b328e56f49
Update eca_halonext26ts weights to a better set
3 years ago
2ddef942b9
Better fix for #954 that doesn't break torchscript, pull torch._assert into timm namespace when it exists
3 years ago
4f0f9cb348
Fix #954 by bringing traceable _assert into timm to allow compat w/ PyTorch < 1.8
3 years ago
a41de1f666
Add interpolation mode handling to transforms. Removes InterpolationMode warning. Works for torchvision versions w/ and w/o InterpolationMode enum. Fix #738 .
3 years ago
ed41d32637
Add repr to auto_augment and random_erasing impl
3 years ago
ae72d009fa
Add weights for lambda_resnet50ts, halo2botnet50ts, lamhalobotnet50ts, updated halonet50ts
3 years ago
a45186a6e8
Merge remote-tracking branch 'origin/master' into bits_and_tpu
3 years ago
b745d30a3e
Fix formatting of last commit
3 years ago
3478f1d7f1
Traceability fix for vit models for some experiments
3 years ago
f658a72e72
Cleanup re-use of Dropout modules in Mlp modules after some twitter feedback :p
3 years ago
f805ba86d9
use .unbind instead of explicitly listing the indices
3 years ago
57992509f9
Fix some formatting in utils/model.py
3 years ago
0fe4fd3f1f
add d8 and e8 regnetz models with group size 8
3 years ago
690f31d02d
Post merge cleanup, restore previous unwrap fn
3 years ago
3b6ba76126
Merge remote-tracking branch 'origin/master' into bits_and_tpu
3 years ago
25e7c8c5e5
Update broken resnetv2_50 weight url, add resnetv1_101 a1h recipe weights for 224x224 train
3 years ago
b6caa356d2
Fixed eca_botnext26ts_256 weights added, 79.27
3 years ago
c02334d9fa
Add weights for regnetz_d and haloregnetz_c, update regnetz_c weights. Add commented PyTorch XLA code for halo attention
3 years ago
02daf2ab94
Add option to include relative pos embedding in the attention scaling as per references. See discussion #912
3 years ago
047a5ec05f
Fix bugs that Mixup does not work device=cpu
3 years ago
cd34913278
Remove some outdated comments, botnet networks working great now.
3 years ago
6ed4cdccca
Update lambda_resnet26t weights with better set
3 years ago
44d6d51668
Add ConvMixer
3 years ago
a85df34993
Update lambda_resnet26rpt weights to 78.9, add better halonet26t weights at 79.1 with tweak to attention dim
3 years ago
b544ad4d3f
regnetz model default cfg tweaks
3 years ago
e5da481073
Small post-merge tweak for freeze/unfreeze, add to __init__ for utils
3 years ago
5ca72dcc75
Merge branch 'freeze-functionality' of https://github.com/alexander-soare/pytorch-image-models into alexander-soare-freeze-functionality
3 years ago
e2b8d44ff0
Halo, bottleneck attn, lambda layer additions and cleanup along w/ experimental model defs
...
* align interfaces of halo, bottleneck attn and lambda layer
* add qk_ratio to all of above, control q/k dim relative to output dim
* add experimental haloregnetz, and trionet (lambda + halo + bottle) models
3 years ago
431e60c83f
Add acknowledgements for freeze_batch_norm inspiration
3 years ago
fbf59c04ee
Change crop ratio on correct resnet50 variant.
3 years ago
ae1ff5792f
Clean a1/a2/3 rsb _0 checkpoints properly, fix v2 loading.
3 years ago
93901e992f
Version bump to 0.5.0 for pending release post RSB and ATTN updates
3 years ago
da0d39bedd
Update default crop_pct for byoanet
3 years ago
cc9bedf373
Add initial ResNet Strikes Back weights for ResNet50 and ResNetV2-50 models
3 years ago
64495505b7
Add updated lambda resnet26 and botnet26 checkpoints with fixes applied
3 years ago
b2094f4ee8
support bits checkpoints in avg/load
3 years ago
007bc39323
Some halo and bottleneck attn code cleanup, add halonet50ts weights, use optimal crop ratios
3 years ago
65c3d78b96
Freeze unfreeze functionality finalized. Tests added
3 years ago
0cb8ea432c
wip
3 years ago
1fdc7af8fd
Merge remote-tracking branch 'origin/fixes_bce_regnet' into bits_and_tpu
3 years ago
b1c2e3eb92
Match rel_pos_indices attr rename in conv branch
3 years ago
b49630a138
Add relative pos embed option to LambdaLayer, fix last transpose/reshape.
