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✨ .
16 Dec 07, 2022
245 Dec 20, 2022
1.1k Jan 02, 2023
102 Dec 30, 2022
173 Dec 25, 2022
45 Aug 27, 2022
194 Dec 27, 2022
39 Oct 12, 2022
4 Dec 26, 2021
11 Dec 17, 2022
31 Jan 08, 2023
2.4k Dec 31, 2022
11 Sep 23, 2022
270 Nov 30, 2022
0 Dec 01, 2021
1.4k Dec 28, 2022
26 Oct 05, 2022
124 Dec 20, 2022
29 May 25, 2022
12 Dec 14, 2022