight init. Lets see what the impact is...
4 years ago
Ross Wightman
4de57ccf01
Add weight init scheme that's closer to JAX impl
4 years ago
Ross Wightman
14ac4abf74
Change huggingface hub revision delimiter to '@', add hf_hub reference for eca_nfnet_l0 model as an example.
4 years ago
Ross Wightman
740f32c96a
Add ECA-NFNet-L0 weights and update model name. Update README and bump version to 0.4.6
4 years ago
Ross Wightman
5e2e4e7fb6
Merge pull request #502 from khatami-mehrdad/efficientnet_dg
...
adding efficientnet_el, efficientnet_es_pruned and efficientnet_el_pruned pre-trained models
4 years ago
Ross Wightman
45c048ba13
A few minor fixes and bit more cleanup on the huggingface hub integration.
4 years ago
Mehrdad
97f49d163c
adding efficientnet_el, efficientnet_es_prunedefficientnet_es_pruned and efficientnet_el_pruned pretrained models to timm/models
4 years ago
Ross Wightman
ead80d33c5
Fix typo, naming consistency
4 years ago
Ross Wightman
d584e7f617
Support for huggingface hub via create_model and default_cfgs.
...
* improve consistency of model creation helper fns
* add comments to some of the model helpers
* support passing external default_cfgs so they can be sourced from hub
4 years ago
Ross Wightman
1f799afcb3
Remove capital letters in model names
4 years ago
AFLALO, Jonathan Isaac
82c1fe958a
added hardcorenas model
...
refactoring to support feature extraction
4 years ago
Ross Wightman
f57db99101
Update README, fix iabn pip version print.
4 years ago
Ross Wightman
7ef7788ee9
Fix CUDA crash w/ channels-last + CSP models. Remove use of chunk()
4 years ago
Ross Wightman
317ea3e599
Tweak NFNet, ResNetV2, RexNet feature extraction, use pre-act features for simplicty. Update tests for pytorch 1.8. 0.4.5 version bump.
4 years ago
Ross Wightman
17cdee7354
Fix C&P patch_size error, and order of op patch_size arg resolution bug. Remove a test vit model.
4 years ago
Ross Wightman
0706d05d52
Benchmark models listed in txt file. Add more hybrid vit variants for testing
4 years ago
Ross Wightman
de97be9146
Spell out diff between my small and deit small vit models.
4 years ago
Ross Wightman
f0ffdf89b3
Add numerous experimental ViT Hybrid models w/ ResNetV2 base. Update the ViT naming for hybrids. Fix #426 for pretrained vit resizing.
4 years ago
Ross Wightman
4bc103f504
Fix CUDA crash w/ channels-last + CSP models. Remove use of chunk()
4 years ago
Ross Wightman
8563609b28
Update notes in ScaledStdConv impl
4 years ago
Ross Wightman
678ba4e0a2
Add NFNet-F model weights ported from DeepMind Haiku impl and new set of models w/ compatible config.
4 years ago
Ross Wightman
4f49b94311
Initial AGC impl. Still testing.
4 years ago
Ross Wightman
5f9aff395c
Fix stem width in NFNet-F models, add some more comments, add some 'light' NFNet models for testing.
4 years ago
Ross Wightman
d86dbe45c2
Update README.md and few more comments
4 years ago
Ross Wightman
0d253e2c5e
Fix issue with nfnet tests, bit more cleanup.
4 years ago
Ross Wightman
cb06c7a910
Add NFNet-F models and tweak existing NF models.
4 years ago
Ross Wightman
e4de077021
Add first 'Normalizer Free' models. nf_regnet_b1 79.3 @ 288x288 test, and nf_resnet50 80.3 @ 256x256 test (80.68 @ 288x288).
4 years ago
Ross Wightman
d8e69206be
Merge pull request #419 from rwightman/byob_vgg_models
...
More models, GPU-Efficient Nets, RepVGG, classic VGG, and flexible Byob backbone.
4 years ago
Ross Wightman
6853b07bbd
Improve RegVGG block identity/vs non for clariy and fix attn usage. Add comments.
4 years ago
Ross Wightman
0356e773f5
Default to native PyTorch AMP instead of APEX amp. Too many APEX issues cropping up lately.
4 years ago
Reuben
94ca140b67
update collections.abc import
4 years ago
Ross Wightman
b4e216e377
Fix a few small things.
4 years ago
Ross Wightman
dc85e5a237
Add ByobNet w/ GPU-EfficientNets and RepVGG. Also add classic vgg models.
4 years ago
Ross Wightman
1bcc69e0ad
Use in_channels for depthwise groups, allows using `out_channels=N * in_channels` (does not impact existing models). Fix #354 .
4 years ago
Ross Wightman
9811e229f7
Fix regression in models with 1001 class pretrained weights. Improve batchnorm arg and BatchNormAct layer handling in several models.
