Commit Graph

40 Commits (2cabc3428adf5cb3fc0be0f273cc025c4b0a8781)

Author SHA1 Message Date
liaoxingyu 2cabc3428a Support vision transformer backbone 2021-05-31 17:08:57 +08:00
Xingyu Liao 9b5af4166e
support repvgg (#429)
Summary:
* support repvgg backbone, and verify the consistency of train mode and eval mode
* onnx export logger style modification
2021-03-11 14:23:24 +08:00
liaoxingyu b786001ebd add mobilenetv2 support 2021-01-26 18:17:01 +08:00
liaoxingyu b5c3c0a24d update docs 2021-01-22 21:11:19 +08:00
liaoxingyu e26182e6ec make lr warmup by iter
Summary: change warmup way by iter not by epoch, which will make it more flexible when training small epochs
2021-01-22 11:17:21 +08:00
liaoxingyu 7e83d3175f update README.md
Summary: add information about fastreid V1.0
2021-01-18 11:44:55 +08:00
liaoxingyu 15e1729a27 update fastreid V1.0 2021-01-18 11:36:38 +08:00
liaoxingyu c49414bb9f fix SE layer of basicblock in resnet (#375)
Summary: SE layer defined in `__init__` but not used in `forward`

close #375
2021-01-04 10:46:54 +08:00
liaoxingyu a327a70f0d v0.3 update
Summary:
1. change DPP training in apex way;
2. make warmup scheduler by iter and lr scheduler by epoch;
3. replace random erasing with torchvision implementation;
4. naming modification in config file
2020-12-07 14:19:20 +08:00
liaoxingyu2 42cadaeebc update backbone and config
Summary: update resnet backbone for adaptation caffe export; modify effnet loading keyword
2020-11-06 10:58:38 +08:00
liaoxingyu 2f29228086 fix regnet cfg problem 2020-09-23 14:41:44 +08:00
liaoxingyu 648198e6e5 add efficientnet support 2020-09-10 11:04:52 +08:00
liaoxingyu 1b84348619 remove `num_splits` in batchnorm
Summary: `num_splits` works for GhostBN, but it's very uncommon
2020-09-10 11:01:07 +08:00
liaoxingyu d00ce8fc3c refactor model arch 2020-09-01 16:14:45 +08:00
liaoxingyu ac8409a7da updating for pytorch1.6 2020-08-20 15:51:41 +08:00
liaoxingyu 9c667d1a0f add pretrain_path support in backbone 2020-08-14 14:00:26 +08:00
liaoxingyu db6b42da4f update resnest url 2020-08-10 14:18:00 +08:00
liaoxingyu d1c20cbe50 fix pre-train model bugs
fix bugs locks when downloading pre-train model
2020-08-04 15:56:36 +08:00
liaoxingyu 2430b8ed75 pretrain model bugfix
Fix pretrain model download bugs and testing bugs in multiprocess
2020-07-31 10:42:38 +08:00
liaoxingyu 65169b40bd support ddp testing 2020-07-30 20:15:28 +08:00
liaoxingyu 16655448c2 onnx/trt support
Summary: change model pretrain mode and support onnx/TensorRT export
2020-07-29 17:43:39 +08:00
liaoxingyu ee634df290 rm _all_ in resnet 2020-07-17 19:40:25 +08:00
liaoxingyu 5ad22d5d36 update regnet init 2020-07-17 19:35:40 +08:00
liaoxingyu f9539be683 add regnet config file 2020-07-17 19:32:36 +08:00
liaoxingyu 3b57dea49f support regnet backbone 2020-07-17 19:13:45 +08:00
liaoxingyu f8d468647c resnet expansion add 2020-07-10 22:40:07 +08:00
liaoxingyu fec7abc461 finish v0.2 ddp training 2020-07-06 16:57:43 +08:00
liaoxingyu 3732f94405 update osnet 2020-06-09 14:38:49 +08:00
liaoxingyu a1cb123cfa fix R101 bottleneck missing problem
Summary: add key 101 in block dict to support R101
2020-05-26 14:48:32 +08:00
liaoxingyu 5982f90920 support loading various pretrained weights
Summary: Support loading pretrained model by custom path. With this function, we can load infoMin weights.
2020-05-26 14:33:18 +08:00
liaoxingyu 5d4758125d support ResNet34 backbone
Summary: add BasicBlock to support ResNet34
2020-05-26 13:18:09 +08:00
liaoxingyu 8ab0bc2455 style(backbone): make parameters loading logging more elegant 2020-05-08 12:22:06 +08:00
liaoxingyu a2dcd7b4ab feat(layers/norm): add ghost batchnorm
add a get_norm fucntion to easily change normalization between batchnorm, ghost bn and group bn
2020-05-01 09:02:46 +08:00
liaoxingyu e3ae03cc58 feat($modeling/backbones): add new backbones
add osnet, resnext and resnest backbone supported
2020-04-24 12:14:56 +08:00
liaoxingyu 6c9af664dc refactor($modeling/meta_arch): remove useless parts
remove useless meta_archs and backbones
2020-04-21 11:42:14 +08:00
liaoxingyu 95a3c62ad2 refactor(fastreid)
refactor architecture
2020-04-20 10:59:29 +08:00
liaoxingyu 23bedfce12 update version0.2 code 2020-03-25 10:58:26 +08:00
L1aoXingyu 12957f66aa Change architecture:
1. delete redundant preprocess
2. add data prefetcher to accelerate data loading
3. fix minor bug of triplet sampler when only one image for one id
2020-02-18 21:01:23 +08:00
L1aoXingyu a2f69d0537 Update StrongBaseline results for market1501 and dukemtmc 2020-02-11 22:38:40 +08:00
L1aoXingyu db6ed12b14 Update sampler code 2020-02-10 07:38:56 +08:00