Closed Sucran closed 6 years ago
Actually it is a approximate value. You can test your model on some dataset, say MSRA-B, and report the average time on each image. It seems the speed is not that important.
If you want an exact value, we can resize all the images of some dataset to size 300 * 400.
I had read many CVPR2017 paper related to saliency detection, your model and NLDF(Non-Local Deep Features for Salient Object Detection) all say the processing time == 0.08s, but the model and DL framwork(TF vs Caffe) are different, which should cause a bit different. This makes me confused. Can you upload an simple ipynb file to explain how the 0.08s to be computed ? or just tell me your method if it's easy to implement. Thank you very much.