766b4d3262
Fix features for resnetv2_50t
2021-06-28 15:56:24 -07:00
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.
2021-06-28 10:52:45 -07:00
20a2be14c3
Add gMLP-S weights, 79.6 top-1
2021-06-23 10:40:30 -07:00
85f894e03d
Fix ViT in21k representation (pre_logits) layer handling across old and new npz checkpoints
2021-06-23 10:38:34 -07:00
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
2021-06-22 23:16:05 -07:00
9c9755a808
AugReg release
2021-06-20 17:46:06 -07:00
381b279785
Add hybrid model fwds back
2021-06-19 22:28:44 -07:00
26f04a8e3e
Fix a weight link
2021-06-19 16:39:36 -07:00
8f4a0222ed
Add GMixer-24 MLP model weights, trained w/ TPU + PyTorch XLA
2021-06-18 16:49:28 -07:00
4c09a2f169
Bump version 0.4.12
2021-06-18 16:17:34 -07:00
b319eb5b5d
Update ViT weights, more details to be added before merge.
2021-06-18 16:16:49 -07:00
8257b86550
Fix up resnetv2 bit/bitm model default res
2021-06-18 16:16:06 -07:00
1228f5a3d8
Add BiT distilled 50x1 and teacher 152x2 models from 'A good teacher is patient and consistent' paper.
2021-06-18 11:40:33 -07:00
511a8e8c96
Add official ResMLP weights.
2021-06-14 17:03:16 -07:00
b9cfb64412
Support npz custom load for vision transformer hybrid models. Add posembed rescale for npz load.
2021-06-14 12:31:44 -07:00
8319e0c373
Add file docstring to std_conv.py
2021-06-13 12:31:06 -07:00
4d96165989
Merge branch 'master' into cleanup_xla_model_fixes
2021-06-12 23:19:25 -07:00
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
2021-06-12 16:40:02 -07:00
ba2ca4b464
One codepath for stdconv, switch layernorm to batchnorm so gain included. Tweak epsilon values for nfnet, resnetv2, vit hybrid.
2021-06-12 12:27:43 -07:00
b7a568f065
Fix torchscript issue in bat
2021-06-08 23:19:51 -07:00
d17b374f0f
Minimum input_size needed to be higher
2021-06-08 21:31:39 -07:00
b3b90d944d
Add min_input_size to bat_resnext to prevent test breakage.
2021-06-08 17:32:08 -07:00
d413eef1bf
Add ResMLP-24 model weights that I trained in PyTorch XLA on TPU-VM. 79.2 top-1.
2021-06-08 14:22:05 -07:00
10d8fa4620
Add gc and bat attention resnext26ts variants to byob for test.
2021-06-08 14:21:07 -07:00
2f5ed2dec1
Update `init_values` const for 24 and 36 layer ResMLP models
2021-06-07 17:15:04 -07:00
8e4ac3549f
All ScaledStdConv and StdConv uses default to using F.layernorm so that they work with PyTorch XLA. eps value tweaking is a WIP.
2021-06-07 17:14:19 -07:00
2a63d0246b
Post merge cleanup
2021-06-07 14:38:30 -07:00
45dec179e5
Merge pull request #681 from lmk123568/master
...
Update convit.py
2021-06-07 14:10:53 -07:00
ded1671483
Fix stochastic depth working only with a shortcut
2021-06-07 23:08:55 +09:00
b87d98b238
Update convit.py
...
Cut out the duplicates
2021-06-06 17:58:31 +08:00
02320c3e3d
Bump version to 0.4.11
2021-05-31 15:41:51 -07:00
bda8ab015a
Remove min channels for SelectiveKernel, divisor should cover cases well enough.
2021-05-31 15:38:56 -07:00
a27f4aec4a
Missed args for skresnext w/ refactoring.
2021-05-31 14:06:34 -07:00
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.
2021-05-31 13:18:11 -07:00
8bf63b6c6c
Able to use other attn layer in EfficientNet now. Create test ECA + GC B0 configs. Make ECA more configurable.
