Commit Graph

124 Commits (b1c2e3eb92c85e460ca90133b93bbbf5476f927e)

Author SHA1 Message Date
Ross Wightman b1c2e3eb92 Match rel_pos_indices attr rename in conv branch
3 years ago
Ross Wightman b49630a138 Add relative pos embed option to LambdaLayer, fix last transpose/reshape.
3 years ago
Ross Wightman b81e79aae9 Fix bottleneck attn transpose typo, hopefully these train better now..
3 years ago
Ross Wightman 515121cca1 Use reshape instead of view in std_conv, causing issues in recent PyTorch in channels_last
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 492c0a4e20 Update HaloAttn comment
3 years ago
Ross Wightman 3b9032ea48 Use Tensor.unfold().unfold() for HaloAttn, fast like as_strided but more clarity
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 925e102982 Update attention / self-attn based models from a series of experiments:
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 8165cacd82 Realized LayerNorm2d won't work in all cases as is, fixed.
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.
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 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 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 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 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 f45de37690 Merge branch 'master' into levit_visformer_rednet
4 years ago
Ross Wightman d5af752117 Add preliminary gMLP and ResMLP impl to Mlp-Mixer
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 c4f482a08b EfficientNetV2 official impl w/ weights ported from TF. Cleanup/refactor of related EfficientNet classes and 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 0721559511 Improved (hopefully) init for SA/SA-like layers used in ByoaNets
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 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 4e4b863b15 Missed norm.py
4 years ago
Ross Wightman ce62f96d4d ByoaNet with bottleneck transformer, lambda resnet, and halo net experiments
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 cf5fec5047 Cleanup experimental vit weight init a bit
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 f57db99101 Update README, fix iabn pip version print.
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 d8e69206be
Merge pull request #419 from rwightman/byob_vgg_models
4 years ago
Reuben 94ca140b67 update collections.abc import
4 years ago