RetinaNet
An implementation of RetinaNet in PyTorch.
Installation
- Install PyTorch and torchvision.
- For faster data augmentation, install pillow-simd:
pip uninstall -y pillow
pip install pillow-simd
Training
COCO 2017
- First, install pycocotools:
git clone https://github.com/pdollar/coco/
cd coco/PythonAPI
make
python setup.py install
cd ../..
rm -r coco
- Then download COCO 2017 into
./datasets/COCO/:
cd datasets
mkdir COCO
cd COCO
If your using wget:
wget http://images.cocodataset.org/zips/train2017.zip &&
wget http://images.cocodataset.org/zips/val2017.zip &&
wget http://images.cocodataset.org/annotations/annotations_trainval2017.zip
If your using aria2c (recommended on for higher bandwidth connections and for allowing resumption of the download. Tune the number of max concurrent downloads (-j) and max connections per server (-x) as needed:
aria2c -x 10 -j 10 http://images.cocodataset.org/zips/train2017.zip &&
aria2c -x 10 -j 10 http://images.cocodataset.org/zips/val2017.zip &&
aria2c -x 10 -j 10 http://images.cocodataset.org/annotations/annotations_trainval2017.zip
unzip *.zip
rm *.zip
Then just run:
python train_coco.py
Pascal VOC
cd datasets
mkdir VOC
cd VOC
wget http://host.robots.ox.ac.uk/pascal/VOC/voc2007/VOCtrainval_06-Nov-2007.tar &&
wget http://host.robots.ox.ac.uk/pascal/VOC/voc2012/VOCtrainval_11-May-2012.tar &&
wget http://host.robots.ox.ac.uk/pascal/VOC/voc2007/VOCtest_06-Nov-2007.tar
If your using aria2c (recommended on for higher bandwidth connections and for allowing resumption of the download. Tune the number of max concurrent downloads (-j) and max connections per server (-x) as needed:
aria2c -x 10 -j 10 http://host.robots.ox.ac.uk/pascal/VOC/voc2007/VOCtrainval_06-Nov-2007.tar &&
aria2c -x 10 -j 10 http://host.robots.ox.ac.uk/pascal/VOC/voc2012/VOCtrainval_11-May-2012.tar &&
aria2c -x 10 -j 10 http://host.robots.ox.ac.uk/pascal/VOC/voc2007/VOCtest_06-Nov-2007.tar
tar xf *.tar
rm *.tar
Then just run:
python train_voc.py
Custom Dataset
Lots to write here.
Evaluation
To evaluate an image on a trained model:
python eval.py [checkpoint_path] [image_path]
This will create an image (output.jpg) with bounding box annotations.
Todo
- Finish converting the COCO dataset class to work with batches.
- Train COCO 2017 for 90,000 iterations and save a reusable checkpoint.
- Try training on Pascal VOC and add download instructions.
- Produce bounding box outputs for a few sanity check images.
- Upload trained weights to Github releases.
- Train on the
🔮 magic proprietary dataset✨ .
95 Nov 22, 2022
38 Dec 12, 2022
856 Jan 06, 2023
30 Nov 18, 2022
1.3k Jan 03, 2023
1.3k Jan 03, 2023
46 Oct 30, 2022
197 Nov 29, 2022
87 Sep 13, 2022
16 Aug 14, 2022
58 Oct 26, 2022
18 Jan 03, 2023
79 Dec 30, 2022
97 Dec 20, 2022
50 Dec 30, 2022
96 Dec 12, 2022
3 Sep 26, 2022
147 Jan 06, 2023
6 Apr 18, 2022
114 Dec 10, 2022