vpulab / Semantic-Aware-Scene-Recognition

Code repository for paper https://www.sciencedirect.com/science/article/pii/S0031320320300613 @ Pattern Recognition 2020
MIT License
100 stars 16 forks source link

How to test this model? #22

Closed rohanakut closed 3 years ago

rohanakut commented 3 years ago

Thank you for the amazing repo However, it appears as if this repo is used for training the model. is it possible to create a file that just takes the input image and generates an output from the trained model?

alexlopezcifuentes commented 3 years ago

Hi!

The repo is precisly for evaluating the model not for training. If you want to extract results for a single image you can create your own script using fragments of the code, however, you can get the same results using batch_size=1