3 years ago
d657e2cc0b
Remove dead code line from efficientnet
3 years ago
0ca687f224
Make 'regnetz' model experiments closer to actual RegNetZ, bottleneck expansion, expand from in_chs, no shortcut on stride 2, tweak model sizes
3 years ago
51eaf9360d
Remove a duplicate layer creation in byobnet.py
...
`self.conv2_kxk` is repeated in `byobnet.py`. Remove the duplicate code.
3 years ago
b81e79aae9
Fix bottleneck attn transpose typo, hopefully these train better now..
3 years ago
80075b0b8a
Add worker_seeding arg to allow selecting old vs updated data loader worker seed for (old) experiment repeatability
3 years ago
52c481ea8e
Merge remote-tracking branch 'origin/fixes_bce_regnet' into bits_and_tpu
3 years ago
6478bcd02c
Fix regnetz_d conv layer name, use inception mean/std
3 years ago
25d52ea71d
Merge remote-tracking branch 'origin/fixes_bce_regnet' into bits_and_tpu
3 years ago
0387e6057e
Update binary cross ent impl to use thresholding as an option (convert soft targets from mixup/cutmix to 0, 1)
3 years ago
f8a63a3b71
Add worker_init_fn to loader for numpy seed per worker
3 years ago
515121cca1
Use reshape instead of view in std_conv, causing issues in recent PyTorch in channels_last
3 years ago
da06cc61d4
ResNetV2 seems to work best without zero_init residual
3 years ago
8e11da0ce3
Add experimental RegNetZ(ish) models for training / perf trials.
3 years ago
6bbc50beb4
make it possible to provide norm_layer via create_model
3 years ago
adcb74f87f
🎨 Import load_state_dict_from_url directly
3 years ago
e65a2cba3d
🎨 cleanup and add a couple comments
3 years ago
2b6ade24b3
🎨 write model card to enable inference
3 years ago
cf5ac2800c
BotNet models were still off, remove weights for bad configs. Add good SE-HaloNet33-TS weights.
3 years ago
24720abe3b
Merge branch 'master' into attn_update
3 years ago
1c9284c640
Add BeiT 'finetuned' 1k weights and pretrained 22k weights, pretraining specific (masked) model excluded for now
3 years ago
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
7ab2491ab7
Better handling of crossvit for tests / forward_features, fix torchscript regression in my changes
3 years ago
f1808e0970
Post crossvit merge cleanup, change model names to reflect input size, cleanup img size vs scale handling, fix tests
3 years ago
4027412757
Add resnet33ts weights, update resnext26ts baseline weights
3 years ago
9fe5798bee
fix bug for reset classifier and fix for validating the dimension
3 years ago
3718c5a5bd
fix loading pretrained model
3 years ago
bb50b69a57
fix for torch script
3 years ago
abf9d51bc3
🚧 wip
3 years ago
3581affb77
Update train.py with some flags related to scheduler tweaks, fix best checkpoint bug.
3 years ago
c2f02b08b8
Merge remote-tracking branch 'origin/attn_update' into bits_and_tpu
3 years ago
5bd04714e4
Cleanup weight init for byob/byoanet and related
3 years ago
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
5f12de4875
Add initial AttentionPool2d that's being trialed. Fix comment and still trying to improve reliability of sgd test.
3 years ago
76881d207b
Add baseline resnet26t @ 256x256 weights. Add 33ts variant of halonet with at least one halo in stage 2,3,4
3 years ago
484e61648d
Adding the attn series weights, tweaking model names, comments...
