Commit Graph

339 Commits (198f6ea0f3dae13f041f3ea5880dd79089b60d61)

Author SHA1 Message Date
Ross Wightman 0f5d9d8166 Add CSPResNet50 weights, 79.6 top-1 at 256x256 2020-08-12 11:20:11 -07:00
Ross Wightman b1b6e7c361 Fix a few more issues related to #216 w/ TResNet (space2depth) and FP16 weights in wide resnets. Also don't completely dump pretrained weights in in_chans != 1 or 3 cases. 2020-08-11 18:57:47 -07:00
Ross Wightman 512b2dd645 Add new EfficientNet-B3 and RegNetY-3.2GF weights, both just over 82 top-1 2020-08-11 14:18:51 -07:00
Ross Wightman 6890300877 Add DropPath (stochastic depth) to RegNet 2020-08-11 14:08:53 -07:00
Ross Wightman cd23f55397 Fix mixed prec issues with new mixup code 2020-08-11 12:17:43 -07:00
Yusuke Uchida f6b56602f9 fix test_model_default_cfgs 2020-08-11 23:23:57 +09:00
Ross Wightman f471c17c9d More cutmix/mixup overhaul, ready to kick-off some trials. 2020-08-11 00:10:33 -07:00
Ross Wightman d5145fa4d5 Change default_cfg names for senet to include the legacy and match model names 2020-08-08 11:12:58 -07:00
Ross Wightman 92f2d0d65d Merge branch 'master' into cutmix. Fixup a few issues. 2020-08-07 15:59:52 -07:00
Ross Wightman 1696499ce5 Bump version to 0.2.0, ready to roll (I think) 2020-08-05 16:55:18 -07:00
Ross Wightman e62758cf4f More documentation updates, fix a typo 2020-08-05 15:59:31 -07:00
Ross Wightman dfe80414a6 Add bool arg helper 2020-08-05 13:17:23 -07:00
Ross Wightman fa28067704 Add more augmentation arguments, including a no_aug disable flag. Fix #209 2020-08-05 13:16:44 -07:00
Ross Wightman b1f1a54de9 More uniform treatment of classifiers across all models, reduce code duplication. 2020-08-03 22:18:24 -07:00
Ross Wightman d72ddafe56 Fix some checkpoint / model str regressions 2020-07-29 19:43:01 -07:00
Ross Wightman ac18adb9c3 Remove debug print from RexNet 2020-07-29 11:15:19 -07:00
Ross Wightman c53ec33ae0 Add synset/label indices for results generation. Add 'valid labels' to validation script to support imagenet-a/r label subsets properly. 2020-07-29 00:58:57 -07:00
Ross Wightman ec4976fdba Add EfficientNet-Lite0 weights trained with this code by @hal-314, 75.484 top-1 2020-07-29 00:32:08 -07:00
Ross Wightman 9ecd16bd7b Add new seresnet50 (non-legacy) model weights, 80.274 top-1 2020-07-29 00:17:42 -07:00
Ross Wightman 7995295968 Merge branch 'logger' into features. Change 'logger' to '_logger'. 2020-07-27 18:00:46 -07:00
Ross Wightman 1998bd3180 Merge branch 'feature/AB/logger' of https://github.com/antoinebrl/pytorch-image-models into logger 2020-07-27 16:06:01 -07:00
Ross Wightman 6c17d57a2c Fix some attributions, add copyrights to some file docstrings 2020-07-27 13:44:56 -07:00
Ross Wightman a69c0e04f0 Fix pool size in cspnet 2020-07-27 13:44:02 -07:00
Ross Wightman 14ef7a0dd6 Rename csp.py -> cspnet.py 2020-07-27 11:15:07 -07:00
Ross Wightman ec37008432 Add pretrained weight links to CSPNet for cspdarknet53, cspresnext50 2020-07-27 11:13:21 -07:00
Sangdoo Yun e93e571f7a Add `adamp` and 'sgdp' optimizers.
Update requirements.txt

