Data

Tools

Indexes

Applications

Experiments

Open Source Science

Recent Releases of detrex

detrex - detrex v0.5.0 Release

Release v0.5.0

Support New Algorithms and Benchmarks, including: - Support Focus-DETR (ICCV'2023) - Support SQR-DETR (CVPR'2023), credits to Fangyi Chen - Support EVA-01 (CVPR'2023 Highlight) - Support EVA-02 (ArXiv'2023) - Support DINO-EVA benchmarks, including dino-eva-01 and dino-eva-02 with LSJ augmentation. - Support Align-DETR (ArXiv'2023), credits to Zhi Cai

All the pretrained DINO-EVA checkpoints can be downloaded in Huggingface Space

- Python
Published by rentainhe over 2 years ago

detrex - detrex v0.4.0 Release

Main updates

  • Support CO-MOT aims for End-to-End Multi-Object Tracking by Feng Yan.
  • Release DINO with optimized hyper-parameters which achieves 50.0 AP under 1x settings.
  • Release pretrained DINO based on InternImage, ConvNeXt-1K pretrained backbones.
  • Release Deformable-DETR-R50 pretrained weights.
  • Release DETA and better H-DETR pretrained weights: achieving 50.2 AP and 49.1 AP respectively.

Pretrained Model

  • DETA-R50-5scale-12ep bs=8: 50.0AP
  • DETA-R50-5scale-12ep aligned hyper-param: 49.9AP
  • DETA-R50-5scale-12ep with only freeze the stem of backbone: 50.2AP
  • H-Deformable-DETR-two-stage-R50-12ep aligned optimizer hyper-params: 49.1AP
  • DINO-R50-4scale-12ep aligned optimizer hyper-params: 49.4AP
  • DINO-Focal-3level-4scale-36ep: 58.3AP

Benchmark ConvNeXt on DINO - convnext-tiny-384: 52.4AP - convnext-small-384: 54.2AP - convnext-base-384: 55.1AP - convnext-large-384: 55.5AP

Benchmark InternImage on DINO - internimage-tiny: 52.3AP - internimage-small: 53.5AP - internimage-base: 54.7AP - internimage-large: 57.0AP

Benchmark FocalNet on DINO - focalnet-tiny - focalnet-small - focalnet-base

Other pre-trained weights - Deformable-DETR R50: 44.9 AP (better than 44.5AP from original repo) - Group-DETR-R50-12ep: 37.8AP

- Python
Published by rentainhe over 2 years ago

detrex - detrex v0.3.0 Release

What's New

New Algorithms - Support Anchor-DETR - Support DETA

More training techniques - Support EMAHook during training by setting train.model_ema.enabled=True, which can further enhance the model performance. - Fully support mixed precision training by setting train.amp.enabled=True, which can reduce 20% to 30% GPU memory usage. - Support encoder-decoder checkpoint in DINO which may reduce 30% GPU memory usage. And for more details about the checkpoint usage, please refer to this PR: #200 - Support fast debugging by setting train.fast_dev_run=True. - Support a great slurm training scripts by @rayleizhu , please check this issue #213 for more details.

Release more than 10+ pretrained checkpoints | Method | Pretrained | Epochs | Box AP | |:---|:---:|:---:|:---:| | DETR-R50-DC5 | IN1k | 500 | 43.4 | | DETR-R101-DC5 | IN1k | 500 | 44.9 | | Anchor-DETR-R50 | IN1k | 50 | 42.2 | | Anchor-DETR-R50-DC5 | IN1k | 50 | 44.2 | | Anchor-DETR-R101 | IN1k | 50 | 43.5 | | Anchor-DETR-R101-DC5 | IN1k | 50 | 45.1 | | Conditional-DETR-R50-DC5 | IN1k | 50 | 43.8 | | Conditional-DETR-R101 | IN1k | 50 | 43.0 | | Conditional-DETR-R101 -DC5 | IN1k | 50 | 45.1 | | DAB-DETR-R50-3patterns | IN1k | 50 | 42.8 | | DAB-DETR-R50-DC5 | IN1k | 50 | 44.6 | | DAB-DETR-R50-DC5-3patterns | IN1k | 50 | 45.7 | | DAB-DETR-101-DC5 | IN1k | 50 | 45.7 | | DN-DETR-R50-DC5 | IN1k | 50 | 46.3 | | DINO with EMA | IN1k | 12 | 49.4 | | DETA-R50-5scale | IN1k | 12 | 50.1 | | DETA-Swin-Large | object-365 | 24 | 62.9 |

Part of the pre-trained weights are converted from their official repo, and all the pre-trained weights can be downloaded in detrex Model Zoo

- Python
Published by rentainhe almost 3 years ago

detrex - detrex v0.2.1 Release

Highlights

  • DINO has been accepted to ICLR 2023!
  • Thanks a lot for @powermano provides us a detailed usage about onnx export in detrex. Please see this issue https://github.com/IDEA-Research/detrex/issues/192