3 years ago
fb94350896
Update training script and loader factory to allow use of scheduler updates, repeat augment, and bce loss
3 years ago
f262137ff2
Add RepeatAugSampler as per DeiT RASampler impl, showing promise for current (distributed) training experiments.
3 years ago
ba9c1108a1
Add a BCE loss impl that converts dense targets to sparse /w smoothing as an alternate to CE w/ smoothing. For training experiments.
3 years ago
29a37e23ee
LR scheduler update:
...
* add polynomial decay 'poly'
* cleanup cycle specific args for cosine, poly, and tanh sched, t_mul -> cycle_mul, decay -> cycle_decay, default cycle_limit to 1 in each opt
* add k-decay for cosine and poly sched as per https://arxiv.org/abs/2004.05909
* change default tanh ub/lb to push inflection to later epochs
3 years ago
28d2841acf
💄 apply isort
3 years ago
492c0a4e20
Update HaloAttn comment
3 years ago
e72c989973
✨ add ability to push to hf hub
3 years ago
7ab9d4555c
add crossvit
3 years ago
3b9032ea48
Use Tensor.unfold().unfold() for HaloAttn, fast like as_strided but more clarity
3 years ago
78933122c9
Fix silly typo
3 years ago
2568ffc5ef
Merge branch 'master' into attn_update
3 years ago
708d87a813
Fix ViT SAM weight compat as weights at URL changed to not use repr layer. Fix #825 . Tweak optim test.
3 years ago
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
f2e14685a8
Add force-cpu flag for train/validate, fix CPU fallback for device init, remove old force cpu flag for EMA model weights
3 years ago
a8b65695f1
Add resnet26ts and resnext26ts models for non-attn baselines
3 years ago
a5a542f17d
Fix typo
3 years ago
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
d667351eac
Tweak accuracy topk safety. Fix #807
3 years ago
2ee398d501
Merge branch 'master' into bits_and_tpu
3 years ago
35c9740826
Fix accuracy when topk > num_classes
3 years ago
a16a753852
Add lamb/lars to optim init imports, remove stray comment
3 years ago
c207e02782
MOAR optimizer changes. Woo!
3 years ago
f4fb068b11
Merge branch 'master' into bits_and_tpu
3 years ago
a426511c95
More optimizer cleanup. Change all to no longer use .data. Improve (b)float16 use with adabelief. Add XLA compatible Lars.
3 years ago
b0265ef8a6
Merge branch 'master' into bits_and_tpu
3 years ago
9541f4963b
One more scalar -> tensor fix for lamb optimizer
3 years ago
b76b48e8e9
Update optimizer creation for master optimizer changes
3 years ago
f98662b9c9
Merge branch 'master' into bits_and_tpu
3 years ago
8f68193c91
Update lamp.py comment
3 years ago
4d284017b8
Merge pull request #813 from rwightman/opt_cleanup
...
Optimizer cleanup and additions
3 years ago
a6af48be64
add madgradw optimizer
3 years ago
55fb5eedf6
Remove experiment from lamb impl
3 years ago
8a9eca5157
A few optimizer comments, dead import, missing import
3 years ago
ac469b50da
Optimizer improvements, additions, cleanup
...
* Add MADGRAD code
* Fix Lamb (non-fused variant) to work w/ PyTorch XLA
* Tweak optimizer factory args (lr/learning_rate and opt/optimizer_name), may break compat
* Use newer fn signatures for all add,addcdiv, addcmul in optimizers
* Use upcoming PyTorch native Nadam if it's available
* Cleanup lookahead opt
* Add optimizer tests
* Remove novograd.py impl as it was messy, keep nvnovograd
* Make AdamP/SGDP work in channels_last layout
* Add rectified adablief mode (radabelief)
* Support a few more PyTorch optim, adamax, adagrad
3 years ago
abf3e044bb
Update scheduler_factory.py
...
remove duplicate code from create_scheduler()
3 years ago
cb621e0f00
Remove print, arg order
3 years ago
c06c739901
Merge branch 'master' into bits_and_tpu
3 years ago
40457e5691
Transforms, augmentation work for bits, add RandomErasing support for XLA (pushing into transforms), revamp of transform/preproc config, etc ongoing...
