This is a PyTorch version of Faster R-CNN, origin code is here
-
Clone this repository
git clone https://github.com/Detection-Learner/PyTorch-Faster-R-CNN.git
-
Choose your
-archoption to match your GPU.
| GPU model | Architecture |
|---|---|
| TitanX (Maxwell/Pascal) | sm_52 |
| Titan Black | sm_35 |
| GTX 960M | sm_50 |
| GTX 1080 (Ti) | sm_61 |
| Grid K520 (AWS g2.2xlarge) | sm_30 |
| Tesla K80 (AWS p2.xlarge) | sm_37 |
-
Run
tools/make.shscriptsh tools/make.sh "your GPU architecture"Note: default arch is "sm_35".