if not torch.cuda.is_available():
logging.info('no gpu device available')
sys.exit(1)
cudnn.benchmark = True
cudnn.enabled = True
if config.train_params.use_seed:
utils.set_seed(config.train_params.seed)
logging.info("args = %s", args)
logging.info('Training with config:')
logging.info(pprint.pformat(config))
if os.path.isfile(os.path.join(args.load_path, 'net_config')):
config.net_config, config.net_type = utils.load_net_config(
os.path.join(args.load_path, 'net_config'))
derivedNetwork = getattr(model_derived, '%s_Net' % config.net_type.upper())
model = derivedNetwork(config.net_config, config=config)
model.eval()
if hasattr(model, 'net_config'):
logging.info("Network Structure: \n" +
'|\n'.join(map(str, model.net_config)))
if args.meas_lat:
latency_cpu = utils.latency_measure(model, (3, 224, 224),
1,
2000,
mode='cpu')
logging.info('latency_cpu (batch 1): %.2fms' % latency_cpu)
latency_gpu = utils.latency_measure(model, (3, 224, 224),
32,
def main():
args = parse_args()
if args.out is not None and not args.out.endswith(('.pkl', '.pickle')):
raise ValueError('The output file must be a pkl file.')
cfg = mmcv.Config.fromfile(args.config)
# set cudnn_benchmark
if cfg.get('cudnn_benchmark', False):
torch.backends.cudnn.benchmark = True
cfg.model.pretrained = None
cfg.data.test.test_mode = True
if args.net_config is not None:
cfg.model.backbone.net_config = utils.load_net_config(args.net_config)
utils.set_data_path(args.data_path, cfg.data)
dataset = obj_from_dict(cfg.data.test, datasets, dict(test_mode=True))
if args.gpus == 1:
model = build_detector(cfg.model,
train_cfg=None,
test_cfg=cfg.test_cfg)
load_checkpoint(model, args.checkpoint)
model = MMDataParallel(model, device_ids=[0])
data_loader = build_dataloader(
dataset,
imgs_per_gpu=1,
workers_per_gpu=cfg.data.workers_per_gpu,
num_gpus=1,
dist=False,
shuffle=False)
outputs = single_test(model, data_loader, args.show)
else:
model_args = cfg.model.copy()
model_args.update(train_cfg=None, test_cfg=cfg.test_cfg)
model_type = getattr(detectors, model_args.pop('type'))
outputs = parallel_test(model_type,
model_args,
args.checkpoint,
dataset,
_data_func,
range(args.gpus),
workers_per_gpu=args.proc_per_gpu)
if args.out:
print('writing results to {}'.format(args.out))
mmcv.dump(outputs, args.out)
eval_types = args.eval
if eval_types:
print('Starting evaluate {}'.format(' and '.join(eval_types)))
if eval_types == ['proposal_fast']:
result_file = args.out
coco_eval(result_file, eval_types, dataset.coco)
else:
if not isinstance(outputs[0], dict):
result_file = args.out + '.json'
results2json(dataset, outputs, result_file)
coco_eval(result_file, eval_types, dataset.coco)
else:
for name in outputs[0]:
print('\nEvaluating {}'.format(name))
outputs_ = [out[name] for out in outputs]
result_file = args.out + '.{}.json'.format(name)
results2json(dataset, outputs_, result_file)
coco_eval(result_file, eval_types, dataset.coco)