an experiment for yolo-v1, including training and testing.
This is a experimental repository, which are not exactly the same as the original paper, our performance on voc07test is 0.665 map, 57fps@1080ti
I write this code for the purpose of learning. In yoloLoss.py, i write forward only, with autograd mechanism, backward will be done automatically.
For the convenience of using pytorch pretrained model, our backbone network is resnet50, add an extra block to increase the receptive field, in addition, we drop Fully connected layer.
Effciency has not been optimized. It may be faster... I don't know
model | backbone | map@voc2007test | FPS |
---|---|---|---|
our ResNet_YOLO | ResNet50 | 66.5% | 57 |
YOLO | darknet19? | 63.4% | 45 |
YOLO VGG-16 | VGG-16 | 66.4% | 21 |
Run python train.py
Be careful: 1. change the image file path 2. I recommend you install visdom and run it
Run python eval_voc.py
be careful 1. change the image file path
Our map in voc2007 test set is 0.665~ some result are below, you can see more in testimg folder.