2021-05-30 12:47:02 -07:00
bcec14d3b5
Bring EfficientNet SE layer in line with others, pull se_ratio outside of blocks. Allows swapping w/ other attn layers.
2021-05-29 23:41:38 -07:00
9611458e19
Throw in some FBNetV3 code I had lying around, some refactoring of SE reduction channel calcs for all EffNet archs.
2021-05-28 20:47:24 -07:00
01b9108619
Merge branch 'master' into more_attn
2021-05-28 11:09:37 -07:00
d7bab8a6c5
Fix strict flag change for checkpoint load.
2021-05-28 09:54:50 -07:00
02f9d4bc34
Add weights for resnet51q model, add 61q def.
2021-05-28 09:53:16 -07:00
f615474be3
Fix broken test, repvgg block doesn't have attn_last attr.
2021-05-27 18:12:22 -07:00
742c2d5247
Add Gather-Excite and Global Context attn modules. Refactor existing SE-like attn for consistency and refactor byob/byoanet for less redundancy.
2021-05-27 18:03:29 -07:00
9c78de8c02
Fix #661 , move hardswish out of default args for LeViT. Enable native torch support for hardswish, hardsigmoid, mish if present.
2021-05-26 15:28:42 -07:00
5db7452173
Fix visformer in_chans stem handling
2021-05-25 14:11:36 -07:00
318360c3f9
Update README.md before merge. Bump version to 0.4.10
2021-05-25 12:26:16 -07:00
11ae795e99
Redo LeViT attention bias caching in a way that works with both torchscript and DataParallel
2021-05-25 10:15:32 -07:00
d400f1dbdd
Filter test models before creation for backward/torchscript tests
2021-05-25 10:14:45 -07:00
c4572cc5aa
Add Visformer-small weighs, tweak torchscript jit test img size.
2021-05-24 22:50:12 -07:00
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.
2021-05-24 21:13:26 -07:00
18bf520ad1
Add eca_nfnet_l2/l3 defs for future training
2021-05-22 21:55:37 -07:00
f45de37690
Merge branch 'master' into levit_visformer_rednet
2021-05-22 16:34:31 -07:00
23c18a33e4
Add efficientnetv2_rw_m weights trained in PyTorch. 84.8 top-1 @ 416 test. 53M params.
2021-05-21 21:16:25 -07:00
c2ba229d99
Prep for effcientnetv2_rw_m model weights that started training before official release..
2021-05-21 17:47:49 -07:00
30b9880d06
Minor adjustment, mutable default arg, extra check of valid len...
2021-05-21 17:20:51 -07:00
be0abfbcce
Merge branch 'master' of https://github.com/alexander-soare/pytorch-image-models into alexander-soare-master
2021-05-21 17:10:11 -07:00
b7de82e835
ConViT cleanup, fix torchscript, bit of reformatting, reuse existing layers.
2021-05-21 17:04:23 -07:00
306c86b668
Merge branch 'convit' of https://github.com/amaarora/pytorch-image-models into amaarora-convit
2021-05-21 16:27:10 -07:00
a569635045
Update twin weights to a copy in GitHub releases for faster dl. Tweak model class comment.
2021-05-21 16:23:14 -07:00
be99eef9c1
Remove redundant code, cleanup, fix torchscript.
