Change Log
v0.3.0 (17/03/2023)
Support new algorithms including
Anchor-DETR
andDETA
.Release more than 10+ pretrained models (including the converted weights):
DETR-R50 & R101
,DETR-R50 & R101-DC5
,DAB-DETR-R50 & R101-DC5
,DAB-DETR-R50-3patterns
,Conditional-DETR-R50 & R101-DC5
,DN-DETR-R50-DC5
,Anchor-DETR
and theDETA-Swin-o365-finetune
model which can achieve62.9AP
on coco val.Support MaskDINO on ADE20k semantic segmentation task.
Support
EMAHook
during training by settingtrain.model_ema.enabled=True
, which can enhance the model performance. DINO with EMA can achieve49.4AP
with only 12epoch training.Support mixed precision training by setting
train.amp.enabled=True
, which will reduce 20% to 30% GPU memory usage.Support
train.fast_dev_run=True
for fast debugging.Support encoder-decoder checkpoint in DINO, which may reduce 30% GPU memory usage.
Support a great slurm training scripts by @rayleizhu, please check this issue for more details #213
v0.2.1 (01/02/2023)
New Algorithm
MaskDINO COCO instance-seg/panoptic-seg pre-release #154
New Features
Documentation
Add ViTDet / FocalNet download links and usage example, please refer to Download Pretrained Weights.
Add tutorial on how to verify the correct installation of detrex. #194
Bug Fixes
Fix demo confidence filter not to remove mask predictions #156
Code Refinement
v0.2.0 (13/11/2022)
New Features
Rebuild cleaner config files for projects #107
Support H-Deformable-DETR #110
Release H-Deformable-DETR pretrained weights including
H-Deformable-DETR-R50
,H-Deformable-DETR-Swin-Tiny
,H-Deformable-DETR-Swin-Large
.Add demo for visualizing customized input images or videos using pretrained weights #119
Release new baselines for
DINO-Swin-Large-36ep
,DAB-Deformable-DETR-R50-50ep
,DAB-Deformable-DETR-Two-Stage-50ep
,H-DETR
.
v0.1.1 (18/10/2022)
New Features
Bug Fixes
Fix bugs in ConvNeXt backbone #91
Documentation
Add pretrained model weights download links #86
v0.1.0 (21/09/2022)
The beta v0.1.0 version of detrex was released in 21/09/2022
New Features
Support various backbones including: FocalNet, Swin-T, ResNet and other detectron2 builtin backbones.
Add timm backbones wrapper and torchvision backbones wrapper.
Support various transformer based detection algorithms including: DETR, Deformable-DETR, Conditional-DETR, DAB-DETR, DN-DETR, DINO.
Support flexible config system based on Lazy Configs