Commit Graph

983 Commits (79927baaecb6cdd1a25eed7f0f8c122b99712c72)
 

Author SHA1 Message Date
Ross Wightman 79927baaec
Merge pull request #702 from rwightman/cleanup_xla_model_fixes
3 years ago
Ross Wightman 9c9755a808 AugReg release
3 years ago
Ross Wightman 381b279785 Add hybrid model fwds back
3 years ago
Ross Wightman 26f04a8e3e Fix a weight link
3 years ago
Ross Wightman 8f4a0222ed Add GMixer-24 MLP model weights, trained w/ TPU + PyTorch XLA
3 years ago
Ross Wightman 4c09a2f169 Bump version 0.4.12
3 years ago
Ross Wightman b319eb5b5d Update ViT weights, more details to be added before merge.
3 years ago
Ross Wightman 8257b86550 Fix up resnetv2 bit/bitm model default res
3 years ago
Ross Wightman 1228f5a3d8 Add BiT distilled 50x1 and teacher 152x2 models from 'A good teacher is patient and consistent' paper.
3 years ago
Ross Wightman 511a8e8c96 Add official ResMLP weights.
3 years ago
Ross Wightman b9cfb64412 Support npz custom load for vision transformer hybrid models. Add posembed rescale for npz load.
3 years ago
Ross Wightman 8319e0c373 Add file docstring to std_conv.py
3 years ago
Ross Wightman 0020268d9b Try lower max size for non_std default_cfg test
3 years ago
Ross Wightman 4d96165989 Merge branch 'master' into cleanup_xla_model_fixes
3 years ago
Ross Wightman 8880f696b6 Refactoring, cleanup, improved test coverage.
3 years ago
Ross Wightman ba2ca4b464 One codepath for stdconv, switch layernorm to batchnorm so gain included. Tweak epsilon values for nfnet, resnetv2, vit hybrid.
3 years ago
Ross Wightman 07fb05cc3d Update results csv files
3 years ago
Ross Wightman b79dfd4fc2
Merge pull request #693 from SamuelGabriel/patch-1
3 years ago
SamuelGabriel 7c19c35d9f
Global instead of local rank.
3 years ago
Ross Wightman b7a568f065 Fix torchscript issue in bat
3 years ago
Ross Wightman d17b374f0f Minimum input_size needed to be higher
3 years ago
Ross Wightman b3b90d944d Add min_input_size to bat_resnext to prevent test breakage.
3 years ago
Ross Wightman 758c4438a7 Update README.md
3 years ago
Ross Wightman d413eef1bf Add ResMLP-24 model weights that I trained in PyTorch XLA on TPU-VM. 79.2 top-1.
3 years ago
Ross Wightman 10d8fa4620 Add gc and bat attention resnext26ts variants to byob for test.
3 years ago
Ross Wightman 2f5ed2dec1 Update `init_values` const for 24 and 36 layer ResMLP models
3 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.
3 years ago
Ross Wightman 2a63d0246b Post merge cleanup
3 years ago
Ross Wightman 45dec179e5
Merge pull request #681 from lmk123568/master
3 years ago
Ross Wightman 4907f8f70d
Merge pull request #685 from dyhan0920/master
3 years ago
Dongyoon Han ded1671483 Fix stochastic depth working only with a shortcut
3 years ago
Mike b87d98b238
Update convit.py
3 years ago
Ross Wightman 54a6cca27a
Merge pull request #668 from rwightman/more_attn
3 years ago
Ross Wightman 02320c3e3d Bump version to 0.4.11
3 years ago
Ross Wightman bda8ab015a Remove min channels for SelectiveKernel, divisor should cover cases well enough.
3 years ago
Ross Wightman a27f4aec4a Missed args for skresnext w/ refactoring.
3 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.
3 years ago
Ross Wightman 17dc47c8e6 Missed comma in test filters.
3 years ago
Ross Wightman 34522097b1 See if we can use tcmalloc in test runner
3 years ago
Ross Wightman 8bf63b6c6c Able to use other attn layer in EfficientNet now. Create test ECA + GC B0 configs. Make ECA more configurable.
3 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.
3 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.
3 years ago
Ross Wightman 01b9108619 Merge branch 'master' into more_attn
3 years ago
Ross Wightman d7bab8a6c5 Fix strict flag change for checkpoint load.
3 years ago
Ross Wightman 02f9d4bc34 Add weights for resnet51q model, add 61q def.
3 years ago
Ross Wightman f615474be3 Fix broken test, repvgg block doesn't have attn_last attr.
3 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.
3 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.
3 years ago
Ross Wightman 07d952c7a7
Merge pull request #637 from rwightman/levit_visformer_rednet
3 years ago
Ross Wightman 7f368782b7
Merge pull request #660 from petervandenabeele/readme_fix_typos
3 years ago