return cifar_ds
if __name__ == '__main__':
args_opt = parse_args()
context.set_context(mode=context.GRAPH_MODE,
device_target=args_opt.device_target)
# download cifar10 dataset
if not args_opt.dataset_path:
args_opt.dataset_path = download_dataset('cifar10')
# build the network
if args_opt.do_eval and args_opt.load_pretrained == 'hub':
from tinyms import hub
net = hub.load(args_opt.hub_uid, class_num=args_opt.num_classes)
else:
net = vgg16(class_num=args_opt.num_classes)
net.update_parameters_name(prefix='huawei')
model = Model(net)
# define the loss function
net_loss = SoftmaxCrossEntropyWithLogits(sparse=True, reduction="mean")
# define the optimizer
net_opt = Momentum(filter(lambda x: x.requires_grad, net.get_parameters()),
0.01, 0.9)
model.compile(loss_fn=net_loss,
optimizer=net_opt,
metrics={"Accuracy": Accuracy()})
epoch_size = args_opt.epoch_size
batch_size = args_opt.batch_size
return mnist_ds
if __name__ == "__main__":
args_opt = parse_args()
context.set_context(mode=context.GRAPH_MODE,
device_target=args_opt.device_target)
# download mnist dataset
if not args_opt.dataset_path:
args_opt.dataset_path = download_dataset('mnist')
# build the network
if args_opt.do_eval and args_opt.load_pretrained == 'hub':
from tinyms import hub
net = hub.load(args_opt.hub_uid)
else:
net = lenet5()
model = Model(net)
# define the loss function
net_loss = SoftmaxCrossEntropyWithLogits(sparse=True, reduction='mean')
# define the optimizer
net_opt = Momentum(net.trainable_params(), 0.01, 0.9)
model.compile(net_loss, net_opt, metrics={"Accuracy": Accuracy()})
epoch_size = args_opt.epoch_size
batch_size = args_opt.batch_size
mnist_path = args_opt.dataset_path
dataset_sink_mode = not args_opt.device_target == "CPU"
if args_opt.do_eval: # as for evaluation, users could use model.eval
model.train(epoch_size,
ds_train,
callbacks=[
ckpoint_cb,
LossMonitor(),
TimeMonitor(data_size=dataset_size)
],
dataset_sink_mode=dataset_sink_mode)
else: # as for evaluation, users could use model.eval
ds_eval = create_dataset(voc_path, batch_size=1, is_training=False)
total = ds_eval.get_dataset_size()
# define the infer wrapper
if args_opt.load_pretrained == 'hub':
from tinyms import hub
eval_net = hub.load(args_opt.hub_uid,
class_num=args_opt.num_classes,
is_training=False)
else:
eval_net = ssd300_mobilenetv2(class_num=args_opt.num_classes,
is_training=False)
model = Model(eval_net)
if args_opt.load_pretrained == 'local':
if args_opt.checkpoint_path:
model.load_checkpoint(args_opt.checkpoint_path)
# perform the model predict operation
print("\n========================================\n")
print("total images num: ", total)
print("Processing, please wait a moment...")
start = time.time()
pred_data = []
id_iter = 0
cifar10_path = args_opt.dataset_path
# set runtime environment
context.set_context(mode=context.GRAPH_MODE,
device_target=args_opt.device_target)
dataset_sink_mode = not args_opt.device_target == "CPU"
# create cifar10 dataset for training
ds_train = create_dataset(cifar10_path, batch_size=batch_size)
step_size = ds_train.get_dataset_size()
# build the network
if args_opt.do_eval and args_opt.load_pretrained == 'hub':
from tinyms import hub
net = hub.load(args_opt.hub_uid,
class_num=args_opt.num_classes,
is_training=not args_opt.do_eval)
else:
net = mobilenetv2(class_num=args_opt.num_classes,
is_training=not args_opt.do_eval)
model = Model(net)
# define the loss function
loss = CrossEntropyWithLabelSmooth(smooth_factor=args_opt.label_smooth,
num_classes=args_opt.num_classes)
# get learning rate
lr_max = 0.001
lr_init_scale = 0.01
lr_end_scale = 0.01
lr = mobilenetv2_lr(global_step=0,
lr_init=lr_max * lr_init_scale,
lr_end=lr_max * lr_end_scale,