如何利用 CANN DVPP 进行图片的等比例缩放？

aclError acldvppJpegDecodeAsync(acldvppChannelDesc *channelDesc, const void *data, uint32_t size, acldvppPicDesc *outputDesc,aclrtStream stream)

aclError acldvppVpcCropAsync(acldvppChannelDesc *channelDesc, acldvppPicDesc *inputDesc, acldvppPicDesc *outputDesc, acldvppRoiConfig *cropArea, aclrtStream stream)

aclError acldvppVpcResizeAsync(acldvppChannelDesc *channelDesc, acldvppPicDesc *inputDesc, acldvppPicDesc *outputDesc, acldvppResizeConfig *resizeConfig, aclrtStream stream)

aclError aclrtMemset (void *devPtr, size_t maxCount, int32_t value, size_t count)

aclError acldvppVpcCropAndPasteAsync(acldvppChannelDesc *channelDesc, acldvppPicDesc *inputDesc, acldvppPicDesc *outputDesc, acldvppRoiConfig *cropArea, acldvppRoiConfig *pasteArea, aclrtStream stream)

acldvppChannelDesc *channelDescchannelDesc = acldvppCreateChannelDesc();aclError ret = acldvppCreateChannel(channelDesc);// 销毁与创建的顺序相反acldvppDestroyChannel(channelDesc);acldvppDestroyChannelDesc(channelDesc);

acldvppPicDesc *picDesc
picDesc = acldvppCreatePicDesc();
acldvppSetPicDescData(picDesc, decodeOutDevBuffer_); // 图像的内存地址
acldvppSetPicDescSize(picDesc, decodeOutBufferSize); // 图像所占的内存大小
acldvppSetPicDescFormat(picDesc, PIXEL_FORMAT_YUV_SEMIPLANAR_420); // 图像的格式
acldvppSetPicDescWidth(picDesc, inputWidth_); // 图像的实际宽
acldvppSetPicDescHeight(picDesc, inputHeight_); // 图像的实际高
acldvppSetPicDescWidthStride(picDesc, decodeOutWidthStride); // 图像在内存中对齐后的宽
acldvppSetPicDescHeightStride(picDesc, decodeOutHeightStride); // 图像在内存中对齐后的高
// 销毁
acldvppDestroyPicDesc(picDesc);

// device侧，200DK等只有device内存的也用此接口，且只用此接口aclError aclrtMalloc(void **devPtr, size_t size, aclrtMemMallocPolicy policy)aclError aclrtFree(void *devPtr)// host侧aclError aclrtMallocHost(void **hostPtr, size_t size)aclError aclrtFreeHost(void *hostPtr)// dvpp 内存（在device侧，因为需要内存地址128对齐，所以拥有单独的接口）aclError acldvppMalloc(void **devPtr, size_t size)aclError acldvppFree(void *devPtr)

acldvppRoiConfig *acldvppCreateRoiConfig(uint32_t left, uint32_t right, uint32_t top, uint32_t bottom)
// 销毁
aclError acldvppDestroyRoiConfig(acldvppRoiConfig *roiConfig)

// 通过此接口可以方便的获取JPEG图像的宽，高，色彩通道数，编码格式，只需要传入对应的JPEG源数据地址以及大小
aclError acldvppJpegGetImageInfoV2(const void *data, uint32_t size, uint32_t *width, uint32_t *height, int32_t *components, acldvppJpegFormat *format)
// 获取JPEG图片解码后的数据大小，因为解码后会对齐到128,所以不能任何时候都简单地依据原图大小计算解码后占用的内存大小。
aclError acldvppJpegPredictDecSize(const void *data, uint32_t dataSize, acldvppPixelFormat outputPixelFormat, uint32_t *decSize)
// 获取PNG图像的宽和高
aclError acldvppPngGetImageInfo(const void *data, uint32_t dataSize, uint32_t *width, uint32_t *height, int32_t *components)
// 预测PNG图片解码后占用内存空间
aclError acldvppPngPredictDecSize(const void *data, uint32_t dataSize, acldvppPixelFormat outputPixelFormat, uint32_t *decSize)
// 获取JPEG图像编码后的占用内存空间
aclError acldvppJpegPredictEncSize(const acldvppPicDesc *inputDesc, const acldvppJpegeConfig *config, uint32_t *size)