3 years ago
3cdaf5ed56
Add `mmax` config key to auto_augment for increasing upper bound of RandAugment magnitude beyond 10. Make AugMix uniform sampling default not override config setting.
3 years ago
1042b8a146
Add non fused LAMB optimizer option
3 years ago
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
d3f7440650
Add EfficientNetV2 XL model defs
3 years ago
72b227dcf5
Merge pull request #750 from drjinying/master
...
Specify "interpolation" mode in vision_transformer's resize_pos_embed
3 years ago
2907c1f967
Merge pull request #746 from samarth4149/master
...
Adding a Multi Step LR Scheduler
3 years ago
748ab852ca
Allow act_layer switch for xcit, fix in_chans for some variants
3 years ago
20b2d4b69d
Use bicubic interpolation in resize_pos_embed()
4 years ago
d3255adf8e
Merge branch 'xcit' of https://github.com/alexander-soare/pytorch-image-models into alexander-soare-xcit
4 years ago
f8039c7492
Fix gc effv2 model cfg name
4 years ago
3a55a30ed1
add notes from author
4 years ago
899cf84ccc
bug fix - missing _dist postfix for many of the 224_dist models
4 years ago
623e8b8eb8
wip xcit
4 years ago
392368e210
Add efficientnetv2_rw_t defs w/ weights, and gc variant, as well as gcresnet26ts for experiments. Version 0.4.13
4 years ago
daab57a6d9
1. Added a simple multi step LR scheduler
4 years ago
6d8272e92c
Add SAM pretrained model defs/weights for ViT B16 and B32 models.
4 years ago
ee4d8fc69a
Remove unecessary line from nest post refactor
4 years ago
8165cacd82
Realized LayerNorm2d won't work in all cases as is, fixed.
4 years ago
81cd6863c8
Move aggregation (convpool) for nest into NestLevel, cleanup and enable features_only use. Finalize weight url.
4 years ago
6ae0ac6420
Merge branch 'nested_transformer' of https://github.com/alexander-soare/pytorch-image-models into alexander-soare-nested_transformer
4 years ago
7b8a0017f1
wip to review
4 years ago
b11d949a06
wip checkpoint with some feature extraction work
4 years ago
23bb72ce5e
nested_transformer wip
4 years ago
766b4d3262
Fix features for resnetv2_50t
4 years ago
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
20a2be14c3
Add gMLP-S weights, 79.6 top-1
4 years ago
85f894e03d
Fix ViT in21k representation (pre_logits) layer handling across old and new npz checkpoints
4 years ago
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
9c9755a808
AugReg release
4 years ago
381b279785
Add hybrid model fwds back
4 years ago
26f04a8e3e
Fix a weight link
4 years ago
8f4a0222ed
Add GMixer-24 MLP model weights, trained w/ TPU + PyTorch XLA
4 years ago
4c09a2f169
Bump version 0.4.12
4 years ago
b319eb5b5d
Update ViT weights, more details to be added before merge.
4 years ago
8257b86550
Fix up resnetv2 bit/bitm model default res
4 years ago
1228f5a3d8
Add BiT distilled 50x1 and teacher 152x2 models from 'A good teacher is patient and consistent' paper.
4 years ago
511a8e8c96
Add official ResMLP weights.
4 years ago
b9cfb64412
Support npz custom load for vision transformer hybrid models. Add posembed rescale for npz load.
4 years ago
8319e0c373
Add file docstring to std_conv.py
4 years ago
4d96165989
Merge branch 'master' into cleanup_xla_model_fixes
4 years ago
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
ba2ca4b464
One codepath for stdconv, switch layernorm to batchnorm so gain included. Tweak epsilon values for nfnet, resnetv2, vit hybrid.
4 years ago
b7a568f065
Fix torchscript issue in bat
4 years ago
d17b374f0f
Minimum input_size needed to be higher
4 years ago
b3b90d944d
Add min_input_size to bat_resnext to prevent test breakage.
