Commit Graph

466 Commits (9d83550b670df49395bc8ba863a736b01a836d6a)
 

Author SHA1 Message Date
liaoxingyu 9d83550b67 bugfix
Summary: make `deploy` adaptation for other models except repvgg
2021-03-26 10:10:45 +08:00
Xingyu Liao 15c556c43a
remove apex dependency (#442)
Summary: Use Pytorch1.6(or above) built-in amp training
2021-03-23 12:12:35 +08:00
Xingyu Liao 883fd4aede
add configurable decorator & linear loss decouple (#441)
Summary: Add configurable decorator which can call `Baseline` with `Baseline(cfg)` or `Baseline(cfg, heads=heads, ...)`
Decouple linear and loss computation for partial-fc support.

Reviewed By: l1aoxingyu
2021-03-23 12:10:06 +08:00
Xingyu Liao 41c3d6ff4d
add Dockerfile (#440) 2021-03-23 11:45:03 +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
Xingyu Liao cb7a1cb3e1
update deployment toolchain (#428)
Summary:
Remove tiny-tensorrt dependency and rewrite a new tensorrt inference api.
In the new version of trt infer, it can pad the input to fixed batch automatically, so you don't need to worry about dynamic batch size.
2021-03-10 16:48:59 +08:00
Darren d7c1294d9e
fastrt patch update
Summary:
move div255 to gpu
add read/write numpy ndarray, which will make the comparison between torch and trt results more easily.

Reviewed By: l1aoxingyu
2021-03-10 10:53:18 +08:00
Xingyu Liao 0cc9fb95a6
Merge pull request #425 from JDAI-CV/multi-node
Summary: Add multiple machine training getting started docs.
Change multiple dataset evaluation logging mode, which will show the testing result of each dataset immediately.

Reviewed by: l1aoxingyu
2021-03-09 20:13:29 +08:00
liaoxingyu f57c5764e3 support multi-node training 2021-03-09 20:07:28 +08:00
liaoxingyu 68c190b53c replace list in evaluator process with dict 2021-03-09 20:07:13 +08:00
Xingyu Liao 44ad4b83b1
update veriwild training config
Summary: fix veriwild training config for reproducing.
Reviewed by: l1aoxingyu
2021-03-04 15:20:39 +08:00
Xingyu Liao fcfa6800bb
Merge pull request #416 from TCHeish
Reviewed by: l1aoxingyu
2021-03-04 15:18:47 +08:00
Xinchen Liu 575aeaec3f
Update bagtricks_R50-ibn.yml 2021-03-03 12:07:39 +08:00
darrenhsieh b9bda486f0 add trt api div255 2021-02-27 16:45:29 +08:00
darrenhsieh 69eb044b81 [v004] de-couple fastreid config from Model base-class
fix baseline class ctr bug
2021-02-27 16:40:04 +08:00
liaoxingyu 96fd58c48f update vehicleid and veriwild datasets 2021-02-26 19:26:48 +08:00
liaoxingyu 52b75b7974 update prid and grid datasets 2021-02-26 19:26:38 +08:00
liaoxingyu e2a1e14bc3 remove extra info 2021-02-24 14:40:45 +08:00
Xingyu Liao 2f1836825c
update requirements.txt location 2021-02-23 19:05:24 +08:00
Namgyu Ho 527b09c696
Update requirement.txt location in INSTALL.md
Previously, it was hard to find the requirements.txt file
2021-02-23 14:50:16 +09:00
liaoxingyu c4412d367f update GETTING_STARTED.md 2021-02-18 11:34:45 +08:00
liaoxingyu 819c5a8ab4 update vehicle reid config 2021-02-18 11:33:05 +08:00
Xingyu Liao cf46e5f071
Attribute projects update
Summary: 1.fix zero divided in attribute metric computation;2.update market/duke attribute dataset loading.
Reviewed by: l1aoxingyu
2021-02-18 10:32:48 +08:00
Xingyu Liao 3854069f4e
update datset description
Reviewed by: l1aoxingyu
2021-02-18 10:27:50 +08:00
Xingyu Liao 2f95da9a59
patch update for fasttrv003 2021-02-18 10:26:55 +08:00
darrenhsieh 0617e3eeb7 refactor: embedding_head
* add abstract poolinglayer

* add poolinglayer factory
2021-02-13 21:28:29 +08:00
darrenhsieh 159494e4a4 refactor: model class
* add Module as base class

* add head type

* replace template func args with Module ptr

* add Module factory
2021-02-13 21:14:14 +08:00
Zhedong Zheng 96b7d3133a
Update README.md 2021-02-10 15:29:09 +08:00
Jinkai Zheng 39e25e0457 add Market1501Attr and DukeMTMCAttr dataloader 2021-02-05 22:36:54 +08:00
Jinkai Zheng c9537c97d1 add eps in attr_evaluation.py 2021-02-05 21:52:39 +08:00
liaoxingyu 254a489eb1 Merge branch 'master' of github.com:L1aoXingyu/fast-reid 2021-02-01 10:56:24 +08:00
liaoxingyu 50ceeb0832 add gitter url 2021-02-01 10:55:24 +08:00
Xingyu Liao a8ae0fd1e9
fastRT refactor
fix cmake bug and model.h refacotr
2021-02-01 10:12:22 +08:00
darrenhsieh 5f7d3d586e refactor: model.h 2021-01-31 18:12:35 +08:00
darrenhsieh ebc375e51e fix: cmake bug 2021-01-31 18:08:25 +08:00
liaoxingyu 1666c82db4 update readme about FastRT 2021-01-30 16:11:08 +08:00
Xingyu Liao d2f9450041
Merge pull request #397 from TCHeish/FastRTv001
feat: support reid model with trt C++APIs
2021-01-30 16:05:05 +08:00
darrenhsieh dc5f1924dc feat: support reid model with trt C++APIs
Summary: support reid model with tensorrt network definition APIs
2021-01-30 15:40:05 +08:00
liaoxingyu 2f877d239b update fastdistill readme 2021-01-30 11:52:47 +08:00
liaoxingyu 77a91b1204 feat: support multi-teacher kd
Summary: support multi-teacher kd with logits and overhaul distillation
2021-01-29 17:25:31 +08:00
liaoxingyu db8670db63 feat: update naic20 1-st solution 2021-01-29 11:50:59 +08:00
liaoxingyu 6b4b935ce4 fix augmix warning
Summary: add array.clone to avoid warning about numpy array not writable
2021-01-29 11:50:33 +08:00
Xingyu Liao 1c08b7ac88
update veri-wild training config
Update bagtricks_R50-ibn.yml in veri-wild
2021-01-28 11:30:44 +08:00
Xinchen Liu 885dc96608
Update bagtricks_R50-ibn.yml
The config that obtains the best performance on VeRi-Wild. The model is trained on 4 P40 GPUs
2021-01-28 11:15:57 +08:00
liaoxingyu 1ed1a13eed update vehicle reid pretrained model (#321, #351)
close #321, #351
2021-01-27 17:23:41 +08:00
liaoxingyu 69454860d1 Merge branch 'master' of github.com:L1aoXingyu/fast-reid 2021-01-26 18:17:25 +08:00
liaoxingyu b786001ebd add mobilenetv2 support 2021-01-26 18:17:01 +08:00
Xingyu Liao 63ed07ab0d
update readme 2021-01-25 13:43:04 +08:00
Xinchen Liu efcc2f28cb
Update README.md
Correct the link to INSTALL.md
2021-01-25 11:06:19 +08:00
liaoxingyu ef6ebf451b refactor apex import 2021-01-23 15:35:48 +08:00