昇思25天学习打卡营第2天|Mindspore入门

学习目标：

1、处理数据集
2、网络构建
3、模型训练
4、保存模型
5、加载模型
6、学习小结

学习内容：

1、处理数据集

from download import download

url = "https://mindspore-website.obs.cn-north-4.myhuaweicloud.com/" \
      "notebook/datasets/MNIST_Data.zip"
download(url, "./", "zip", replace=True)

# dataset
from mindspore.dataset import MnistDataset

train_dataset = MnistDataset('MNIST_Data/train')
test_dataset = MnistDataset('MNIST_Data/test')
print(train_dataset.get_col_names())

# data preprocess
import mindspore
from mindspore.dataset import transforms, vision

def datapipe(dataset, batch_size):
    image_transforms = [
        vision.Rescale(1.0 / 255.0, 0),
        vision.Normalize(mean=(0.1307,), std=(0.3081,)),
        vision.HWC2CHW()
    ]
    label_transform = transforms.TypeCast(mindspore.int32)

    dataset = dataset.map(image_transforms, 'image')
    dataset = dataset.map(label_transform, 'label')
    dataset = dataset.batch(batch_size)
    return dataset

train_dataset = datapipe(train_dataset, 64)
test_dataset = datapipe(test_dataset, 64)

for data in test_dataset.create_dict_iterator():
    print(f"Shape of image [N, C, H, W]: {data['image'].shape} {data['image'].dtype}")
    print(f"Shape of label: {data['label'].shape} {data['label'].dtype}")
    break

2、网络构建

# network
from mindspore import nn, ops

class Network(nn.Cell):
    def __init__(self):
        super().__init__()
        self.flatten = nn.Flatten()
        self.dense_relu_sequential = nn.SequentialCell(
            nn.Dense(28*28, 512),
            nn.ReLU(),
            nn.Dense(512, 512),
            nn.ReLU(),
            nn.Dense(512, 10)
        )
        
    def construct(self, x):
        x = self.flatten(x)
        logits = self.dense_relu_sequential(x)
        return logits
    
model = Network()
print(model)

3、模型训练

# train
loss_fn = nn.CrossEntropyLoss()
optimizer = nn.SGD(model.trainable_params(), 1e-2)

def forward_fn(data, label):
    logits = model(data)
    loss = loss_fn(logits, label)
    return loss, logits

grad_fn = mindspore.value_and_grad(forward_fn, None, optimizer.parameters, has_aux=True)

def train_step(data, label):
    (loss, _), grads = grad_fn(data, label)
    optimizer(grads)
    return loss

def train(model, dataset):
    size = dataset.get_dataset_size()
    model.set_train()
    for batch, (data, label) in enumerate(dataset.create_tuple_iterator()):
        loss = train_step(data, label)
        
        if batch % 100 == 0:
            loss, current = loss.asnumpy(), batch
            print(f"loss: {loss:>7f} [{current:3d}/{size:3d}]")
            
def test(model, dataset, loss_fn):
    num_batches = dataset.get_dataset_size()
    model.set_train(False)
    total, test_loss, correct = 0, 0, 0
    
    # error point 
    for data, label in dataset.create_tuple_iterator():
        pred = model(data)
        total += len(data)
        test_loss = loss_fn(pred, label).asnumpy()
        correct += (pred.argmax(1) == label).asnumpy().sum()
    test_loss /= num_batches
    correct /= total
    print(f"Test: \n Accuracy: {(100*correct):>0.1f}%, Avg Loss: {test_loss:>8f} \n")
    
epochs = 3
for t in range(epochs):
    print(f"Epoch {t+1}\n-------------------------------")
    train(model, train_dataset)
    test(model, test_dataset, loss_fn)

4、保存模型

# save model
mindspore.save_checkpoint(model, 'model.ckpt')
print('Saved Model to model.ckpt')

5、加载模型

# load model
model = Network()
param_dict = mindspore.load_checkpoint('model.ckpt')
param_not_load, _ = mindspore.load_param_into_net(model, param_dict)
# print(param_not_load)

# predict
model.set_train(False)
for data, label in test_dataset:
    pred = model(data)
    predicted = pred.argmax(1)
    print(f'Predicted: "{predicted[:10]}", Actual: "{label[:10]}"')
    break

6.学习小结