2021-05-20 23:38:35 -07:00
5ab372a3ec
Merge branch 'master' of https://github.com/abcdvzz/pytorch-image-models into abcdvzz-master
2021-05-20 23:37:50 -07:00
5db1eb6ba5
Add defaults
2021-05-21 02:11:20 +00:00
8b1f2e8e1f
remote unused matplotlib import
2021-05-20 23:42:42 +00:00
40c506ba1e
Add ConViT
2021-05-20 23:17:28 +00:00
7976019864
extend positional embedding resizing functionality to tnt
2021-05-20 11:55:48 +01:00
8086943b6f
allow resize positional embeddings to non-square grid
2021-05-20 11:27:58 +01:00
dc1a4efd28
mixer_b16_224_miil, mixer_b16_224_miil_in21k models
2021-05-20 10:35:50 +03:00
7b799c4e79
add latest code
2021-05-20 11:15:49 +08:00
d5af752117
Add preliminary gMLP and ResMLP impl to Mlp-Mixer
2021-05-19 09:55:05 -07:00
00548b8427
Add Twins
2021-05-18 19:21:53 +08:00
e7f0db8664
Fix drop/drop_path arg on MLP-Mixer model. Fix #641
2021-05-16 08:31:52 -07:00
9a3ae97311
Another set of byoanet models w/ ECA channel + SA + groups
2021-05-15 22:56:51 -07:00
d53e91218e
Fix tf.data options setting for newer TF versions
2021-05-15 22:56:12 -07:00
7077f16c6a
Change 21k model naming from _21k to _in21k for consistency with existing 21k models.
2021-05-15 12:42:26 -07:00
94d4b53352
Add temporary default_cfgs to visformer models so they pass tests
2021-05-15 08:41:31 -07:00
3bffc701f1
Merge branch 'master' into levit_visformer_rednet
2021-05-14 23:02:12 -07:00
ecc7552c5c
Add levit, levit_c, and visformer model defs. Largely untested and not finished cleanup.
2021-05-14 17:16:34 -07:00
165fb354b2
Add initial RedNet model / Involution layer impl for testing
2021-05-14 17:16:34 -07:00
328249f11a
Update README, tweak fine-tune effv2 model names.
2021-05-14 16:37:43 -07:00
c4f482a08b
EfficientNetV2 official impl w/ weights ported from TF. Cleanup/refactor of related EfficientNet classes and models.
2021-05-14 15:50:00 -07:00
4fbc32d3d0
Fix crop_pct for cait models.
2021-05-11 10:50:15 -07:00
715519a5ef
Rethink name of patch embed grid info
2021-05-06 14:08:20 -07:00
b2c305c2aa
Move Mlp and PatchEmbed modules into layers. Being used in lots of models now...
2021-05-06 14:03:23 -07:00
3ba6b55cb2
More adjustments to ByoaNet models for further experiments.
2021-05-06 13:59:44 -07:00
5fcddb96a8
Merge branch 'master' into cait
2021-05-05 17:29:38 -07:00
3db12b4b6a
Finish CaiT cleanup
2021-05-05 17:28:19 -07:00
2d8b09fe8b
Add official pretrained weights to MLP-Mixer, complete model cfgs.
2021-05-05 15:59:40 -07:00
12efffa6b1
Initial MLP-Mixer attempt...
2021-05-05 00:59:45 -07:00
0721559511
Improved (hopefully) init for SA/SA-like layers used in ByoaNets
2021-05-04 21:40:39 -07:00
d5473c17f7
Fix incorrect name of shortcut/identity paths in many residual nets. Inherited from naming in old old torchvision, long fixed there.
2021-05-04 21:27:15 -07:00
0d87650fea
Remove filter hack from BlurPool w/ non-persistent buffer. Use BlurPool2d instead of AntiAliasing.. for TResNet. Breaks PyTorch < 1.6.
2021-05-04 16:56:28 -07:00
ddc743fdf8
Update ResNet-RS models to EMA weights
2021-05-04 16:16:55 -07:00
08d60f4a9a
resnetrs50 pool sizing wrong
2021-05-04 12:41:09 -07:00
1daa15ecc3
Initial Cait commit. Still some cleanup to do.
2021-05-04 11:19:27 -07:00
67d0665b46
Post ResNet-RS merge cleanup. Add weight urls, adjust train/test/crop pct.
2021-05-04 11:04:23 -07:00
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
2021-05-04 10:59:44 -07:00
9cc7dda6e5
Fixup byoanet configs to pass unit tests. Add swin_attn and swinnet26t model for testing.
2021-04-29 21:08:37 -07:00
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.