4 years ago
d413eef1bf
Add ResMLP-24 model weights that I trained in PyTorch XLA on TPU-VM. 79.2 top-1.
4 years ago
10d8fa4620
Add gc and bat attention resnext26ts variants to byob for test.
4 years ago
2f5ed2dec1
Update `init_values` const for 24 and 36 layer ResMLP models
4 years ago
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
2a63d0246b
Post merge cleanup
4 years ago
45dec179e5
Merge pull request #681 from lmk123568/master
...
Update convit.py
4 years ago
ded1671483
Fix stochastic depth working only with a shortcut
4 years ago
847b4af144
Update README.md
4 years ago
b87d98b238
Update convit.py
...
Cut out the duplicates
4 years ago
5c5cadfe4c
Update README.md
4 years ago
ee2b8f49ee
Update README.md
4 years ago
cc870df7b8
Update README.md
4 years ago
6b2d9c2660
Another bits/README.md update
4 years ago
c3db5f5801
Worker hack for TFDS eval, add TPU env var setting.
4 years ago
f411724de4
Fix checkpoint delete issue. Add README about bits and initial Pytorch XLA usage on TPU-VM. Add some FIXMEs and fold train_cfg into train_state by default.
4 years ago
b57a03bd0d
Merge branch 'master' into bits_and_tpu
4 years ago
91ab0b6ce5
Add proper TrainState checkpoint save/load. Some reorg/refactoring and other cleanup. More to go...
4 years ago
02320c3e3d
Bump version to 0.4.11
4 years ago
bda8ab015a
Remove min channels for SelectiveKernel, divisor should cover cases well enough.
4 years ago
a27f4aec4a
Missed args for skresnext w/ refactoring.
4 years ago
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
8bf63b6c6c
Able to use other attn layer in EfficientNet now. Create test ECA + GC B0 configs. Make ECA more configurable.
4 years ago
bcec14d3b5
Bring EfficientNet SE layer in line with others, pull se_ratio outside of blocks. Allows swapping w/ other attn layers.
4 years ago
9611458e19
Throw in some FBNetV3 code I had lying around, some refactoring of SE reduction channel calcs for all EffNet archs.
4 years ago
01b9108619
Merge branch 'master' into more_attn
4 years ago
d7bab8a6c5
Fix strict flag change for checkpoint load.
4 years ago
02f9d4bc34
Add weights for resnet51q model, add 61q def.
4 years ago
f615474be3
Fix broken test, repvgg block doesn't have attn_last attr.
4 years ago
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
9c78de8c02
Fix #661 , move hardswish out of default args for LeViT. Enable native torch support for hardswish, hardsigmoid, mish if present.
4 years ago
5db7452173
Fix visformer in_chans stem handling
4 years ago
318360c3f9
Update README.md before merge. Bump version to 0.4.10
4 years ago
11ae795e99
Redo LeViT attention bias caching in a way that works with both torchscript and DataParallel
4 years ago
d400f1dbdd
Filter test models before creation for backward/torchscript tests
4 years ago
c4572cc5aa
Add Visformer-small weighs, tweak torchscript jit test img size.
4 years ago
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
18bf520ad1
Add eca_nfnet_l2/l3 defs for future training
4 years ago
f45de37690
Merge branch 'master' into levit_visformer_rednet
4 years ago
23c18a33e4
Add efficientnetv2_rw_m weights trained in PyTorch. 84.8 top-1 @ 416 test. 53M params.
4 years ago
5b9c69e80a
Add basic training resume based on legacy code
4 years ago
c2ba229d99
Prep for effcientnetv2_rw_m model weights that started training before official release..
4 years ago
30b9880d06
Minor adjustment, mutable default arg, extra check of valid len...
4 years ago
be0abfbcce
Merge branch 'master' of https://github.com/alexander-soare/pytorch-image-models into alexander-soare-master
4 years ago
b7de82e835
ConViT cleanup, fix torchscript, bit of reformatting, reuse existing layers.
