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 COCOIf 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.zipIf 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 *.zipThen just run:
python train_coco.py
Pascal VOC
cd datasets
mkdir VOC
cd VOCwget 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.tarIf 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 *.tarThen just run:
python train_voc.pyCustom 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✨ .