Update optim_factory.py

Add `adamp` optimizer

Update __init__.py

copy files of adamp & sgdp

Create adamp.py

Update __init__.py

Create sgdp.py

Update optim_factory.py

Update optim_factory.py

Update requirements.txt

Update adamp.py

Update sgdp.py

Update sgdp.py

Update adamp.py
2020-07-25 15:33:20 -07:00
Ross Wightman 08016e839d Cleanup FeatureInfo getters, add TF models sourced Xception41/65/71 weights 2020-07-24 17:59:21 -07:00
Ross Wightman 7ba5a384d3 Add ReXNet w/ remapped weights, feature support 2020-07-23 10:28:57 -07:00
Ross Wightman c9d54bc1c3 Add HRNet feature extraction, fix senet type, lower feature testing res to 96x96 2020-07-21 17:39:29 -07:00
Ross Wightman 2ac663f340 Add feature support to legacy senets, add 32x32 resnext models to exclude list for feature testing. 2020-07-21 11:15:30 -07:00
Ross Wightman c146b54abc Cleanup EfficientNet/MobileNetV3 feature extraction a bit, only two tap locations now, small mobilenetv3 models work 2020-07-21 01:21:38 -07:00
Ross Wightman 68fd8a267b Merge branch 'master' into features 2020-07-20 16:11:38 -07:00
Ross Wightman 4e61c6a12d Cleanup, refactoring of Feature extraction code, add tests, fix tests, non hook feature extraction working with torchscript 2020-07-20 16:10:31 -07:00
Ross Wightman 6eec3fb4a4 Move FeatureHooks into features.py, switch EfficientNet, MobileNetV3 to use build model helper 2020-07-19 15:00:43 -07:00
Ross Wightman 9eba134d79 More models supporting feature extraction, xception, gluon_xception, inception_v3, inception_v4, pnasnet, nasnet, dla. Fix DLA unused projection params. 2020-07-19 14:02:02 -07:00
Ross Wightman 298fba09ac Back out some activation hacks trialing upcoming pytorch changes 2020-07-17 18:41:37 -07:00
Ross Wightman 3b9004bef9 Lots of changes to model creation helpers, close to finalizing feature extraction / interfaces 2020-07-17 17:54:26 -07:00
Ross Wightman e2cc481310 Update CSP ResNets for cross expansion without activation. Fix VovNet IABN compatibility with fixed activation arg. 2020-07-13 16:24:55 -07:00
Ross Wightman 3b6cce4c95 Add initial impl of CrossStagePartial networks, yet to be trained, not quite the same as darknet cfgs. 2020-07-13 15:01:06 -07:00
Ross Wightman 3aebc2f06c Switch DPN to use BnAct layer, train a new DPN 68b model with RA to 79.21 2020-07-12 11:13:06 -07:00
Ross Wightman f122f0274b Significant ResNet refactor:
* stage creation + make_layer moved to separate fn with more sensible dilation/output_stride calc
* drop path rate decay easy to impl with refactored block creation loops
* fix dilation + blur pool combo
2020-07-05 00:48:12 -07:00
Ross Wightman a66df5fb91 More model feature extraction support, start to deprecate senet.py, dilations added to regnet, add proper aligned xception 2020-07-03 00:41:30 -07:00
Ross Wightman 7729f40dca Fix another bug, update all gluon resnet models to use new creation method (feature support) 2020-06-30 16:44:15 -07:00
Ross Wightman d72ac0db25 Fix #173, lr cycle default 0 vs 1. Fix #177, mirror resnest weights for future stability. 2020-06-29 21:31:48 -07:00
Ross Wightman d0113f9cdb Fix a few issues that came up in tests 2020-06-29 21:13:21 -07:00
Ross Wightman d23a2697d0 Working on feature extraction, interfaces refined, a number of models working, some in progress. 2020-06-29 18:18:59 -07:00
Ross Wightman 24e7535278 Remove tests from distrib 2020-06-16 22:57:26 -07:00
Ross Wightman 328339a086 Add ESE-VoVNet-19-DW weights 2020-06-15 14:31:55 -07:00
Ross Wightman 2d83752bc2 Fix default interpolation/crop of largest 2 ResNeSt models 2020-06-12 16:42:47 -07:00