What's New

New Algorithm

  • MaskDINO COCO instance-seg/panoptic-seg pre-release #154

New Features

  • New baselines for Res/Swin-DINO-5scale, ViTDet-DINO, FocalNet-DINO, etc. #138, #155
  • Support FocalNet backbone #145
  • Support Swin-V2 backbone #152

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

  • Make more readable logging info for criterion and matcher #151
  • Modified learning rate scheduler config usage, add fundamental scheduler configuration #191

New Pretrained Models

All the pretrained weights can be downloaded in detrex Model Zoo

DINO

| Method | Pretrained | Epochs | Box AP | |:---|:---:|:---:|:---:| | DINO-ViTDet-Base-4scale | MAE | 12 | 50.2 | | DINO-ViTDet-Base-4scale | MAE | 50 | 55.0 | | DINO-ViTDet-Large-4scale | MAE | 12 | 50.2 | | DINO-ViTDet-Large-4scale | MAE | 50 | 55.0 | | DINO-FocalNet-Large-3level-4scale | IN22k| 12 | 57.5 | | DINO-FocalNet-Large-4level-4scale | IN22k| 12 | 58.0 | | DINO-FocalNet-Large-4level-5scale | IN22k| 12 | 58.5 |

- Python
Published by rentainhe about 3 years ago

detrex - MaskDINO Release

MaskDINO Release

- Python
Published by HaoZhang534 about 3 years ago

detrex - detrex v0.2.0 Release

What's New

  • Rebuild cleaner config files for projects
  • Support H-Deformable-DETR, thanks a lot for @JiaDingCN
  • 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 in demo, please check our documentation about the usage.
  • Release new baselines for DINO-Swin-Large-36ep, DAB-Deformable-DETR-R50-50ep, DAB-Deformable-DETR-Two-Stage-50ep.

New Pretrained Models

All the pretrained weights can be downloaded in detrex Model Zoo

H-Deformable-DETR

| Method | Pretrained | Epochs | Query Num | Box AP | |:---|:---:|:---:|:---:|:---:| | H-Deformable-DETR-R50 + tricks | IN1k | 12 | 300 | 48.9 | | H-Deformable-DETR-R50 + tricks | IN1k | 36 | 300 | 50.3 | | H-Deformable-DETR-Swin-T + tricks | IN1k | 12 | 300 | 50.6 | | H-Deformable-DETR-Swin-T+ tricks | IN1k | 36 | 300 | 53.5 | | H-Deformable-DETR-Swin-L + tricks | IN22k | 12 | 300 | 56.2 | | H-Deformable-DETR-Swin-L + tricks | IN22k | 36 | 300 | 57.5 | | H-Deformable-DETR-Swin-L + tricks | IN22k | 12 | 900 | 56.4 | | H-Deformable-DETR-Swin-L + tricks | IN22k | 36 | 900 | 57.7 |

DINO

| Method | Pretrained | Epochs | Box AP | |:---|:---:|:---:|:---:| | DINO-R50-4Scale-12ep | IN1k | 12 | 49.2 |

DAB-Deformable-DETR

| Method | Pretrained | Epochs | Box AP | |:---|:---:|:---:|:---:| | DAB-Deformable-DETR-R50 | IN1k | 50 | 49.0 | | DAB-Deformable-DETR-R50-Two-Stage | IN1k | 50 | 49.7 |

- Python
Published by rentainhe over 3 years ago

detrex - detrex v0.1.1 Release

What's New

New Pretrained Models

All the pretrained weights can be downloaded in detrex Model Zoo.

DINO

| Method | Pretrained | Epochs | Box AP | |:-----|:-----:|:-----:|:-----:| | DINO-R50-4Scale | IN1k | 24 | 50.60 | | DINO-R101-4Scale | IN1k | 12 | 49.95 | | DINO-Swin-Tiny-224-4Scale | IN1k | 12 | 51.30 | | DINO-Swin-Tiny-224-4Scale | IN22k to IN1k | 12 | 51.30 | | DINO-Swin-Small-224-4Scale | IN1k | 12 | 52.96 | | DINO-Swin-Base-384-4Scale | IN22k to IN1k | 12 | 55.83 | | DINO-Swin-Large-224-4Scale | IN22k to IN1k | 12 | 56.92 | | DINO-Swin-Large-384-4Scale | IN22k to IN1k | 12 | 56.93 |

Deformable-DETR

| Method | Pretrained | Epochs | Box AP | |:-----|:-----:|:-----:|:-----:| | Deformable-DETR-R50 + Box-Refinement | IN1k | 50 | 46.99 | | Deformable-DETR-R50 + Box-Refinement + Two-Stage | IN1k | 50 | 48.19 |

- Python
Published by rentainhe over 3 years ago