【ArkTS应用开发】【AI服务】MindSpore Lite图像分类：如何获取模型标签文件？ - OpenHarmony开发者论坛

// Index.ets
import { photoAccessHelper } from '@kit.MediaLibraryKit';
import { BusinessError } from '@kit.BasicServicesKit';
import { image } from '@kit.ImageKit';
import { fileIo } from '@kit.CoreFileKit';
import modelPredict from './model';
@Entry
@Component
struct Index {
@State modelName: string = 'mobilenetv2.ms';
@State modelInputHeight: number = 224;
@State modelInputWidth: number = 224;
@State uris: Array<string> = [];
@State max: number = 0;
@State maxIndex: number = 0;
@State maxArray: Array<number> = [];
@State maxIndexArray: Array<number> = [];
build() {
Row() {
Column() {
Button() {
Text('photo')
.fontSize(30)
.fontWeight(FontWeight.Bold)
}
.type(ButtonType.Capsule)
.margin({
top: 20
})
.backgroundColor('#0D9FFB')
.width('40%')
.height('5%')
.onClick(() => {
let resMgr = this.getUIContext()?.getHostContext()?.getApplicationContext().resourceManager;
resMgr?.getRawFileContent(this.modelName).then(modelBuffer => {
let float32View = new Float32Array(this.modelInputHeight * this.modelInputWidth * 3);
// 获取相册图片
// 1.创建图片文件选择实例
let photoSelectOptions = new photoAccessHelper.PhotoSelectOptions();
// 2.设置选择媒体文件类型为IMAGE，设置选择媒体文件的最大数目
photoSelectOptions.MIMEType = photoAccessHelper.PhotoViewMIMETypes.IMAGE_TYPE;
photoSelectOptions.maxSelectNumber = 1;
// 3.创建图库选择器实例，调用select()接口拉起图库界面进行文件选择。文件选择成功后，返回photoSelectResult结果集。
let photoPicker = new photoAccessHelper.PhotoViewPicker();
photoPicker.select(photoSelectOptions, async (
err: BusinessError, photoSelectResult: photoAccessHelper.PhotoSelectResult) => {
if (err) {
console.error('MS_LITE_ERR: PhotoViewPicker.select failed with err: ' + JSON.stringify(err));
return;
}
console.info('MS_LITE_LOG: PhotoViewPicker.select successfully, ' +
'photoSelectResult uri: ' + JSON.stringify(photoSelectResult));
console.info('MS_LITE_LOG: 图库选择器选择成功... ' +
'photoSelectResult uri: ' + JSON.stringify(photoSelectResult));
this.uris = photoSelectResult.photoUris;
console.info('MS_LITE_LOG: uri: ' + this.uris);
// 预处理图片数据
try{
// 1.使用fileIo.openSync接口，通过uri打开这个文件得到fd
let file = fileIo.openSync(this.uris[0], fileIo.OpenMode.READ_ONLY);
console.info('MS_LITE_LOG: file fd: ' + file.fd);
console.info('MS_LITE_LOG: 文件描述符 fd:: ' + file.fd);
// 2.通过fd使用fileIo.readSync接口读取这个文件内的数据
let inputBuffer = new ArrayBuffer(4096000);
let readLen = fileIo.readSync(file.fd, inputBuffer);
console.info('MS_LITE_LOG: readSync data to file succeed and inputBuffer size is:' + readLen);
console.info('MS_LITE_LOG: 读取文件数据成功...and inputBuffer size is:' + readLen);
// 3.通过PixelMap预处理
let imageSource = image.createImageSource(file.fd);
imageSource.createPixelMap().then((pixelMap) => {
pixelMap.getImageInfo().then((info) => {
console.info('MS_LITE_LOG: info.width = ' + info.size.width);
console.info('MS_LITE_LOG: 原始图片宽度 = ' + info.size.width);
console.info('MS_LITE_LOG: info.height = ' + info.size.height);
// 4.根据模型输入的尺寸，将图片裁剪为对应的size，获取图片buffer数据readBuffer
pixelMap.scale(256.0 / info.size.width, 256.0 / info.size.height).then(() => {