2021-04-29 10:58:49 -07:00
e5e15754c9
Fix coat first conv ident
2021-04-28 18:09:23 -07:00
76739a7589
CoaT merge. Bit of formatting, fix torchscript (for non features), remove einops/einsum dep, add pretrained weight hub (url) support.
2021-04-28 16:31:35 -07:00
026430c083
Merge branch 'master' of https://github.com/morizin/pytorch-image-models-1 into morizin-master
2021-04-28 11:24:27 -07:00
a0492e3b48
A few miil weights naming tweaks to improve compat with model registry and filtering wildcards.
2021-04-28 10:33:02 -07:00
8c1f03e56c
comment
2021-04-28 09:04:10 +03:00
19e1b67a84
old spaces
2021-04-28 09:01:29 +03:00
a443865876
update naming and scores
2021-04-28 08:57:06 +03:00
cf0e371594
84_0
2021-04-27 22:33:55 +03:00
0968bdeca3
vit, tresnet and mobilenetV3 ImageNet-21K-P weights
2021-04-27 20:54:06 +03:00
1e3b6d4dfc
Update __init__.py
2021-04-24 18:22:59 +05:30
fd022fd6a2
Update __init__.py
2021-04-24 18:22:36 +05:30
c2d5087eae
Add files via upload
2021-04-24 17:47:57 +05:30
79640fcc1f
Enable uniform augmentation magnitude sampling and set AugMix default
2021-04-19 14:21:12 -07:00
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.
2021-04-19 10:42:56 -07:00
e8a64fb881
Test input size for efficientnet_v2s was wrong in last results run
2021-04-17 16:17:41 -07:00
2df77ee5cb
Fix torchscript compat and features_only behaviour in GhostNet PR. A few minor formatting changes. Reuse existing layers.
2021-04-15 10:20:26 -07:00
d793deb51a
Merge branch 'master' of https://github.com/iamhankai/pytorch-image-models into iamhankai-master
2021-04-15 09:30:25 -07:00
e685618f45
Merge pull request #550 from amaarora/wandb
...
Wandb Support
2021-04-15 09:26:35 -07:00
f606c45c38
Add Swin Transformer models from https://github.com/microsoft/Swin-Transformer
2021-04-13 12:17:21 -07:00
de445e7827
Add GhostNet
2021-04-13 23:19:51 +08:00
5a196dddf6
Update README.md with latest, bump version to 0.4.8
2021-04-12 13:15:00 -07:00
b3d7580df1
Update ByoaNet comments. Fix first Steam feat chs for ByobNet.
2021-04-12 12:11:35 -07:00
16f7aa9f54
Add default_cfg options for min_input_size / fixed_input_size, queries in model registry, and use for testing self-attn models
2021-04-12 11:54:22 -07:00
4e4b863b15
Missed norm.py
2021-04-12 09:57:56 -07:00
7c97e66f7c
Remove commented code, add more consistent seed fn
2021-04-12 09:51:36 -07:00
364dd6a58e
Merge branch 'master' into byoanet-self_attn
2021-04-12 09:38:59 -07:00
ce62f96d4d
ByoaNet with bottleneck transformer, lambda resnet, and halo net experiments
2021-04-12 09:38:02 -07:00
cd3dc4979f
Fix adabelief imports, remove prints, preserve memory format is the default arg for zeros_like
2021-04-12 08:25:31 -07:00
21812d33aa
Add prelim efficientnet_v2s weights from 224x224 train, eval 83.3 @ 288. Add eca_nfnet_l1 weights, train at 256, eval 84 @ 320.
2021-04-11 23:26:13 -07:00
5772c55c57
Make wandb optional
2021-04-10 01:34:20 -04:00
f54897cc0b
make wandb not required but rather optional as huggingface_hub
2021-04-10 01:27:23 -04:00
3f028ebc0f
import wandb in summary.py
2021-04-08 03:48:51 -04:00
624c9b6949
log to wandb only if using using wandb
2021-04-08 03:40:22 -04:00
addfc7c1ac
adabelief
2021-04-04 23:48:15 -04:00
fb896c0b26
Update some comments re preliminary EfficientNet-V2 assumptions
2021-04-03 12:00:25 -07:00
2b49ab7a36
Fix ResNetV2 pretrained classifier issue. Fixes #540
2021-04-03 11:18:12 -07:00
de9dff933a
EfficientNet-V2S preliminary model def (for experimentation)
2021-04-02 09:36:51 -07:00
37c71a5609
Some further create_optimizer_v2 tweaks, remove some redudnant code, add back safe model str. Benchmark step times per batch.
