ModelArts学习笔记|Lenet的手写数字MINST识别

目录

1.数据集准备

2.实验过程

2.1导入实验环境

2.2数据处理

2.2.1获取数据集

2.2.2对数据进行预处理

2.3定义模型

2.4训练

---

 

letnet5+MINST

 

1.数据集准备

方法 1：从 MNIST 官网下载数据集到本地，MNIST 数据集的官网
http://yann.lecun.com/exdb/mnist/

方法 2：从华为云 OBS 中下载 MNIST 数据集并解压。 https://ascend-
professional-construction-dataset.obs.myhuaweicloud.com/deep-
learning/MNIST.zip

2.实验过程

2.1导入实验环境

import os
import numpy as np
import mindspore as ms
import mindspore.context as context
import mindspore.dataset.transforms.c_transforms as C
import mindspore.dataset.vision.c_transforms as CV

from mindspore import nn
from mindspore.train import Model
from mindspore.train.callback import LossMonitor

context.set_context(mode=context.GRAPH_MODE, device_target='Ascend') # Ascend, CPU, GPU

2.2数据处理

2.2.1获取数据集

!wget https://ascend-professional-construction-dataset.obs.myhuaweicloud.com/deep-learning/MNIST.zip
!unzip MNIST.zip

2.2.2对数据进行预处理

def create_dataset(data_dir, training=True, batch_size=32, resize=(32, 32),
                   rescale=1/(255*0.3081), shift=-0.1307/0.3081, buffer_size=64):
    data_train = os.path.join(data_dir, 'train') # 训练集信息
    data_test = os.path.join(data_dir, 'test') # 测试集信息
    ds = ms.dataset.MnistDataset(data_train if training else data_test)

    ds = ds.map(input_columns=["image"], operations=[CV.Resize(resize), CV.Rescale(rescale, shift), CV.HWC2CHW()])
    ds = ds.map(input_columns=["label"], operations=C.TypeCast(ms.int32))
    # When `dataset_sink_mode=True` on Ascend, append `ds = ds.repeat(num_epochs) to the end
    ds = ds.shuffle(buffer_size=buffer_size).batch(batch_size, drop_remainder=True)

    return ds

2.3定义模型

图片来源于
http://yann.lecun.com/exdb/publis/pdf/lecun-01a.pdf

class LeNet5(nn.Cell):
    def __init__(self):
        super(LeNet5, self).__init__()
        self.conv1 = nn.Conv2d(1, 6, 5, stride=1, pad_mode='valid')
        self.conv2 = nn.Conv2d(6, 16, 5, stride=1, pad_mode='valid')
        self.relu = nn.ReLU()
        self.pool = nn.MaxPool2d(kernel_size=2, stride=2)
        self.flatten = nn.Flatten()
        self.fc1 = nn.Dense(400, 120)
        self.fc2 = nn.Dense(120, 84)
        self.fc3 = nn.Dense(84, 10)

    def construct(self, x):
        x = self.relu(self.conv1(x))
        x = self.pool(x)
        x = self.relu(self.conv2(x))
        x = self.pool(x)
        x = self.flatten(x)
        x = self.fc1(x)
        x = self.fc2(x)
        x = self.fc3(x)

        return x

2.4训练

def train(data_dir, lr=0.01, momentum=0.9, num_epochs=3):
    ds_train = create_dataset(data_dir)
    ds_eval = create_dataset(data_dir, training=False)

    net = LeNet5()
    loss = nn.loss.SoftmaxCrossEntropyWithLogits(sparse=True, reduction='mean')
    opt = nn.Momentum(net.trainable_params(), lr, momentum)
    loss_cb = LossMonitor(per_print_times=ds_train.get_dataset_size())

    model = Model(net, loss, opt, metrics={'acc', 'loss'})
    # dataset_sink_mode can be True when using Ascend
    model.train(num_epochs, ds_train, callbacks=[loss_cb], dataset_sink_mode=True)
    metrics = model.eval(ds_eval, dataset_sink_mode=True)
    print('Metrics:', metrics)

train('MNIST')

epoch: 1 step 1875, loss is 0.23394052684307098
epoch: 2 step 1875, loss is 0.4737345278263092
epoch: 3 step 1875, loss is 0.07734094560146332
Metrics: {'loss': 0.10531254443608654, 'acc': 0.9701522435897436}