Migrations
/
pytorch-image-models
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity
897 Commits
41 Branches
41 Tags
28 MiB
Branches Tags
${ item.name }
Create tag ${ searchTerm }
Create branch ${ searchTerm }
from '5b9c69e80a'
${ noResults }
Commit Graph

897 Commits (5b9c69e80a5ff4ecfd62429246e51a1de0f834fe)
 

Author SHA1 Message Date
Ross Wightman 5b9c69e80a Add basic training resume based on legacy code
3 years ago
Ross Wightman 4210d922d2 Merge branch 'master' into bits_and_tpu
3 years ago
Ross Wightman cf4ce2f15b
Merge pull request #647 from rwightman/more_mlp
3 years ago
Ross Wightman 72ca831dd4 Back to using strings for the enum translation, forgot about import dep
3 years ago
Ross Wightman b3b503c13d
Merge pull request #626 from cvcomar/master
3 years ago
Ross Wightman 6d81374b88 Update tests for new mlp models
3 years ago
Ross Wightman d5af752117 Add preliminary gMLP and ResMLP impl to Mlp-Mixer
3 years ago
Ross Wightman cbd4ee737f Fix model init for XLA, remove some prints.
3 years ago
Ross Wightman 6d90fcf282 Fix distribute_bn and model_ema
3 years ago
Ross Wightman 74d2829341 Merge branch 'master' into bits_and_tpu
3 years ago
Ross Wightman aa92d7b1c5 Major timm.bits update. Updater and DeviceEnv now dataclasses, after_step closure used, metrics base impl w/ distributed reduce, many tweaks/fixes.
3 years ago
Ross Wightman e7f0db8664 Fix drop/drop_path arg on MLP-Mixer model. Fix #641
3 years ago
Ross Wightman 7077f16c6a Change 21k model naming from _21k to _in21k for consistency with existing 21k models.
3 years ago
Ross Wightman 2a72d38ba2
Update README.md
3 years ago
Ross Wightman 758802e1f6
Merge pull request #636 from rwightman/effnetv2_official
3 years ago
Ross Wightman 328249f11a Update README, tweak fine-tune effv2 model names.
3 years ago
Ross Wightman c4f482a08b EfficientNetV2 official impl w/ weights ported from TF. Cleanup/refactor of related EfficientNet classes and models.
3 years ago
Ross Wightman c16d65a8a7 Update results.csv files with cait, mlp-mixer, resnetrs, miil imagenet21k pretrained, and my latest efficientnet v2s/b4 weights.
3 years ago
Ross Wightman 4fbc32d3d0 Fix crop_pct for cait models.
3 years ago
comar d7e1e7144a fix: the exeption when topk is 1
3 years ago
comar ffa90e04d3 fix: the exception not using default topk argument
3 years ago
Ross Wightman 715519a5ef Rethink name of patch embed grid info
3 years ago
Ross Wightman b2c305c2aa Move Mlp and PatchEmbed modules into layers. Being used in lots of models now...
3 years ago
Ross Wightman 3ba6b55cb2 More adjustments to ByoaNet models for further experiments.
3 years ago
Ross Wightman f480734ad5 Update README.md
3 years ago
Ross Wightman 504fef4bc1
Merge pull request #609 from rwightman/cait
3 years ago
Ross Wightman d45e50b9db Update test for cait 448x448 model
3 years ago
Ross Wightman 5fcddb96a8 Merge branch 'master' into cait
3 years ago
Ross Wightman 3db12b4b6a Finish CaiT cleanup
3 years ago
Ross Wightman 936e9b331d
Merge pull request #613 from rwightman/mlp-mixer
3 years ago
Ross Wightman 2d8b09fe8b Add official pretrained weights to MLP-Mixer, complete model cfgs.
3 years ago
Ross Wightman 12efffa6b1 Initial MLP-Mixer attempt...
3 years ago
Ross Wightman 0721559511 Improved (hopefully) init for SA/SA-like layers used in ByoaNets
3 years ago
Ross Wightman d5473c17f7 Fix incorrect name of shortcut/identity paths in many residual nets. Inherited from naming in old old torchvision, long fixed there.
3 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.
3 years ago
Ross Wightman ddc743fdf8 Update ResNet-RS models to EMA weights
3 years ago
Ross Wightman 08d60f4a9a resnetrs50 pool sizing wrong
3 years ago
Ross Wightman 137a374930
Merge pull request #555 from MichaelMonashev/patch-1
3 years ago
Ross Wightman 1daa15ecc3 Initial Cait commit. Still some cleanup to do.
3 years ago
Ross Wightman 67d0665b46 Post ResNet-RS merge cleanup. Add weight urls, adjust train/test/crop pct.
3 years ago
Aman Arora 560eae38f5
[WIP] Add ResNet-RS models (#554)
3 years ago
Ross Wightman 9cc7dda6e5 Fixup byoanet configs to pass unit tests. Add swin_attn and swinnet26t model for testing.
3 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.
3 years ago
Ross Wightman d15ad3e919 Merge branch 'morizin-master'
3 years ago
Ross Wightman e5e15754c9 Fix coat first conv ident
3 years ago
Ross Wightman 76739a7589 CoaT merge. Bit of formatting, fix torchscript (for non features), remove einops/einsum dep, add pretrained weight hub (url) support.
3 years ago
Ross Wightman 026430c083 Merge branch 'master' of https://github.com/morizin/pytorch-image-models-1 into morizin-master
3 years ago
Ross Wightman c03e45cbf3 Merge branch 'mrT23-master'
3 years ago
Ross Wightman a0492e3b48 A few miil weights naming tweaks to improve compat with model registry and filtering wildcards.
3 years ago
talrid 8c1f03e56c comment
3 years ago