all projects
shippedpytorchcomputer-visiontensorrt
Facial Expression Recognition
ResNet + U-Net hybrid for real-time emotion detection, optimised with TensorRT for video. Highest accuracy on FER2013 in the cohort.
- FER2013 accuracy
- 77%
- venue
- BCS · IIT Kanpur
What it is
A PyTorch model combining ResNet + U-Net masking blocks for facial-expression classification on FER2013, then optimised for real-time video inference.
What I shipped
- Implemented and trained the ResNet/U-Net hybrid; reached 77% accuracy on FER2013 - highest in my Brain & Cognitive Society cohort.
- Optimised the inference path with TensorRT for low-latency real-time video emotion detection.
- Combined LFFD and OpenCV for fast face detection in the pipeline.