2021-04-01 22:34:55 -07:00
2bb65bd875
Wrong default_cfg pool_size for L1
2021-04-01 20:00:41 -07:00
bf2ca6bdf4
Merge jax and original weight init
2021-04-01 18:11:51 -07:00
acbd698c83
Update README.md with updates. Small tweak to head_dist handling.
2021-04-01 17:49:05 -07:00
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.
2021-04-01 17:22:27 -07:00
c468c47a9c
Add regnety_160 weights from DeiT teacher model, update that and my regnety_032 weights to use higher test size.
2021-04-01 16:41:04 -07:00
288682796f
Update benchmark script to add precision arg. Fix some downstream (DeiT) compat issues with latest changes. Bump version to 0.4.7
2021-04-01 16:40:12 -07:00
ea9c9550b2
Fully move ViT hybrids to their own file, including embedding module. Remove some extra DeiT models that were for benchmarking only.
2021-04-01 14:17:38 -07:00
a5310a3451
Merge remote-tracking branch 'origin/benchmark-fixes-vit_hybrids' into pit_and_vit_update
2021-04-01 12:15:34 -07:00
7953e5d11a
Fix pos_embed scaling for ViT and num_classes != 1000 for pretrained distilled deit and pit models. Fix #426 and fix #433
2021-03-31 23:11:28 -07:00
a760a4c3f4
Some ViT cleanup, merge distilled model with main, fixup torchscript support for distilled models
2021-03-31 18:21:02 -07:00
0dfc5a66bb
Add PiT model from https://github.com/naver-ai/pit
2021-03-31 18:20:14 -07:00
51febd869b
Small tweak to tests for tnt model, reorder model imports.
2021-03-29 11:33:08 -07:00
b27a4e0d88
Merge branch 'master' of https://github.com/contrastive/pytorch-image-models into contrastive-master
2021-03-29 10:37:05 -07:00
6b18061773
Add GIST to docstring for quick access
2021-03-29 15:33:31 +11:00
de86314655
Update TNT
2021-03-29 08:23:34 +08:00
92b1db9a79
update docstrings and add check on and
2021-03-29 10:04:51 +11:00
b85be24054
update to work with fnmatch
2021-03-29 09:36:31 +11:00
cfc15283a4
Update TNT url
2021-03-28 23:19:15 +08:00
4a09bc851e
Add TNT model
2021-03-28 19:53:42 +08:00
20626e8387
Add to extract stats for SPP
2021-03-27 05:40:04 +11:00
cf5fec5047
Cleanup experimental vit weight init a bit
2021-03-20 09:44:24 -07:00
f42f1df26c
Improve evenness of per-worker split for validation set with TFDS
2021-03-18 23:16:14 -07:00
cbcb76d72c
Should have included Conv2d layers in original weight init. Lets see what the impact is...
2021-03-18 23:15:48 -07:00
4de57ccf01
Add weight init scheme that's closer to JAX impl
2021-03-18 15:35:22 -07:00
14ac4abf74
Change huggingface hub revision delimiter to '@', add hf_hub reference for eca_nfnet_l0 model as an example.
2021-03-18 11:38:06 -07:00
740f32c96a
Add ECA-NFNet-L0 weights and update model name. Update README and bump version to 0.4.6
2021-03-17 13:55:32 -07:00
5e2e4e7fb6
Merge pull request #502 from khatami-mehrdad/efficientnet_dg
...
adding efficientnet_el, efficientnet_es_pruned and efficientnet_el_pruned pre-trained models
2021-03-17 13:35:22 -07:00
45c048ba13
A few minor fixes and bit more cleanup on the huggingface hub integration.
