def infer(valid_queue, model, criterion, drop_path_prob):
objs = utils.AvgrageMeter()
top1 = utils.AvgrageMeter()
top5 = utils.AvgrageMeter()
model.eval()
for step, (input, target) in enumerate(valid_queue):
# with torch.cuda.device(0):
input = Variable(input, volatile=True).cuda()
# target = Variable(target, volatile=True).cuda(async=True)
target = Variable(target, volatile=True).cuda()
#
# input = Variable(input, volatile=True)
# target = Variable(target, volatile=True)
logits, _ = model(input, drop_path_prob)
loss = criterion(logits, target)
prec1, prec5 = utils.accuracy(logits, target, topk=(1, 5))
n = input.size(0)
objs.update(loss.data[0], n)
top1.update(prec1.data[0], n)
top5.update(prec5.data[0], n)
# if step == 1:
# return top1.avg, objs.avg
if step % 50 == 0:
print('valid {} {} {} {}'.format(step, objs.avg, top1.avg, top5.avg))
return top1.avg, objs.avg
def train(train_queue, model, criterion, optimizer):
objs = utils.AvgrageMeter()
top1 = utils.AvgrageMeter()
top5 = utils.AvgrageMeter()
model.train()
for step, (input, target) in enumerate(train_queue):
input = Variable(input).cuda()
target = Variable(target).cuda(async=True)
#
# input = Variable(input)
# target = Variable(target)
optimizer.zero_grad()
logits, logits_aux = model(input)
loss = criterion(logits, target)
if AUXILIARY:
loss_aux = criterion(logits_aux, target)
loss += 0.4 * loss_aux
loss.backward()
nn.utils.clip_grad_norm(model.parameters(), 5)
optimizer.step()
prec1, prec5 = utils.accuracy(logits, target, topk=(1, 5))
n = input.size(0)
objs.update(loss.data[0], n)
top1.update(prec1.data[0], n)
top5.update(prec5.data[0], n)
if step % 50 == 0:
print(loss.data[0])
print('train {} {} {} {}'.format(step, objs.avg, top1.avg,
top5.avg))
return top1.avg, objs.avg
