1、导入需要的模块并传入数据集import mindspore.dataset as dsimport mindspore.dataset.transforms.c_transforms as Cimport mindspore.dataset.vision.c_transforms as CVfrom mindspore import nn, Tensor, Modelfrom mindspore import dtype as mstypeDATA_DIR = "./datasets/cifar-10-batches-bin/train"
2、定义神经网络class Net(nn.Cell): 蟠校盯昂def __init__(self, num_class=10, num_channel=3): super(Net, self).__init__() self.conv1 = nn.Conv2d(num_channel, 6, 5, pad_mode='valid') self.conv2 = nn.Conv2d(6, 16, 5, pad_mode='valid') self.fc1 = nn.Dense(16 * 5 * 5, 120) self.fc2 = nn.Dense(120, 84) self.fc3 = nn.Dense(84, num_class) self.relu = nn.ReLU() self.max_pool2d = nn.MaxPool2d(kernel_size=2, stride=2) self.flatten = nn.Flatten() def construct(self, x): x = self.conv1(x) x = self.relu(x) x = self.max_pool2d(x) x = self.conv2(x) x = self.relu(x) x = self.max_pool2d(x) x = self.flatten(x) x = self.fc1(x) x = self.relu(x) x = self.fc2(x) x = self.relu(x) x = self.fc3(x) return xnet = Net()epochs = 5batch_size = 64learning_rate = 1e-3
3、构建数据集衡痕贤伎sampler = ds.SequentialSampler(num_samples=128)dataset = ds.Cif锾攒揉敫ar10Dataset(DATA_DIR, sampler=sampler)数据类型转换type_cast_op_image = C.TypeCast(mstype.float32)type_cast_op_label = C.TypeCast(mstype.int32)HWC2CHW = CV.HWC2CHW()dataset = dataset.map(operations=[type_cast_op_image, HWC2CHW], input_columns="image")dataset = dataset.map(operations=type_cast_op_label, input_columns="label")dataset = dataset.batch(batch_size)
4、定义超参、损失函数及优化器optim = nn.SGD(params=net.trainable_params(), learning_rate=learning_rate)loss = nn.SoftmaxCrossEntropyWithLogits(sparse=True, reduction='mean')
5、输入训练轮次和数据集进行训练model = Model(net, loss_fn=loss, optimizer=optim)model.train(epoch=epochs, train_dataset=dataset)