4 years ago
306c86b668
Merge branch 'convit' of https://github.com/amaarora/pytorch-image-models into amaarora-convit
4 years ago
a569635045
Update twin weights to a copy in GitHub releases for faster dl. Tweak model class comment.
4 years ago
be99eef9c1
Remove redundant code, cleanup, fix torchscript.
4 years ago
5ab372a3ec
Merge branch 'master' of https://github.com/abcdvzz/pytorch-image-models into abcdvzz-master
4 years ago
5db1eb6ba5
Add defaults
4 years ago
8b1f2e8e1f
remote unused matplotlib import
4 years ago
40c506ba1e
Add ConViT
4 years ago
7976019864
extend positional embedding resizing functionality to tnt
4 years ago
8086943b6f
allow resize positional embeddings to non-square grid
4 years ago
dc1a4efd28
mixer_b16_224_miil, mixer_b16_224_miil_in21k models
4 years ago
4210d922d2
Merge branch 'master' into bits_and_tpu
4 years ago
7b799c4e79
add latest code
4 years ago
72ca831dd4
Back to using strings for the enum translation, forgot about import dep
4 years ago
d5af752117
Add preliminary gMLP and ResMLP impl to Mlp-Mixer
4 years ago
cbd4ee737f
Fix model init for XLA, remove some prints.
4 years ago
00548b8427
Add Twins
4 years ago
74d2829341
Merge branch 'master' into bits_and_tpu
4 years ago
aa92d7b1c5
Major timm.bits update. Updater and DeviceEnv now dataclasses, after_step closure used, metrics base impl w/ distributed reduce, many tweaks/fixes.
4 years ago
e7f0db8664
Fix drop/drop_path arg on MLP-Mixer model. Fix #641
4 years ago
9a3ae97311
Another set of byoanet models w/ ECA channel + SA + groups
4 years ago
d53e91218e
Fix tf.data options setting for newer TF versions
4 years ago
7077f16c6a
Change 21k model naming from _21k to _in21k for consistency with existing 21k models.
4 years ago
94d4b53352
Add temporary default_cfgs to visformer models so they pass tests
4 years ago
3bffc701f1
Merge branch 'master' into levit_visformer_rednet
4 years ago
ecc7552c5c
Add levit, levit_c, and visformer model defs. Largely untested and not finished cleanup.
4 years ago
165fb354b2
Add initial RedNet model / Involution layer impl for testing
4 years ago
328249f11a
Update README, tweak fine-tune effv2 model names.
4 years ago
c4f482a08b
EfficientNetV2 official impl w/ weights ported from TF. Cleanup/refactor of related EfficientNet classes and models.
4 years ago
4fbc32d3d0
Fix crop_pct for cait models.
4 years ago
715519a5ef
Rethink name of patch embed grid info
4 years ago
b2c305c2aa
Move Mlp and PatchEmbed modules into layers. Being used in lots of models now...
4 years ago
3ba6b55cb2
More adjustments to ByoaNet models for further experiments.
4 years ago
5fcddb96a8
Merge branch 'master' into cait
4 years ago
3db12b4b6a
Finish CaiT cleanup
4 years ago
2d8b09fe8b
Add official pretrained weights to MLP-Mixer, complete model cfgs.
4 years ago
12efffa6b1
Initial MLP-Mixer attempt...
4 years ago
0721559511
Improved (hopefully) init for SA/SA-like layers used in ByoaNets
4 years ago
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
0d87650fea
Remove filter hack from BlurPool w/ non-persistent buffer. Use BlurPool2d instead of AntiAliasing.. for TResNet. Breaks PyTorch < 1.6.
4 years ago
ddc743fdf8
Update ResNet-RS models to EMA weights
4 years ago
08d60f4a9a
resnetrs50 pool sizing wrong
4 years ago
1daa15ecc3
Initial Cait commit. Still some cleanup to do.
4 years ago
67d0665b46
Post ResNet-RS merge cleanup. Add weight urls, adjust train/test/crop pct.
4 years ago
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
9cc7dda6e5
Fixup byoanet configs to pass unit tests. Add swin_attn and swinnet26t model for testing.