Ross Wightman f225ae8e59 Update README with model results and attribution. Make scheduler factory bit more robust to arg differences, add noise to plateau lr and fix min/max. 2020-06-12 13:33:12 -07:00
Ross Wightman 39f27c1add Almost ready to merge, vovnet typo, version bump, readme addition 2020-06-11 15:41:58 -07:00
Ross Wightman 151679c2f1 Add custom grad tests, fix cut & paste error with hard_mish ME, add a few more pytorch act fns to factory 2020-06-11 14:49:23 -07:00
Ross Wightman 6c7932fe75 Update sotabench.py, tweak VovNet cfg 2020-06-11 14:34:25 -07:00
Ross Wightman 0aca08384f Update regnet cfg keys to match model names so registry works properly 2020-06-09 14:37:45 -07:00
Antoine Broyelle 78fa0772cc Leverage python hierachical logger
with this update one can tune the kind of logs generated by timm but
training and inference traces are unchanged
2020-06-09 18:28:48 +01:00
Ross Wightman 13c0a6290e Add ESE-VovNet39 weights, 79.32 top-1 2020-06-06 22:50:21 -07:00
Ross Wightman 4ddde1d3a4 Fix two regressions 2020-06-05 11:04:51 -07:00
Ross Wightman a7e8cadd15 Remove pointless densenet configs, add an iabn version of 264 as it makes more sense to try someday... 2020-06-03 17:13:52 -07:00
Ross Wightman e78daf586a better densenet121 and densenetblur121d weights 2020-06-03 13:30:03 -07:00
Ross Wightman 7be299504f Add missing feature_info() on MobileNetV3, make hook feature output order/type consistent with bottleneck (list, decreasing fmap size) 2020-06-03 00:00:37 -07:00
Ross Wightman 88129b2569 Add set_layer_config contextmgr to adjust all layer configs at once, use in create_module with new args. Remove a few old warning causing constant annotations for jit. 2020-06-02 21:06:10 -07:00
Ross Wightman f28170df3f Fix an an untested change, remove a debug print 2020-06-01 17:26:42 -07:00
Ross Wightman eb7653614f Monster commit, activation refactor, VoVNet, norm_act improvements, more
* refactor activations into basic PyTorch, jit scripted, and memory efficient custom auto
* implement hard-mish, better grad for hard-swish
* add initial VovNet V1/V2 impl, fix #151
* VovNet and DenseNet first models to use NormAct layers (support BatchNormAct2d, EvoNorm, InplaceIABN)
* Wrap IABN for any models that use it
* make more models torchscript compatible (DPN, PNasNet, Res2Net, SelecSLS) and add tests
2020-06-01 17:16:52 -07:00
Ross Wightman 0ea53cecc3 Merge branch 'master' into densenet_update_and_more 2020-05-22 16:18:10 -07:00
Ross Wightman 6441e9cc1b Fix memory_efficient mode for DenseNets. Add AntiAliasing (Blur) support for DenseNets and create one test model. Add lr cycle/mul params to train args. 2020-05-22 16:16:45 -07:00
Ross Wightman afb6bd0669 Add backward and default_cfg tests and fix a few issues found. Fix #153 2020-05-21 15:30:58 -07:00
Ross Wightman 50658b9a67 Add RegNet models and weights 2020-05-18 00:08:52 -07:00
Ross Wightman 7df83258c9 Merge branch 'master' into densenet_update_and_more 2020-05-13 23:34:44 -07:00
Ross Wightman 1904ed8fec Improve dropblock impl, add fast variant, and better AMP speed, inplace, batchwise... few ResNeSt cleanups 2020-05-13 15:17:08 -07:00
Ross Wightman 17270c69b9 Remove annoying InceptionV3 dependency on scipy and insanely slow trunc_norm init. Bring InceptionV3 code into this codebase and use upcoming torch trunch_norm_ init. 2020-05-12 21:59:34 -07:00
Ross Wightman c4ca016656
Merge pull request #145 from rwightman/resnest
ResNeSt
2020-05-12 13:38:29 -07:00
Ross Wightman 208e7912f7 Missed one of the abalation model entrypoints, update README 2020-05-12 13:36:31 -07:00
