def main():
args = parser.parse_args()
print_arguments(args)
check_cuda(args.use_gpu)
data_dir = args.data_dir
dataset = args.dataset
assert dataset in ['pascalvoc', 'coco2014', 'coco2017']
# for pascalvoc
label_file = 'label_list'
train_file_list = 'trainval.txt'
val_file_list = 'test.txt'
if dataset == 'coco2014':
train_file_list = 'annotations/instances_train2014.json'
val_file_list = 'annotations/instances_val2014.json'
elif dataset == 'coco2017':
train_file_list = 'annotations/instances_train2017.json'
val_file_list = 'annotations/instances_val2017.json'
mean_BGR = [float(m) for m in args.mean_BGR.split(",")]
image_shape = [int(m) for m in args.image_shape.split(",")]
train_parameters[dataset]['image_shape'] = image_shape
train_parameters[dataset]['batch_size'] = args.batch_size
train_parameters[dataset]['lr'] = args.learning_rate
train_parameters[dataset]['epoc_num'] = args.epoc_num
train_parameters[dataset]['ap_version'] = args.ap_version
data_args = reader.Settings(dataset=args.dataset,
data_dir=data_dir,
label_file=label_file,
resize_h=image_shape[1],
resize_w=image_shape[2],
mean_value=mean_BGR,
apply_distort=True,
apply_expand=True,
ap_version=args.ap_version)
train(args,
data_args,
train_parameters[dataset],
train_file_list=train_file_list,
val_file_list=val_file_list)
def main():
args = parser.parse_args()
print_arguments(args)
check_cuda(args.use_gpu)
train_async(args)
def main(args):
devices = os.getenv("CUDA_VISIBLE_DEVICES") or ""
devices_num = len(devices.split(","))
startup_prog = fluid.Program()
infer_prog = fluid.Program()
infer_fetch_list = build_program(
main_prog=infer_prog, startup_prog=startup_prog, args=args)
infer_prog = infer_prog.clone(for_test=True)
place = fluid.CUDAPlace(0) if args.use_gpu else fluid.CPUPlace()
exe = fluid.Executor(place)
exe.run(startup_prog)
valid_reader = reader.train_valid(
batch_size=args.batch_size, is_train=False, is_shuffle=False, args=args)
fluid.io.load_persistables(exe, args.model_dir, main_program=infer_prog)
infer_prog = fluid.CompiledProgram(infer_prog)
top1 = infer(infer_prog, exe, valid_reader, infer_fetch_list, args)
logger.info("test_acc {:.6f}".format(top1))
if __name__ == '__main__':
args = parser.parse_args()
utility.print_arguments(args)
utility.check_cuda(args.use_gpu)
main(args)
def main():
paddle.enable_static()
args = parser.parse_args()
print_arguments(args)
check_cuda(args.use_gpu)
eval(args)
def main():
args = parser.parse_args()
print_arguments(args)
check_cuda(args.use_gpu)
infer(args)
batch_id = 0
while True:
test_map, = exe.run(test_prog, fetch_list=[accum_map])
if batch_id % 10 == 0:
print("Batch {0}, map {1}".format(batch_id, test_map))
batch_id += 1
except (fluid.core.EOFException, StopIteration):
test_py_reader.reset()
print("Test model {0}, map {1}".format(model_dir, test_map))
if __name__ == '__main__':
args = parser.parse_args()
print_arguments(args)
check_cuda(args.use_gpu)
data_dir = 'data/pascalvoc'
test_list = 'test.txt'
label_file = 'label_list'
if not os.path.exists(args.model_dir):
raise ValueError("The model path [%s] does not exist." %
(args.model_dir))
if 'coco' in args.dataset:
data_dir = 'data/coco'
if '2014' in args.dataset:
test_list = 'annotations/instances_val2014.json'
elif '2017' in args.dataset:
test_list = 'annotations/instances_val2017.json'
def main():
paddle.enable_static()
args = parser.parse_args()
print_arguments(args)
check_cuda(args.use_gpu)
save_inference_model(args)