4 years ago
Ross Wightman
a39c3ee216
Merge branch 'master' into eca-weights
4 years ago
Ross Wightman
666de85cf1
Move stride in EdgeResidual block to 3x3 expansion conv. Fix #414
4 years ago
Ross Wightman
3b57490a63
Fix some half removed resnet model defs, pooling for ecaresnet269d
4 years ago
Ross Wightman
68a4144882
Add new weights for ecaresnet26t/50t/269d models. Remove distinction between 't' and 'tn' (tiered models), tn is now t. Add test time img size spec to default cfg.
4 years ago
Ross Wightman
b9843f954b
Merge pull request #282 from tigert1998/patch-1
...
Add symbolic for SwishJitAutoFn to support onnx
4 years ago
hwangdeyu
7a4be5c035
add operator HardSwishJitAutoFn export to onnx
4 years ago
Ross Wightman
f0e65e37b7
Fix NF-ResNet101 model defs
4 years ago
Ross Wightman
2de54d174a
Fix pool size defs for NFNet models, add a comment.
4 years ago
Ross Wightman
90980de4a9
Fix up a few details in NFResNet models, managed stable training. Add support for gamma gain to be applied in activation or ScaleStdConv. Some tweaks to ScaledStdConv.
4 years ago
Ross Wightman
5a8e1e643e
Initial Normalizer-Free Reg/ResNet impl. A bit of related layer refactoring.
4 years ago
Ross Wightman
38d8f67570
Fix potential issue with change to num_classes arg in train/validate.py defaulting to None (rely on model def / default_cfg)
4 years ago
Ross Wightman
bb50ac4708
Add DeiT distilled weights and distilled model def. Remove some redudant ViT model args.
4 years ago
Ross Wightman
c16e965037
Add some ViT comments and fix a few minor issues.
4 years ago
Ross Wightman
22748f1a2d
Convert samples/targets in ParserImageInTar to numpy arrays, slightly less mem usage for massive datasets. Add a few more se/eca model defs to resnet.py
4 years ago
Ross Wightman
55f7dfa9ea
Refactor vision_transformer entrpy fns, add pos embedding resize support for fine tuning, add some deit models for testing
4 years ago
Ross Wightman
d55bcc0fee
Finishing adding stochastic depth support to BiT ResNetV2 models
4 years ago
Ross Wightman
855d6cc217
More dataset work including factories and a tensorflow datasets (TFDS) wrapper
...
* Add parser/dataset factory methods for more flexible dataset & parser creation
* Add dataset parser that wraps TFDS image classification datasets
* Tweak num_classes handling bug for 21k models
* Add initial deit models so they can be benchmarked in next csv results runs
4 years ago
Ross Wightman
20516abc18
Fix some broken tests for ResNetV2 BiT models
4 years ago
Ross Wightman
59ec7e6a53
Merge branch 'master' into imagenet21k_datasets_more
4 years ago
Ross Wightman
4e2533db77
Add 320x320 model default cfgs for 101D and 152D ResNets. Add SEResNet-152D weights and 320x320 cfg.
4 years ago
Ross Wightman
0167f749d3
Remove some old __future__ imports
4 years ago
Ross Wightman
ce69de70d3
Add 21k weight urls to vision_transformer. Cleanup feature_info for preact ResNetV2 (BiT) models
4 years ago
Ross Wightman
231d04e91a
ResNetV2 pre-act and non-preact model, w/ BiT pretrained weights and support for ViT R50 model. Tweaks for in21k num_classes passing. More to do... tests failing.
4 years ago
Ross Wightman
392595c7eb
Add pool_size to default cfgs for new models to prevent tests from failing. Add explicit 200D_320 model entrypoint for next benchmark run.
4 years ago
Ross Wightman
b1f1228a41
Add ResNet101D, 152D, and 200D weights, remove meh 66d model
4 years ago
Ross Wightman
cd72e66eff
Bug in last mod for features_only default_cfg
4 years ago
Ross Wightman
867a0e5a04
Add default_cfg back to models wrapped in feature extraction module as per discussion in #294 .
4 years ago
Ross Wightman
2ed8f24715
A few more changes for 0.3.2 maint release. Linear layer change for mobilenetv3 and inception_v3, support no bias for linear wrapper.
4 years ago
Ross Wightman
460eba7f24
Work around casting issue with combination of native torch AMP and torchscript for Linear layers
4 years ago
Ross Wightman
5f4b6076d8
Fix inplace arg compat for GELU and PreLU via activation factory
4 years ago
Ross Wightman
fd962c4b4a
Native SiLU (Swish) op doesn't export to ONNX
4 years ago
tigertang
43f2500c26
Add symbolic for SwishJitAutoFn to support onnx
4 years ago