336-end-to-end-object-detection-with-transformers

https://github.com/szu-advtech-2024/336-end-to-end-object-detection-with-transformers

Science Score: 31.0%

This score indicates how likely this project is to be science-related based on various indicators:

✓
CITATION.cff file
Found CITATION.cff file
✓
codemeta.json file
Found codemeta.json file
○
.zenodo.json file
○
DOI references
○
Academic publication links
○
Academic email domains
○
Institutional organization owner
○
JOSS paper metadata
○
Scientific vocabulary similarity
Low similarity (3.3%) to scientific vocabulary

Last synced: 10 months ago · JSON representation ·

Repository

Basic Info

Host: GitHub
Owner: SZU-AdvTech-2024
Default Branch: main
Size: 0 Bytes

Statistics

Stars: 0
Watchers: 0
Forks: 0
Open Issues: 0
Releases: 0

Created over 1 year ago · Last pushed over 1 year ago

Metadata Files

Citation

https://github.com/SZU-AdvTech-2024/336-End-to-End-Object-Detection-with-Transformers/blob/main/

detr

[detr](https://github.com/facebookresearch/detr)

[coco](https://cocodataset.org/)

```
path/to/coco/
  annotations/  # annotation json files
  train2017/    # train images
  val2017/      # val images
```



0detrmain.py

```
python  main.py --coco_path /detr/path/ --epochs 50 --lr 0.125e-4 --lr_backbone 0.125e-5
python -m torch.distributed.launch --nproc_per_node=1 --use_env main.py --coco_path /coco/ --epochs 50 --lr 0.125e-4 --lr_backbone 0.125e-5 --batch_size 16 --output_dir result-model
```

premodel

```
python -m torch.distributed.launch --nproc_per_node=1 --use_env main.py \
    --coco_path /coco/ --epochs 20 --lr 0.125e-4 --lr_backbone 0.125e-5 --batch_size 8 \
    --resume /premodel/detr-r50-e632da11.pth --output_dir result-model
```

[voc](https://pjreddie.com/projects/pascal-voc-dataset-mirror/)voctococo.pyvoccoco

```
python -m torch.distributed.launch --nproc_per_node=1 --use_env main.py \
    --coco_path /coco2 --epochs 20 --lr 0.125e-4 --lr_backbone 0.125e-5 --batch_size 8 \
    --resume /premodel/detr-r50-e632da11.pth --output_dir result-model
```

[detr](https://github.com/NielsRogge/Transformers-Tutorials/blob/master/DETR/Fine_tuning_DetrForObjectDetection_on_custom_dataset_(balloon).ipynb) `StepLR` 

[balloon](https://github.com/matterport/Mask_RCNN/releases/download/v2.1/balloon_dataset.zip)VIA2COCOto.py

```
path/to/ballon/
  train/    # train images and custom_train.json
  val/      # val images and custom_val.json
```



```
eval.py  #
Detr.py  #
Detr2.py #Detr.py
detr_interrupt_controller.py #
promptTuning.py  #,
Dataset/dataset.py #
inference.py  #
```

Owner

Name: SZU-AdvTech-2024
Login: SZU-AdvTech-2024
Kind: organization

Repositories: 1
Profile: https://github.com/SZU-AdvTech-2024

Citation (citation.txt)

@inproceedings{REPO336,
    author = "Carion, Nicolas and Massa, Francisco and Synnaeve, Gabriel and Usunier, Nicolas and Kirillov, Alexander and Zagoruyko, Sergey",
    booktitle = "European conference on computer vision",
    organization = "Springer",
    pages = "213--229",
    title = "{End-to-end object detection with transformers}",
    year = "2020"
}

ecosyste.ms

Data

Tools

Indexes

Applications

Experiments

Open Source Science