4 years ago
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
e5e15754c9
Fix coat first conv ident
4 years ago
76739a7589
CoaT merge. Bit of formatting, fix torchscript (for non features), remove einops/einsum dep, add pretrained weight hub (url) support.
4 years ago
026430c083
Merge branch 'master' of https://github.com/morizin/pytorch-image-models-1 into morizin-master
4 years ago
a0492e3b48
A few miil weights naming tweaks to improve compat with model registry and filtering wildcards.
4 years ago
8c1f03e56c
comment
4 years ago
19e1b67a84
old spaces
4 years ago
a443865876
update naming and scores
4 years ago
cf0e371594
84_0
4 years ago
0968bdeca3
vit, tresnet and mobilenetV3 ImageNet-21K-P weights
4 years ago
1e3b6d4dfc
Update __init__.py
4 years ago
fd022fd6a2
Update __init__.py
4 years ago
c2d5087eae
Add files via upload
4 years ago
938716c753
Fix import issue, use devenv for dist info in parser_tfds
4 years ago
76de984a5f
Fix some bugs with XLA support, logger, add hacky xla dist launch script since torch.dist.launch doesn't work
4 years ago
12d9a6d4d2
First timm.bits commit, add initial abstractions, WIP updates to train, val... some of it working
4 years ago
79640fcc1f
Enable uniform augmentation magnitude sampling and set AugMix default
4 years ago
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
e8a64fb881
Test input size for efficientnet_v2s was wrong in last results run
4 years ago
2df77ee5cb
Fix torchscript compat and features_only behaviour in GhostNet PR. A few minor formatting changes. Reuse existing layers.
4 years ago
d793deb51a
Merge branch 'master' of https://github.com/iamhankai/pytorch-image-models into iamhankai-master
4 years ago
e685618f45
Merge pull request #550 from amaarora/wandb
...
Wandb Support
4 years ago
f606c45c38
Add Swin Transformer models from https://github.com/microsoft/Swin-Transformer
4 years ago
de445e7827
Add GhostNet
4 years ago
5a196dddf6
Update README.md with latest, bump version to 0.4.8
4 years ago
b3d7580df1
Update ByoaNet comments. Fix first Steam feat chs for ByobNet.
4 years ago
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
4e4b863b15
Missed norm.py
4 years ago
7c97e66f7c
Remove commented code, add more consistent seed fn
4 years ago
364dd6a58e
Merge branch 'master' into byoanet-self_attn
4 years ago
ce62f96d4d
ByoaNet with bottleneck transformer, lambda resnet, and halo net experiments
4 years ago
cd3dc4979f
Fix adabelief imports, remove prints, preserve memory format is the default arg for zeros_like
4 years ago
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
5772c55c57
Make wandb optional
4 years ago
f54897cc0b
make wandb not required but rather optional as huggingface_hub
4 years ago
3f028ebc0f
import wandb in summary.py
4 years ago
624c9b6949
log to wandb only if using using wandb
4 years ago
addfc7c1ac
adabelief
4 years ago
fb896c0b26
Update some comments re preliminary EfficientNet-V2 assumptions
4 years ago
2b49ab7a36
Fix ResNetV2 pretrained classifier issue. Fixes #540
4 years ago
de9dff933a
EfficientNet-V2S preliminary model def (for experimentation)
4 years ago
37c71a5609
Some further create_optimizer_v2 tweaks, remove some redudnant code, add back safe model str. Benchmark step times per batch.
4 years ago
2bb65bd875
Wrong default_cfg pool_size for L1
4 years ago
bf2ca6bdf4
Merge jax and original weight init
4 years ago
acbd698c83
Update README.md with updates. Small tweak to head_dist handling.
4 years ago
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
c468c47a9c
Add regnety_160 weights from DeiT teacher model, update that and my regnety_032 weights to use higher test size.
4 years ago
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
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
a5310a3451
Merge remote-tracking branch 'origin/benchmark-fixes-vit_hybrids' into pit_and_vit_update
4 years ago
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