Training on custom dataset

[EslamHaourn]

What should I do with this piece of code when I want to train my dataset imgIds = [int(Path(x).stem) for x in dataloader.dataset.img_files] cocoGt = COCO(glob.glob('../coco/annotations/instances_val* .json')[0]) #initialize COCO ground truth api cocoDt = cocoGt.loadRes(f) # initialize COCO pred api cocoEval = COCOeval(cocoGt, cocoDt, 'bbox') cocoEval.params.imgIds = imgIds # image IDs to evaluate cocoEval.evaluate() cocoEval.accumulate() cocoEval.summarize() map, map50 = cocoEval.stats[:2] #update results ([email protected]:0.95, [email protected])

Thanks

[parthkvv]

Same issue, want to train on custom dataset, what changes to make?