MindSpore在Mnist数据集上的实验

mindspore 是华为的深度学习框架，与Pytorch非常类似，下面以官方的入门实验为例进行实验。代码简单，直接放上：

import os
import argparse
from mindspore import context
# args = parser.parse_known_args()[0]
context.set_context(mode=context.GRAPH_MODE, device_target='CPU')

import mindspore.dataset as ds
import mindspore.dataset.transforms.c_transforms as C
import mindspore.dataset.vision.c_transforms as CV
from mindspore.dataset.vision import Inter
from mindspore import dtype as mstype

def create_dataset(data_path, batch_size=32, repeat_size=1,
                   num_parallel_workers=1):
    # 定义数据集
    mnist_ds = ds.MnistDataset(data_path)
    resize_height, resize_width = 32, 32
    rescale = 1.0 / 255.0
    shift = 0.0
    rescale_nml = 1 / 0.3081
    shift_nml = -1 * 0.1307 / 0.3081

    # 定义所需要操作的map映射
    resize_op = CV.Resize((resize_height, resize_width), interpolation=Inter.LINEAR)
    rescale_nml_op = CV.Rescale(rescale_nml, shift_nml)
    rescale_op = CV.Rescale(rescale, shift)
    hwc2chw_op = CV.HWC2CHW()
    type_cast_op = C.TypeCast(mstype.int32)

    # 使用map映射函数，将数据操作应用到数据集
    mnist_ds = mnist_ds.map(operations=type_cast_op, input_columns="label", num_parallel_workers=num_parallel_workers)
    mnist_ds = mnist_ds.map(operations=resize_op, input_columns="image", num_parallel_workers=num_parallel_workers)
    mnist_ds = mnist_ds.map(operations=rescale_op, input_columns="image", num_parallel_workers=num_parallel_workers)
    mnist_ds = mnist_ds.map(operations=rescale_nml_op, input_columns="image", num_parallel_workers=num_parallel_workers)
    mnist_ds = mnist_ds.map(operations=hwc2chw_op, input_columns="image", num_parallel_workers=num_parallel_workers)

    # 进行shuffle、batch操作
    buffer_size = 10000
    mnist_ds = mnist_ds.shuffle(buffer_size=buffer_size)
    mnist_ds = mnist_ds.batch(batch_size, drop_remainder=True)

    return mnist_ds

import mindspore.nn as nn
from mindspore.common.initializer import Normal

class LeNet5(nn.Cell):
    """
    Lenet网络结构
    """
    def __init__(self, num_class=10, num_channel=1):
        super(LeNet5, self).__init__()
        # 定义所需要的运算
        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, weight_init=Normal(0.02))
        self.fc2 = nn.Dense(120, 84, weight_init=Normal(0.02))
        self.fc3 = nn.Dense(84, num_class, weight_init=Normal(0.02))
        self.relu = nn.ReLU()
        self.max_pool2d = nn.MaxPool2d(kernel_size=2, stride=2)
        self.flatten = nn.Flatten()

    def construct(self, x):
        # 使用定义好的运算构建前向网络
        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 x

# 实例化网络
net = LeNet5()

# 定义损失函数
net_loss = nn.SoftmaxCrossEntropyWithLogits(sparse=True, reduction='mean')

# 定义优化器
net_opt = nn.Momentum(net.trainable_params(), learning_rate=0.01, momentum=0.9)

from mindspore.train.callback import ModelCheckpoint, CheckpointConfig
# 设置模型保存参数
config_ck = CheckpointConfig(save_checkpoint_steps=1875, keep_checkpoint_max=10)
# 应用模型保存参数
ckpoint = ModelCheckpoint(prefix="checkpoint_lenet", config=config_ck)

# 导入模型训练需要的库
from mindspore.nn import Accuracy
from mindspore.train.callback import LossMonitor
from mindspore import Model

def train_net(model, epoch_size, data_path, repeat_size, ckpoint_cb, sink_mode):
    """定义训练的方法"""
    # 加载训练数据集
    ds_train = create_dataset(os.path.join(data_path, "train"), 128, repeat_size)
    model.train(epoch_size, ds_train, callbacks=[ckpoint_cb, LossMonitor(125)], dataset_sink_mode=sink_mode)


def test_net(network, model, data_path):
    """定义验证的方法"""
    ds_eval = create_dataset(os.path.join(data_path, "test"))
    acc = model.eval(ds_eval, dataset_sink_mode=False)
    print("{}".format(acc))

train_epoch = 20
mnist_path = "./datasets/MNIST_Data"
dataset_size = 1
model = Model(net, net_loss, net_opt, metrics={"Accuracy": Accuracy()})
train_net(model, train_epoch, mnist_path, dataset_size, ckpoint, False)
test_net(net, model, mnist_path)

在CPU上跑20次循环的实验结果如下图所示： 

 实验运行的识别准确率为98%左右，由于模型是浅层的LeNet5，识别准确率还可以提高。感觉上mindspore的速度比较快，比pytorch要快许多。