how do i get only region of object or do i have to process the image that output network?

imatge-upc / rvos

RVOS: End-to-End Recurrent Network for Video Object Segmentation (CVPR 2019)

https://imatge-upc.github.io/rvos/

Other

277 stars 54 forks source link

how do i get only region of object or do i have to process the image that output network? #18

Open Quezar opened 5 years ago

carlesventura commented 5 years ago

Could you explain with more detail the problem you have?

Regards,

Carles

Quezar commented 5 years ago

Hi Carles

The output of algorithm are frames with the object segmented in the same image. I need get just the object's region (parameters) or object segmented that the program is tracking on the frames without the whole image. Is there any way to get just parameters of object?

Regards

carlesventura commented 5 years ago

If you check the code from eval_previous_mask.py, you will find that the masks for each instance are also saved as binary images in a folder named masks_sep_2assess. This folder should be generated under your model folder, in the same place that the folder named results is also generated.

Best regards,

Carles