The output from demo trained model seem uncorrect

CSAILVision / semantic-segmentation-pytorch

Pytorch implementation for Semantic Segmentation/Scene Parsing on MIT ADE20K dataset

http://sceneparsing.csail.mit.edu/

BSD 3-Clause "New" or "Revised" License

4.95k stars 1.1k forks source link

The output from demo trained model seem uncorrect #293

Open B-Paweekorn opened 5 months ago

B-Paweekorn commented 5 months ago

ADE_val_00001519

I'm attempting to run the demo in a Docker environment with the following specifications: Ubuntu 16.04, Python 3.5, CUDA 8.0, and PyTorch 0.4.0. However, it appears that the segmentation isn't functioning as expected.