The ideal should be by including a parameter that allows to choose the image resolution at which you want to train the model. However, in the current implementation, you should change the following code in train.py for zero-shot (see inputRes argument):
The ideal should be by including a parameter that allows to choose the image resolution at which you want to train the model. However, in the current implementation, you should change the following code in train.py for zero-shot (see inputRes argument):
The same should be done for one-shot in train_previous_mask.py and train_previous_inference_mask.py.
Best regards,
Carles