def infer(valid_queue, model, criterion):
objs = utils.AvgrageMeter()
top1 = utils.AvgrageMeter()
top5 = utils.AvgrageMeter()
model.eval()
args = get_darts_args()
with torch.no_grad():
for step, (input, target) in enumerate(valid_queue):
input = input.cuda()
target = target.cuda(non_blocking=True)
logits = model(input)
loss = criterion(logits, target)
prec1, prec5 = utils.accuracy(logits, target, topk=(1, 5))
n = input.size(0)
objs.update(loss.data.item(), n)
top1.update(prec1.data.item(), n)
top5.update(prec5.data.item(), n)
if step % args['report_freq'] == 0:
logging.info('valid %03d %e %f %f', step, objs.avg, top1.avg,
top5.avg)
return top1.avg, objs.avg
def train(train_queue, valid_queue, model, architect, criterion, optimizer, lr,
epoch):
objs = utils.AvgrageMeter()
top1 = utils.AvgrageMeter()
top5 = utils.AvgrageMeter()
args = get_darts_args()
for step, (input, target) in enumerate(train_queue):
model.train()
n = input.size(0)
input = input.cuda()
target = target.cuda(non_blocking=True)
# get a random minibatch from the search queue with replacement
#input_search, target_search = next(iter(valid_queue))
try:
input_search, target_search = next(valid_queue_iter)
except:
valid_queue_iter = iter(valid_queue)
input_search, target_search = next(valid_queue_iter)
input_search = input_search.cuda()
target_search = target_search.cuda(non_blocking=True)
if epoch >= 15:
architect.step(input,
target,
input_search,
target_search,
lr,
optimizer,
unrolled=args['unrolled'])
optimizer.zero_grad()
logits = model(input)
loss = criterion(logits, target)
loss.backward()
nn.utils.clip_grad_norm(model.parameters(), args['grad_clip'])
optimizer.step()
prec1, prec5 = utils.accuracy(logits, target, topk=(1, 5))
objs.update(loss.data.item(), n)
top1.update(prec1.data.item(), n)
top5.update(prec5.data.item(), n)
if step % args['report_freq'] == 0:
logging.info('train %03d %e %f %f', step, objs.avg, top1.avg,
top5.avg)
return top1.avg, objs.avg
default=0,
help='Experiment number',
type=str)
cmdline_parser.add_argument('-v', '--verbose',
default='INFO',
choices=['INFO', 'DEBUG'],
help='verbosity')
args, unknowns = cmdline_parser.parse_known_args()
log_lvl = logging.INFO if args.verbose == 'INFO' else logging.DEBUG
logging.basicConfig(level=log_lvl)
if unknowns:
logging.warning('Found unknown arguments!')
logging.warning(str(unknowns))
logging.warning('These will be ignored')
darts_args = get_darts_args()
darts_args['seed'] = args.seed
exp_name = f'EXP{str(args.exp_no)}'
exp_dir = f"./{exp_name}"
if not os.path.exists(exp_dir):
os.mkdir(exp_dir)
darts(exp_name, darts_args)
# _ = main(
# bohb_config,
# data_dir=settings.data_dir,
# num_epochs=int(20),
# batch_size=bohb_config['batch_size'],
# learning_rate=bohb_config['learning_rate'],
# train_criterion=settings.loss_dict[bohb_config['training_loss']],
# model_optimizer=settings.opti_dict[bohb_config['optimizer']],
# data_augmentations=None,