Open prayagpawar opened 3 months ago
Yes, it is possible to automate the training process in Detectron2 to some extent, similar to how YOLOv8 does it, but it requires setting up a custom training loop that can monitor the validation loss and determine the optimal number of training steps.
Just like yolov8 is it possible for detectron2 to automate and export perfectly trained steps , As of now we are required to provide number of steps check for detection if not found train again , In yolov8 you just pass on the batch size and the training starts and it exports optimum model by checking validation loss .