2021-03-17 13:18:52 -07:00
97f49d163c
adding efficientnet_el, efficientnet_es_prunedefficientnet_es_pruned and efficientnet_el_pruned pretrained models to timm/models
2021-03-17 10:51:51 -07:00
ead80d33c5
Fix typo, naming consistency
2021-03-16 23:02:51 -07:00
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
2021-03-16 22:48:26 -07:00
1f799afcb3
Remove capital letters in model names
2021-03-15 10:20:34 -07:00
82c1fe958a
added hardcorenas model
...
refactoring to support feature extraction
2021-03-15 08:06:34 +02:00
f57db99101
Update README, fix iabn pip version print.
2021-03-07 16:17:06 -08:00
7ef7788ee9
Fix CUDA crash w/ channels-last + CSP models. Remove use of chunk()
2021-03-06 16:56:34 -08:00
317ea3e599
Tweak NFNet, ResNetV2, RexNet feature extraction, use pre-act features for simplicty. Update tests for pytorch 1.8. 0.4.5 version bump.
2021-03-06 12:48:06 -08:00
17cdee7354
Fix C&P patch_size error, and order of op patch_size arg resolution bug. Remove a test vit model.
2021-03-01 16:53:32 -08:00
0706d05d52
Benchmark models listed in txt file. Add more hybrid vit variants for testing
2021-02-28 16:00:33 -08:00
2db2d87ff7
Add epoch-repeats arg to multiply the number of dataset passes per epoch. Currently for iterable datasets (read TFDS wrapper) only.
2021-02-23 17:31:42 -08:00
de97be9146
Spell out diff between my small and deit small vit models.
2021-02-23 16:22:55 -08:00
f0ffdf89b3
Add numerous experimental ViT Hybrid models w/ ResNetV2 base. Update the ViT naming for hybrids. Fix #426 for pretrained vit resizing.
2021-02-23 15:54:55 -08:00
0e16d4e9fb
Add benchmark.py script, and update optimizer factory to be more friendly to use outside of argparse interface.
2021-02-23 15:38:12 -08:00
4bc103f504
Fix CUDA crash w/ channels-last + CSP models. Remove use of chunk()
2021-02-23 13:15:52 -08:00
8563609b28
Update notes in ScaledStdConv impl
2021-02-18 12:44:08 -08:00
678ba4e0a2
Add NFNet-F model weights ported from DeepMind Haiku impl and new set of models w/ compatible config.
2021-02-18 12:28:46 -08:00
9de2ec5e44
Update README for AGC and bump version to 0.4.4
2021-02-16 09:13:03 -08:00
4f49b94311
Initial AGC impl. Still testing.
2021-02-15 23:22:44 -08:00
5f9aff395c
Fix stem width in NFNet-F models, add some more comments, add some 'light' NFNet models for testing.
2021-02-13 16:58:51 -08:00
d86dbe45c2
Update README.md and few more comments
2021-02-12 22:07:18 -08:00
0d253e2c5e
Fix issue with nfnet tests, bit more cleanup.
2021-02-12 21:05:41 -08:00
cb06c7a910
Add NFNet-F models and tweak existing NF models.
2021-02-12 18:28:56 -08:00
e4de077021
Add first 'Normalizer Free' models. nf_regnet_b1 79.3 @ 288x288 test, and nf_resnet50 80.3 @ 256x256 test (80.68 @ 288x288).
2021-02-11 13:20:11 -08:00
d8e69206be
Merge pull request #419 from rwightman/byob_vgg_models
...
More models, GPU-Efficient Nets, RepVGG, classic VGG, and flexible Byob backbone.
2021-02-10 15:44:09 -08:00
ca9b078ac7
Update README.md and docs. Version bumped to 0.4.3
2021-02-10 14:46:07 -08:00
6853b07bbd
Improve RegVGG block identity/vs non for clariy and fix attn usage. Add comments.
