676 Commits (57992509f9f663036faa59d1ef553226badd84d4)

Author	SHA1	Message	Date
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	76881d207b	Add baseline resnet26t @ 256x256 weights. Add 33ts variant of halonet with at least one halo in stage 2,3,4	3 years ago
Ross Wightman	484e61648d	Adding the attn series weights, tweaking model names, comments...	3 years ago
Ross Wightman	fb94350896	Update training script and loader factory to allow use of scheduler updates, repeat augment, and bce loss	3 years ago
Ross Wightman	f262137ff2	Add RepeatAugSampler as per DeiT RASampler impl, showing promise for current (distributed) training experiments.	3 years ago
Ross Wightman	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
Ross Wightman	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
Ross Wightman	492c0a4e20	Update HaloAttn comment	3 years ago
Richard Chen	7ab9d4555c	add crossvit	3 years ago
Ross Wightman	3b9032ea48	Use Tensor.unfold().unfold() for HaloAttn, fast like as_strided but more clarity	3 years ago
Ross Wightman	78933122c9	Fix silly typo	3 years ago
Ross Wightman	2568ffc5ef	Merge branch 'master' into attn_update	3 years ago
Ross Wightman	708d87a813	Fix ViT SAM weight compat as weights at URL changed to not use repr layer. Fix #825. Tweak optim test.	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	a8b65695f1	Add resnet26ts and resnext26ts models for non-attn baselines	3 years ago
Ross Wightman	a5a542f17d	Fix typo	3 years ago
Ross Wightman	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
Ross Wightman	d667351eac	Tweak accuracy topk safety. Fix #807	3 years ago
Yohann Lereclus	35c9740826	Fix accuracy when topk > num_classes	3 years ago
Ross Wightman	a16a753852	Add lamb/lars to optim init imports, remove stray comment	3 years ago
Ross Wightman	c207e02782	MOAR optimizer changes. Woo!	3 years ago
Ross Wightman	a426511c95	More optimizer cleanup. Change all to no longer use .data. Improve (b)float16 use with adabelief. Add XLA compatible Lars.	3 years ago
Ross Wightman	9541f4963b	One more scalar -> tensor fix for lamb optimizer	3 years ago
Ross Wightman	8f68193c91	Update lamp.py comment	3 years ago
Ross Wightman	4d284017b8	Merge pull request #813 from rwightman/opt_cleanup ... Optimizer cleanup and additions	3 years ago
Ross Wightman	a6af48be64	add madgradw optimizer	3 years ago
Ross Wightman	55fb5eedf6	Remove experiment from lamb impl	3 years ago
Ross Wightman	8a9eca5157	A few optimizer comments, dead import, missing import	3 years ago
Ross Wightman	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
Sepehr Sameni	abf3e044bb	Update scheduler_factory.py ... remove duplicate code from create_scheduler()	3 years ago
Ross Wightman	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
Ross Wightman	1042b8a146	Add non fused LAMB optimizer option	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	d3f7440650	Add EfficientNetV2 XL model defs	3 years ago
Ross Wightman	72b227dcf5	Merge pull request #750 from drjinying/master ... Specify "interpolation" mode in vision_transformer's resize_pos_embed	3 years ago
Ross Wightman	2907c1f967	Merge pull request #746 from samarth4149/master ... Adding a Multi Step LR Scheduler	3 years ago
Ross Wightman	748ab852ca	Allow act_layer switch for xcit, fix in_chans for some variants	3 years ago
Ying Jin	20b2d4b69d	Use bicubic interpolation in resize_pos_embed()	3 years ago
Ross Wightman	d3255adf8e	Merge branch 'xcit' of https://github.com/alexander-soare/pytorch-image-models into alexander-soare-xcit	3 years ago
Ross Wightman	f8039c7492	Fix gc effv2 model cfg name	3 years ago
Alexander Soare	3a55a30ed1	add notes from author	3 years ago
Alexander Soare	899cf84ccc	bug fix - missing _dist postfix for many of the 224_dist models	3 years ago
Alexander Soare	623e8b8eb8	wip xcit	3 years ago
Ross Wightman	392368e210	Add efficientnetv2_rw_t defs w/ weights, and gc variant, as well as gcresnet26ts for experiments. Version 0.4.13	3 years ago
samarth	daab57a6d9	1. Added a simple multi step LR scheduler	3 years ago
Ross Wightman	6d8272e92c	Add SAM pretrained model defs/weights for ViT B16 and B32 models.	3 years ago
Ross Wightman	ee4d8fc69a	Remove unecessary line from nest post refactor	3 years ago
Ross Wightman	8165cacd82	Realized LayerNorm2d won't work in all cases as is, fixed.	3 years ago
Ross Wightman	81cd6863c8	Move aggregation (convpool) for nest into NestLevel, cleanup and enable features_only use. Finalize weight url.	3 years ago
Ross Wightman	6ae0ac6420	Merge branch 'nested_transformer' of https://github.com/alexander-soare/pytorch-image-models into alexander-soare-nested_transformer	3 years ago
Alexander Soare	7b8a0017f1	wip to review	3 years ago
Alexander Soare	b11d949a06	wip checkpoint with some feature extraction work	3 years ago
Alexander Soare	23bb72ce5e	nested_transformer wip	3 years ago
Ross Wightman	766b4d3262	Fix features for resnetv2_50t	3 years ago
Ross Wightman	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.	3 years ago
Ross Wightman	20a2be14c3	Add gMLP-S weights, 79.6 top-1	3 years ago
Ross Wightman	85f894e03d	Fix ViT in21k representation (pre_logits) layer handling across old and new npz checkpoints	3 years ago
Ross Wightman	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	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	4d96165989	Merge branch 'master' into cleanup_xla_model_fixes	3 years ago
Ross Wightman	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	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	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	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 ... Update convit.py	3 years ago
Dongyoon Han	ded1671483	Fix stochastic depth working only with a shortcut	3 years ago
Mike	b87d98b238	Update convit.py ... Cut out the duplicates	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	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	5db7452173	Fix visformer in_chans stem handling	3 years ago
Ross Wightman	318360c3f9	Update README.md before merge. Bump version to 0.4.10	3 years ago