search

scaelles / OSVOS-TensorFlow

One-Shot Video Object Segmentation
http://vision.ee.ethz.ch/~cvlsegmentation/osvos/
GNU General Public License v3.0
438 stars 132 forks source link

How can I use the pre-trained model for testing #25

Closed ferric123 closed 6 years ago

ferric123 commented 6 years ago

Hi, I am interested in this work and want to take look at the test result first. Could you please give me an instruction on how I can make use of your fine-tuned pre-trained model(if there is one could you put the link) to feed an arbitrary test image and see the segmented output?

scaelles commented 6 years ago

Hello, I would recommend that you start in the osvos_demo.py script. You have to input to the algorithm at least one frame with the corresponding annotated binary mask. After training for a while, you will be able to test with the rest of the frames of the video sequence. Let us know if you have any further question!

ferric123 commented 6 years ago

Hello, I would recommend that you start in the osvos_demo.py script. You have to input to the algorithm at least one frame with the corresponding annotated binary mask. After training for a while, you will be able to test with the rest of the frames of the video sequence. Let us know if you have any further question!

Okay,I will try that, thanks in advance!