There is CNN now imagenet pre-trained. I want to do some fine-tuning (re-training) on CNN. I do not think I need to run the imagenet training set at all, so I want to train every 100,000 samples per epoch. If I implement the following, is 100,000 samples sampled every epoch differently?
...
# Weight training
def weight_train(epoch):
print('\nWeight Training Epoch: %d' % epoch)
train_sampler = torch.utils.data.sampler.SubsetRandomSampler(indices[:split])
train_loader = torch.utils.data.DataLoader(train_dataset, batch_size=args.bs, sampler=train_sampler, num_workers=4, drop_last=False, pin_memory=True)
batch_time = AverageMeter()
data_time = AverageMeter()
losses = AverageMeter()
top1 = AverageMeter()
top5 = AverageMeter()
# switch to train model
model.train()
end = time.time()
for batch_idx, (inputs, targets) in enumerate(train_loader):
# measure data loading time
data_time.update(time.time() - end)
if use_cuda is not None:
inputs, targets = inputs.cuda(), targets.cuda()
# compute output
outputs = model(inputs)
loss = criterion(outputs, targets)
# measure accuracy and record loss
prec1, prec5 = accuracy(outputs, targets, topk=(1, 5))
losses.update(loss.item(), inputs.size(0))
top1.update(prec1[0], inputs.size(0))
top5.update(prec5[0], inputs.size(0))
# compute gradient and do SGD step
weight_optimizer.zero_grad()
loss.backward()
weight_optimizer.step()
# measure elapsed time
batch_time.update(time.time() - end)
end = time.time()
progress_bar(batch_idx, len(train_loader),
'Time {batch_time.val:.3f} ({batch_time.avg:.3f})\t'
'Data {data_time.val:.3f} ({data_time.avg:.3f})\t'
'Loss {loss.val:.4f} ({loss.avg:.4f})\t'
'Prec@1 {top1.val:.3f} ({top1.avg:.3f})\t'
'Prec@5 {top5.val:.3f} ({top5.avg:.3f})'.format(
batch_time=batch_time,
data_time=data_time, loss=losses, top1=top1, top5=top5))
...
for epoch in range(0,args.ne):
weight_train(epoch)