Closed saxg closed 4 years ago
I test the code of one shot and the results of each clip are the same as the mask of the ground truth of the first frame. Maybe there is some trouble in the code of eval_previous_mask.py
This is very strange. Have you used the one-shot pre-trained model or have you trained the model for your own dataset?
Best regards,
Carles
I test the code of one shot and the results of each clip are the same as the mask of the ground truth of the first frame. Maybe there is some trouble in the code of eval_previous_mask.py