search

vpulab / Semantic-Aware-Scene-Recognition

Code repository for paper https://www.sciencedirect.com/science/article/pii/S0031320320300613 @ Pattern Recognition 2020
MIT License
102 stars 17 forks source link

how to test model on new images #27

Closed vaibhavkale20009 closed 1 year ago

vaibhavkale20009 commented 2 years ago

how can i modify code to input a image and get the semantics as output

alexlopezcifuentes commented 2 years ago

Hi!

We don't provide a specific Semantic Segmentation code to obtain the semantics, we just provide the semantic segmentations extracted by PSPNet used to obtain the results from the paper.

You can use any Semantic Segmentation CNN of your choice. You just have to save the top3 labels and top3 scores leveraging the 3 channels of an RGB image.

Alex.