Support of the training-independent inference script with pre-trained model

VITA-Group / FasterSeg

[ICLR 2020] "FasterSeg: Searching for Faster Real-time Semantic Segmentation" by Wuyang Chen, Xinyu Gong, Xianming Liu, Qian Zhang, Yuan Li, Zhangyang Wang

MIT License

524 stars 107 forks source link

Support of the training-independent inference script with pre-trained model #43

Closed rose-jinyang closed 3 years ago

rose-jinyang commented 3 years ago

Hello How are you? Thanks for contributing this project. I think that the inference with pre-trained model is dependent on training dataset. Could u provide an independent script for test inference? Thanks.

chenwydj commented 3 years ago

Hi @rose-jinyang! Thank you for your interest in our work!

Please see the configurations here to switch to either evaluation (compute mIoU against your ground truth) or test (no ground truth available, just output the prediction files).