class CrossEntropy(_Loss):
    """CrossEntropy"""
    def __init__(self, smooth_factor=0., num_classes=1000):
        super(CrossEntropy, self).__init__()
        self.onehot = P.OneHot()
        self.on_value = Tensor(1.0 - smooth_factor, mstype.float32)
        self.off_value = Tensor(1.0 * smooth_factor / (num_classes - 1), mstype.float32)
        self.ce = nn.SoftmaxCrossEntropyWithLogits()
        self.mean = P.ReduceMean(False)

    def construct(self, logit, label):
        one_hot_label = self.onehot(label, F.shape(logit)[1], self.on_value, self.off_value)
        loss = self.ce(logit, one_hot_label)
        loss = self.mean(loss, 0)
        return loss

...
from src.crossentropy import CrossEntropy
...
if __name__ == "__main__":
    ...
    # define the loss function
    if not config.use_label_smooth:
        config.label_smooth_factor = 0.0
    loss = CrossEntropy(smooth_factor=config.label_smooth_factor, num_classes=config.class_num)
    ...

...
if args_opt.device_target == "Ascend":
    from src.thor import THOR
else:
    from src.thor import THOR_GPU as THOR
...

if __name__ == "__main__":
    ...
    # learning rate setting
    lr = get_model_lr(0, config.lr_init, config.lr_decay, config.lr_end_epoch, step_size, decay_epochs=39)
    # define the optimizer
    net_opt = opt = THOR(filter(lambda x: x.requires_grad, net.get_parameters()), Tensor(lr), config.momentum,
               filter(lambda x: 'matrix_A' in x.name, net.get_parameters()),
               filter(lambda x: 'matrix_G' in x.name, net.get_parameters()),
               filter(lambda x: 'A_inv_max' in x.name, net.get_parameters()),
               filter(lambda x: 'G_inv_max' in x.name, net.get_parameters()),
               config.weight_decay, config.loss_scale)
    ...

...
from mindspore.train.callback import ModelCheckpoint, CheckpointConfig, TimeMonitor, LossMonitor
...
if __name__ == "__main__":
    ...
    # define callbacks
    time_cb = TimeMonitor(data_size=step_size)
    loss_cb = LossMonitor()
    cb = [time_cb, loss_cb]
    if config.save_checkpoint:
        config_ck = CheckpointConfig(save_checkpoint_steps=config.save_checkpoint_epochs * step_size,
                                     keep_checkpoint_max=config.keep_checkpoint_max)
        ckpt_cb = ModelCheckpoint(prefix="resnet", directory=ckpt_save_dir, config=config_ck)
        cb += [ckpt_cb]
    ...

...
from mindspore.train.loss_scale_manager import FixedLossScaleManager
from src.model_thor import Model_Thor as Model
...

if __name__ == "__main__":
    ...
    loss_scale = FixedLossScaleManager(config.loss_scale, drop_overflow_update=False)
    if target == "Ascend":
        model = Model(net, loss_fn=loss, optimizer=opt, amp_level='O2', loss_scale_manager=loss_scale,
                      keep_batchnorm_fp32=False, metrics={'acc'}, frequency=config.frequency)
    else:
        model = Model(net, loss_fn=loss, optimizer=opt, loss_scale_manager=loss_scale, metrics={'acc'},
                      amp_level="O2", keep_batchnorm_fp32=True, frequency=config.frequency)
    ...

...
from mindspore.train.serialization import load_checkpoint, load_param_into_net
...

if __name__ == "__main__":
    ...
    # define net
    net = resnet(class_num=config.class_num)
    net.add_flags_recursive(thor=False)

    # load checkpoint
    param_dict = load_checkpoint(args_opt.checkpoint_path)
    keys = list(param_dict.keys())
    for key in keys:
        if "damping" in key:
            param_dict.pop(key)
    load_param_into_net(net, param_dict)
    net.set_train(False)

    # define model
    model = Model(net, loss_fn=loss, metrics={'top_1_accuracy', 'top_5_accuracy'})
	
    # eval model
    res = model.eval(dataset)
    print("result:", res, "ckpt=", args_opt.checkpoint_path)