pixelMap.crop(
{ x: 16, y: 16, size: { height: this.modelInputHeight, width: this.modelInputWidth } }
).then(async () => {
let info = await pixelMap.getImageInfo();
console.info('MS_LITE_LOG: crop info.width = ' + info.size.width);
console.info('MS_LITE_LOG: 裁剪后图片宽度 = ' + info.size.width);
console.info('MS_LITE_LOG: crop info.height = ' + info.size.height);
// 需要创建的像素buffer大小
let readBuffer = new ArrayBuffer(this.modelInputHeight * this.modelInputWidth * 4);
await pixelMap.readPixelsToBuffer(readBuffer);
console.info('MS_LITE_LOG: Succeeded in reading image pixel data, buffer: ' +
readBuffer.byteLength);
console.info('MS_LITE_LOG: 读取图片像素数据成功... buffer: ' +
readBuffer.byteLength);
// 处理readBuffer，转换成float32格式，并进行标准化处理
const imageArr = new Uint8Array(
readBuffer.slice(0, this.modelInputHeight * this.modelInputWidth * 4));
console.info('MS_LITE_LOG: imageArr length: ' + imageArr.length);
console.info('MS_LITE_LOG: 图像数组长度: ' + imageArr.length);
let means = [0.485, 0.456, 0.406];
let stds = [0.229, 0.224, 0.225];
let float32View = new Float32Array(this.modelInputHeight * this.modelInputWidth * 3);
let index = 0;
for (let i = 0; i < imageArr.length; i++) {
if ((i + 1) % 4 == 0) {
float32View[index] = (imageArr[i - 3] / 255.0 - means[0]) / stds[0]; // B
float32View[index+1] = (imageArr[i - 2] / 255.0 - means[1]) / stds[1]; // G
float32View[index+2] = (imageArr[i - 1] / 255.0 - means[2]) / stds[2]; // R
index += 3;
}
}
console.info('MS_LITE_LOG: float32View length: ' + float32View.length);
console.info('MS_LITE_LOG: 浮点数组长度: ' + float32View.length);
let printStr = 'float32View data:';
for (let i = 0; i < 20; i++) {
printStr += ' ' + float32View[i];
}
console.info('MS_LITE_LOG: float32View data: ' + printStr);
console.info('MS_LITE_LOG: 浮点数组数据: ' + printStr);
let inputs: ArrayBuffer[] = [float32View.buffer];
// predict
modelPredict(modelBuffer.buffer.slice(0), inputs).then(outputs => {
console.info('=========MS_LITE_LOG: 模型推理成功=====');
// 结果打印
for (let i = 0; i < outputs.length; i++) {
let out = new Float32Array(outputs[i].getData());
let printStr = outputs[i].name + ':';
for (let j = 0; j < out.length; j++) {
printStr += out[j].toString() + ',';
}
console.info('MS_LITE_LOG: ' + printStr);
// 取分类占比的最大值
this.max = 0;
this.maxIndex = 0;
this.maxArray = [];
this.maxIndexArray = [];
let newArray = out.filter(value => value !== this.max)
for (let n = 0; n < 5; n++) {
this.max = out[0];
this.maxIndex = 0;
for (let m = 0; m < newArray.length; m++) {
if (newArray[m] > this.max) {
this.max = newArray[m];
this.maxIndex = m;
}
}
this.maxArray.push(Math.round(this.max * 10000))
this.maxIndexArray.push(this.maxIndex)
// filter数组过滤函数
newArray = newArray.filter(value => value !== this.max)
}
console.info('MS_LITE_LOG: max:最大概率值:' + this.maxArray);
console.info('MS_LITE_LOG: maxIndex:对应类别索引:' + this.maxIndexArray);
}
console.info('=========MS_LITE_LOG END=========');
})
})
})
})
})
} catch (err) {
console.error('MS_LITE_LOG: uri: open file fd failed.' + err);
}
})
})
})
}
.width('100%')
}
.height('100%')
}
}

复制代码