2021-02-10 14:40:29 -08:00
0356e773f5
Default to native PyTorch AMP instead of APEX amp. Too many APEX issues cropping up lately.
2021-02-10 14:31:18 -08:00
94ca140b67
update collections.abc import
2021-02-10 23:54:35 +11:00
b4e216e377
Fix a few small things.
2021-02-09 17:33:43 -08:00
dc85e5a237
Add ByobNet w/ GPU-EfficientNets and RepVGG. Also add classic vgg models.
2021-02-09 16:22:52 -08:00
1bcc69e0ad
Use in_channels for depthwise groups, allows using `out_channels=N * in_channels` (does not impact existing models). Fix #354 .
2021-02-09 16:22:52 -08:00
9811e229f7
Fix regression in models with 1001 class pretrained weights. Improve batchnorm arg and BatchNormAct layer handling in several models.
2021-02-09 16:22:52 -08:00
a39c3ee216
Merge branch 'master' into eca-weights
2021-02-08 11:52:31 -08:00
e9d6fe293c
Update README for new weights. Version 0.4.2
2021-02-08 11:51:16 -08:00
666de85cf1
Move stride in EdgeResidual block to 3x3 expansion conv. Fix #414
2021-02-07 22:10:18 -08:00
3b57490a63
Fix some half removed resnet model defs, pooling for ecaresnet269d
2021-02-07 22:09:25 -08:00
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.
2021-02-06 16:30:02 -08:00
b9843f954b
Merge pull request #282 from tigert1998/patch-1
...
Add symbolic for SwishJitAutoFn to support onnx
2021-02-04 12:18:40 -08:00
7a4be5c035
add operator HardSwishJitAutoFn export to onnx
2021-02-03 09:06:53 +08:00
4203efa36d
Fix #387 so that checkpoint saver works with max history of 1. Add checkpoint-hist arg to train.py.
2021-01-31 20:14:51 -08:00
f0e65e37b7
Fix NF-ResNet101 model defs
2021-01-30 23:26:19 -08:00
2c988c3b6e
Update README.md for NF-nets, bump version to 0.4.1 for merge
2021-01-30 23:19:45 -08:00
2de54d174a
Fix pool size defs for NFNet models, add a comment.
2021-01-30 18:02:33 -08:00
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.
2021-01-30 16:32:07 -08:00
5a8e1e643e
Initial Normalizer-Free Reg/ResNet impl. A bit of related layer refactoring.
2021-01-27 22:06:57 -08:00
38d8f67570
Fix potential issue with change to num_classes arg in train/validate.py defaulting to None (rely on model def / default_cfg)
2021-01-25 11:53:34 -08:00
587780e56b
Update README.md and bump version to 0.4.0
2021-01-25 11:22:11 -08:00
bb50ac4708
Add DeiT distilled weights and distilled model def. Remove some redudant ViT model args.
2021-01-25 11:05:23 -08:00
c16e965037
Add some ViT comments and fix a few minor issues.
2021-01-24 23:18:35 -08:00
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
2021-01-22 16:54:33 -08:00
5d4c3d0af3
Add enhanced ParserImageInTar that can read images from tars within tars, folders with multiple tars, etc. Additional comment cleanup.
2021-01-22 10:52:04 -08:00
55f7dfa9ea
Refactor vision_transformer entrpy fns, add pos embedding resize support for fine tuning, add some deit models for testing
2021-01-18 16:11:02 -08:00
d55bcc0fee
Finishing adding stochastic depth support to BiT ResNetV2 models
2021-01-16 16:32:03 -08:00
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
2021-01-15 17:26:20 -08:00
20516abc18
Fix some broken tests for ResNetV2 BiT models
2021-01-04 23:21:39 -08:00
59ec7e6a53
Merge branch 'master' into imagenet21k_datasets_more
2021-01-04 12:11:05 -08:00
e7a9ddf982
Merge pull request #334 from kecsap/links
...
