【昇思初学入门】第一天打卡

学习心得

1. 昇思api设计及支持静态图又支持动态图，通过context.set_context(mode=context.GRAPH_MODE)或context.set_context(mode=context.PYNATIVE_MODE)来切换
2. 昇思模型可以直接使用vision.HWC2CHW()，将图像的通道从“高度-宽度-通道”（HWC）顺序转换为“通道-高度-宽度”（CHW）顺序
3. 构建网络，使用nn.Cell作为基类，不同于PyTorch继承自nn.Module

笔记

数据准备

import mindspore
from mindspore import nn
from mindspore.dataset import vision, transforms
from mindspore.dataset import MnistDataset
# Download data from open datasets
from download import download

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

train_dataset = MnistDataset('MNIST_Data/train')
test_dataset = MnistDataset('MNIST_Data/test')

数据预处理

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)

构建网络

# Define model
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)

模型训练

# Instantiate loss function and optimizer
loss_fn = nn.CrossEntropyLoss()
optimizer = nn.SGD(model.trainable_params(), 1e-2)

# 1. Define forward function
def forward_fn(data, label):
    logits = model(data)
    loss = loss_fn(logits, label)
    return loss, logits

# 2. Get gradient function
grad_fn = mindspore.value_and_grad(forward_fn, None, optimizer.parameters, has_aux=True)

# 3. Define function of one-step training
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
    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)
print("Done!")

保存模型

mindspore.save_checkpoint(model, "model.ckpt")

加载模型

mindspore.save_checkpoint(model, "model.ckpt")

# Instantiate a random initialized model
model = Network()
# Load checkpoint and load parameter to model
param_dict = mindspore.load_checkpoint("model.ckpt")
param_not_load, _ = mindspore.load_param_into_net(model, param_dict)
#为空时代表所有参数均加载成功
print(param_not_load)

使用模型推理

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