Ross Wightman 9cc289f18c Exclude EfficientNet-L2 models from test 2020-05-12 13:07:03 -07:00
Ross Wightman 2f884a0ce5 Add resnest14, resnest26, and two of the abalation grouped resnest50 models 2020-05-12 12:21:52 -07:00
Ross Wightman f4cdc2ac31 Add ResNeSt models 2020-05-11 23:27:09 -07:00
Ross Wightman 780860d140 Add norm_act factory method, move JIT of norm layers to factory 2020-05-09 22:09:21 -07:00
Ross Wightman 14edacdf9a DenseNet converted to support ABN (norm + act) modules. Experimenting with EvoNorm, IABN 2020-05-09 18:26:41 -07:00
Ross Wightman 022ed001f3 Update DenseNet to latest in Torchvision (torchscript compat, checkpointing, proper init). Start adding ehanced configurability, stem options... 2020-05-07 09:57:48 -07:00
Vyacheslav Shults a7ebe09029 Replace all None by nn.Identity() in all models reset_classifier when False-values num_classes is given.
Make small code refactoring
2020-05-06 09:54:03 +03:00
Vyacheslav Shults f0eb021620 Replace all None by nn.Identity() in HRNet modules 2020-05-05 21:09:35 +03:00
AFLALO, Jonathan Isaac a7f570c9b7 added MultiEpochsDataLoader 2020-05-05 14:47:02 +03:00
Ross Wightman 8d8677e03b Fix #139. Broken SKResNets after BlurPool addition, as a plus, SKResNets support AA now too. 2020-05-04 12:14:43 -07:00
Ross Wightman c9b6f415ca Bump version for Pypi release 2020-05-03 21:18:47 -07:00
AFLALO, Jonathan Isaac 9c15d57505 added efficientnet pruned weights 2020-05-03 09:29:45 +03:00
Ross Wightman ea300709f0 Fix model create fn not passing num_classes through. Fix #135 2020-05-01 18:37:03 -07:00
Ross Wightman 2c438c4e0d Merge branch 'master' of github.com:rwightman/pytorch-models 2020-05-01 17:03:17 -07:00
Ross Wightman 2681a8d618 Final blurpool2d cleanup and add resnetblur50 weights, match tresnet Downsample arg order to BlurPool2d for interop 2020-05-01 17:00:21 -07:00
Ross Wightman 9590f301a9 Merge branch 'blur' of https://github.com/VRandme/pytorch-image-models into VRandme-blur 2020-05-01 15:19:57 -07:00
Ross Wightman a5220ad3aa
Merge pull request #125 from Separius/patch-1
fix typo in eca
2020-05-01 15:11:56 -07:00
Ross Wightman 0834fbc01c Move pruned model adapt strings to separate txt files. A few minor formatting alignment tweaks. 2020-05-01 15:09:20 -07:00
Ross Wightman ba793f5c1c Merge branch 'adding_ECA_resnet' of https://github.com/yoniaflalo/pytorch-image-models into yoniaflalo-adding_ECA_resnet 2020-04-29 16:43:02 -07:00
AFLALO, Jonathan Isaac 07f19dd699 added eca resnet 2020-04-29 19:09:55 +03:00
Ross Wightman 1d4ac1b165 Bump version for pypi release. Fix #130 2020-04-27 18:02:40 -07:00
Ross Wightman be7c784d21 Small TResNet simplification, just use SelectAdaptivePool, don't notice any perf difference 2020-04-27 17:50:19 -07:00
Ross Wightman e3a98171b2 Remove some CRLF that made it into TResNet merge 2020-04-27 13:23:41 -07:00
Ross Wightman 0004f37d25 Some TResNet cleanup.
* allow use of global pool arg, test-time-pooling
* clean checkpoints to just contain state dict, add 448 res checkpoints
* support DataParallel via lazy filter creation for JIT Downsample
* some minor formatting (mostly alignment) preferences
2020-04-27 13:21:05 -07:00
Ross Wightman 64fe37d008 Remove old mean/std helper, rely fully on cmd line or default_cfg now. Fixes #126 2020-04-27 12:32:55 -07:00
Ross Wightman e6f24e5578 Add 'momentum' optimizer (SGD w/o nesterov) for stable EfficientDet training defaults 2020-04-25 19:42:13 -07:00
Sepehr Sameni 20290b5b56
fix typo in eca 2020-04-14 15:20:35 +04:30
Ross Wightman ebf82b84ac
Merge pull request #122 from mrT23/master
TResNet models
2020-04-12 18:23:46 -07:00