Follow symbolic links during dataset scanning
2021-01-04 10:30:58 -08:00
7cae7e7035
Follow links during dataset scanning
2021-01-04 00:16:45 +02:00
c96e9f99a0
Update version to 0.3.3
2021-01-03 12:43:44 -08:00
4e2533db77
Add 320x320 model default cfgs for 101D and 152D ResNets. Add SEResNet-152D weights and 320x320 cfg.
2021-01-03 12:10:25 -08:00
0167f749d3
Remove some old __future__ imports
2021-01-03 11:24:16 -08:00
e35e9760a6
More work on dataset / parser split and imagenet21k (tar) support
2020-12-28 16:59:15 -08:00
ce69de70d3
Add 21k weight urls to vision_transformer. Cleanup feature_info for preact ResNetV2 (BiT) models
2020-12-28 16:59:15 -08:00
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.
2020-12-28 16:59:15 -08:00
de6046e213
Initial commit for dataset / parser reorg to support additional datasets / types
2020-12-28 16:59:15 -08:00
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.
2020-12-18 21:28:47 -08:00
b1f1228a41
Add ResNet101D, 152D, and 200D weights, remove meh 66d model
2020-12-18 17:13:37 -08:00
7c56c718f3
Configure create_optimizer with args.opt_args
...
Closes #301
2020-12-08 00:03:09 -06:00
9a25fdf3ad
Merge pull request #297 from rwightman/ema_simplify
...
Simplified JIT compatible Ema module. Fixes for SiLU export and torchscript training w/ Linear layer.
2020-12-05 11:42:45 -08:00
de15b43865
Fix a bug with accuracy retrieving from RealLabels
2020-12-04 16:12:50 +01:00
cd72e66eff
Bug in last mod for features_only default_cfg
2020-12-03 12:33:01 -08:00
867a0e5a04
Add default_cfg back to models wrapped in feature extraction module as per discussion in #294 .
2020-12-03 10:24:35 -08:00
4ca52d73d8
Add separate set and update method to ModelEmaV2
2020-12-03 10:05:09 -08:00
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.
2020-11-30 16:19:52 -08:00
6504a42832
Version 0.3.2
2020-11-30 13:39:08 -08:00
460eba7f24
Work around casting issue with combination of native torch AMP and torchscript for Linear layers
2020-11-30 13:30:51 -08:00
5f4b6076d8
Fix inplace arg compat for GELU and PreLU via activation factory
2020-11-30 13:27:40 -08:00
fd962c4b4a
Native SiLU (Swish) op doesn't export to ONNX
2020-11-29 21:56:55 -08:00
27bbc70d71
Add back old ModelEma and rename new one to ModelEmaV2 to avoid compat breaks in dependant code. Shuffle train script, add a few comments, remove DataParallel support, support experimental torchscript training.
2020-11-29 16:22:19 -08:00
43f2500c26
Add symbolic for SwishJitAutoFn to support onnx
2020-11-18 14:36:12 +08:00
9214ca0716
Simplifying EMA...
2020-11-16 12:51:52 -08:00
53aeed3499
ver 0.3.1
2020-10-31 18:14:58 -07:00
30ab4a1494
Fix issue in optim factory with sgd / eps flag. Bump version to 0.3.1
2020-10-31 18:05:30 -07:00
741572dc9d
Bump version to 0.3.0 for pending PyPi push
2020-10-29 17:31:39 -07:00
b401952caf
Add newly added vision transformer large/base 224x224 weights ported from JAX official repo
2020-10-29 17:31:01 -07:00
61200db0ab
in_chans=1 working w/ pretrained weights for vision_transformer
2020-10-29 15:49:36 -07:00
Ross Wightman
Ross Wightman
Dongyoon Han
Mike
Aman Arora
Alexander Soare
talrid
李鑫杰
Aman Arora
morizin
Norman Mu
iamhankai
juntang
contrastive
Mehrdad
AFLALO, Jonathan Isaac
Reuben
hwangdeyu
Csaba Kertesz
Jasha
Tymoteusz Wiśniewski
tigertang