amdegroot / ssd.pytorch

A PyTorch Implementation of Single Shot MultiBox Detector
MIT License
5.14k stars 1.75k forks source link

How do you continue your epoch dataload when iteration %epoch_size==0? #529

Open onbigion13 opened 3 years ago

onbigion13 commented 3 years ago

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.

FathiMahdi commented 3 years ago

@onbigion13 have you understand this issue ?