SOLOv2
The code is an unofficial pytorch implementation of SOLOv2: Dynamic, Faster and Stronger
Install
Please check SOLOv1 for installation instructions.
Training
Follows the same way as SOLOv1.
single GPU:
python tools/train.py configs/solov2/solov2_r101_3x.py
multi GPU (for example 8):
./tools/dist_train.sh configs/solov2/solov2_r101_3x.py 8
Weights
Trained model can be download in Google drive BaiduYun ๆๅ็ : qw4e
Results
After training 36 epochs(3x) on the coco dataset using the resnet-101 backbone, the mAP is 39.5 on COCO test-dev2017 dataset. In the original paper, the model achieves 39.7 after 72 epochs(6x).
Visualization๏ผ1 epoch)
