Commit Graph

212 Commits (54f96ba78ad087c7110bafe2132a91536f0b5a01)

Author SHA1 Message Date
liaoxingyu 54f96ba78a fix for lint_python 2021-05-31 17:36:56 +08:00
liaoxingyu 6300bd756e Bugfix for cls_layer
In `any_softmax`, all operations are in-place, so pass into the `logits.clone()` to prevent outside logits changed.
2021-05-31 17:32:24 +08:00
liaoxingyu 91ff631184 Minor changes
Some minor changes, such as class name changing, remove extra blank line, etc.
2021-05-31 17:27:14 +08:00
liaoxingyu 8ab3554958 Support self-distill with EMA updated model 2021-05-31 17:17:24 +08:00
liaoxingyu 256721cfde Impl `freezebb` in optimizer's step()
Make impl. of `freezebb` consistent with impl. of grad clip, and both are implemented through step() in optimizer
2021-05-31 17:15:26 +08:00
liaoxingyu 07b8251ccb Support gradient clip
Follow detectron2's instruction and add gradient clip in step function of optimizer
2021-05-31 17:11:37 +08:00
liaoxingyu 2cabc3428a Support vision transformer backbone 2021-05-31 17:08:57 +08:00
liaoxingyu 2b65882447 change way of layer freezing
Remove `find_unused_parameters` in DDP and add a new step function in optimizer for freezing backbone. It will accelerate training speed in this way.
2021-05-25 15:57:09 +08:00
Sherlock Liao ff8a958fff
bugfix for `plain_train_net.py` and lr scheduler step (#484) 2021-05-11 15:46:17 +08:00
Xingyu Liao 46b0681313
fix randompatch (#470) 2021-04-21 17:08:16 +08:00
liaoxingyu 0c8e3d9805 update imbalanced sampler
Summary: add a new sampler, which is useful for imbalanced or long-tail dataset. This refers to ufoym/imbalanced-dataset-sampler.
2021-04-21 17:05:10 +08:00
Xingyu Liao 1dce15efad
faster dataloader with pre-fetch and cuda stream (#456)
Summary: add a background thread to create a generator with pre-fetch, and create a new cuda stream to copy tensor from cpu to gpu in parallel.

Reviewed by: l1aoxingyu
2021-04-12 15:03:35 +08:00
liaoxingyu 55300730e1 update fastreid v1.2 readme and changelog 2021-04-06 20:09:13 +08:00
liaoxingyu 44cee30dfc update fastreid v1.2
Summary:
1. refactor dataloader and heads
2. bugfix in fastattr, fastclas, fastface and partialreid
3. partial-fc supported in fastface
2021-04-02 21:33:13 +08:00
Xingyu Liao fb36b23678
bugfix for attribute project (#450)
Summary: refactor sample weight in attribute recognition;
change all options to False in defaults.py and modify yaml files
2021-03-31 17:07:19 +08:00
Xie Jingyi 25cfa88fd9
Fix bug: COMBINEALL should add extra prefix to avoid pid conflictions (#447) 2021-03-30 15:49:52 +08:00
Xingyu Liao be0a089e1f
bugfix & merge classification transforms (#448)
Summary: change heads definition in project and config file, merge classification transforms into default transforms
2021-03-30 15:47:14 +08:00
Xingyu Liao 890224f25c
support classification in fastreid (#443)
Summary: support classification and refactor build_dataloader which can support explicit parameters passing
2021-03-26 20:17:39 +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 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 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
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 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 6b4b935ce4 fix augmix warning
Summary: add array.clone to avoid warning about numpy array not writable
2021-01-29 11:50:33 +08:00
liaoxingyu b786001ebd add mobilenetv2 support 2021-01-26 18:17:01 +08:00
liaoxingyu ef6ebf451b refactor apex import 2021-01-23 15:35:48 +08:00
liaoxingyu a53fd17874 update docs 2021-01-23 15:25:58 +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 2c17847980 feat: freeze FC
Summary: update freeze FC in the last stages of training
2020-12-28 14:46:28 +08:00
liaoxingyu fe2e46d40e fix arcSoftmax fp16 training problem
Summary: fixup fp16 training when using arcSoftmax by aligning the data type
2020-12-28 14:45:26 +08:00
liaoxingyu 20a01f2545 fix grayscale image input problem
Summary: handle grayscale images mixed in RGB images by adding the image channels
2020-12-28 14:45:09 +08:00
liaoxingyu 8083547613 add kwargs for convenient dataset parameters passing (#290)
Summary: make it more easy for passing dataset kwargs through `build_reid_train_loader`
2020-12-28 14:39:08 +08:00
liaoxingyu 0e1b91f74a fix checkpoint bug in ddp training
Summary: change pytorch ddp to apex ddp in checkpoint
2020-12-28 14:35:02 +08:00
liaoxingyu f56ca8345e fix keywords error
Summary: add `freeze_fc` and `flip_test` keywords
2020-12-28 14:34:18 +08:00
Xingyu Liao 0428a270e3
update veri dataset
Summary: update veri dataset reference information

Reviewed By: l1aoxingyu
2020-12-22 18:01:37 +08:00
liaoxingyu 766f309d03 feat: update pairwise cosface and pairwise circle loss 2020-12-22 15:51:49 +08:00
liaoxingyu 66941cf27a feat: support flip testing 2020-12-22 15:50:50 +08:00
liaoxingyu bb7a00e615 feat: add save best model checkpoint 2020-12-22 15:50:23 +08:00
liaoxingyu 5469e8ce76 feat: add save best model mechanism 2020-12-22 15:49:46 +08:00
liaoxingyu 04fe9fb2d8 add saivt dataset 2020-12-22 15:47:08 +08:00
liaoxingyu e8739a667e update AirportALERT dataset
Summary: add more IDs from the single camera
2020-12-22 15:36:50 +08:00
Xinchen Liu 218a007b6a
Update veri.py 2020-12-21 16:19:06 +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