ssd.pytorch icon indicating copy to clipboard operation
ssd.pytorch copied to clipboard

How do you continue your epoch dataload when iteration %epoch_size==0?

Open onbigion13 opened this issue 5 years ago • 1 comments

In you code, I see that you do the running loop by the iterating of the variable "iteration" from "args.start_iter" to "cfg['max_iter']". but I see that the declaration of dataloader—— data_loader = data.DataLoader(dataset, args.batch_size, num_workers=args.num_workers, shuffle=True, collate_fn=detection_collate, pin_memory=True). there's nothing special of the dataset VOC0712's declaration. so how do you continue feeding new batches into the model when iteration % epoch_size==0??? it puzzled me few days. I cannot find where you handle the dataloading when itertation%epoch_size==0.

onbigion13 avatar Nov 26 '20 09:11 onbigion13

@onbigion13 have you understand this issue ?

FathiMahdi avatar Jun 09 '21 09:06 FathiMahdi