How to support single-image input for inference?

[AlphaPlusTT]

In the context of Occ related tasks, why do some works support single-image input for inference, while others require multiple images for inference? What is the key factor causing this difference?

[codeimdy]

Hello, after completing the first phase of training, how should I proceed with the second phase? Are there any additional steps required, or do I only need to enter the training command in the terminal? Directly entering the training command results in an error, as shown in the picture.