// 缩放接口,单一接口，将缩放后的图片作为输出
aclError acldvppVpcResizeAsync(acldvppChannelDesc *channelDesc, acldvppPicDesc *inputDesc, acldvppPicDesc *outputDesc, acldvppResizeConfig *resizeConfig, aclrtStream stream)
// 抠图接口，单一接口，从原图中根据ROI区域抠出一部分作为输出
aclError acldvppVpcCropAsync(acldvppChannelDesc *channelDesc, acldvppPicDesc *inputDesc, acldvppPicDesc *outputDesc, acldvppRoiConfig *cropArea, aclrtStream stream)
// 组合接口（抠图+缩放），应用场景：JPEG 解码后的图片中可能有无效的数据，直接缩放到模型需要的大小会把无效数据一起输入，可以先把真实图像的数据抠出来然后进行缩放，减少无效的数据干扰。
aclError acldvppVpcCropResizeAsync(acldvppChannelDesc *channelDesc, acldvppPicDesc *inputDesc, acldvppPicDesc *outputDesc, acldvppRoiConfig *cropArea, acldvppResizeConfig *resizeConfig, aclrtStream stream)
// 组合接口（抠图+贴图 / 抠图+缩放+贴图）如果抠图与贴图的大小不一致会进行一步缩放操作。
aclError acldvppVpcCropAndPasteAsync(acldvppChannelDesc *channelDesc, acldvppPicDesc *inputDesc, acldvppPicDesc *outputDesc, acldvppRoiConfig *cropArea, acldvppRoiConfig *pasteArea, aclrtStream stream)
// 组合接口（抠图+贴图 / 抠图+缩放+贴图）此接口功能与上一个是一致的，但是此接口可以指定不同的缩放算法
aclError acldvppVpcCropResizePasteAsync(acldvppChannelDesc *channelDesc, acldvppPicDesc *inputDesc, acldvppPicDesc *outputDesc, acldvppRoiConfig *cropArea, acldvppRoiConfig *pasteArea, acldvppResizeConfig *resizeConfig, aclrtStream stream)

// 定义一些全局变量namespace { std::string aclConfig = "../src/acl.json"; const std::string image_path = "../data/dog2.jpg"; const std::string image_save_path = "../out/dog2.jpg";    int32_t deviceId = 0; aclrtContext context; aclrtStream stream; aclrtRunMode runMode_ = ACL_DEVICE;    uint32_t model_width = 416; // 模型需要的图像宽    uint32_t model_height = 416; // 模型需要的图像高    uint32_t image_width = 0; // 图像的真实宽    uint32_t image_height = 0; // 图像的真实高 acldvppChannelDesc *dvppChannelDesc = nullptr;}

// 将图片读入内存，如果运行模式为（ACL_HOST）模式，需要申请host侧内存存放我们的原始图片数据，然后申请相同大小的device内存拷贝过去。如果运行在（ACL_DEVICE）模式，例如200DK这样的场景，直接申请device内存，不需要进行内存的拷贝搬运。// 经过读取图片的步骤我们应该能获得如下变量void* JpegImagePtr; // 原始图像在device侧的内存地址（不管运行在那种方式下的昇腾软件栈都是如此）uint32_t JpegImageSize; // 原始图像的大小// 我们不了解图像的编码以及真实宽高，还有颜色通道数，所以需要执行获取图像信息的接口// 图像的原始宽高变量我们前面已经定义过, 所以我们现在只需要定义图像的通道数与编码方式还有图像解码后所占用的内存的大小int32_t components; // 图像的通道数acldvppJpegFormat format; // 图像的编码方式uint32_t JpegdOutSize;void* JpegdOutPtr;aclError ret = acldvppJpegGetImageInfoV2(JpegImagePtr, JpegImageSize, &image_width, &height, &components, &format)aclError ret = acldvppJpegPredictDecSize(JpegImagePtr, JpegImageSize, format, &JpegdOutSize)// 申请存放解码后YUV图像的内存aclError ret = acldvppMalloc(&JpegdOutPtr, JpegdOutSize);// 设置JPEG解码后图像的描述信息（注意JPEG解码后内存宽高对齐到128x16）acldvppPicDesc* JpegdOutputPicDesc = acldvppCreatePicDesc();acldvppSetPicDescData(out_pic_desc, JpegdOutPtr);acldvppSetPicDescSize(out_pic_desc, JpegdOutSize);acldvppSetPicDescFormat(out_pic_desc, PIXEL_FORMAT_YUV_SEMIPLANAR_420);acldvppSetPicDescWidth(out_pic_desc, image_width);acldvppSetPicDescHeight(out_pic_desc, image_height);acldvppSetPicDescWidthStride(out_pic_desc, ALIGN_UP128(image_width));acldvppSetPicDescHeightStride(out_pic_desc, ALIGN_UP16(image_height));// 执行解码接口ret = acldvppJpegDecodeAsync(dvppChannelDesc, JpegImagePtr, JpegImageSize, JpegdOutputPicDesc, stream);ret = aclrtSynchronizeStream(stream_);

// 首先声明原图抠图的区域// 抠图的区域左偏移和上偏移都是偶数// 抠图的区域右偏移和下偏移都是奇数uint32_t left = 0;uint32_t top = 0;uint32_t right = image_width % 2 == 0 ? image_width-1 : image_width;uint32_t bottom = image_height % 2 == 0 ? image_height-1 : image_height;acldvppRoiConfig* cropArea = cropConfig = acldvppCreateRoiConfig(left, right, top, bottom);// 计算等比例缩放后的新的宽高（等比例缩放后可能不满足16x2的对齐规则，需要手动进行对齐的操作）void LargeSizeAtLeast(uint32_t W, uint32_t H, uint32_t &newInputWidth, uint32_t &newInputHeight){ INFO_LOG("W:%u H:%u nw:%u, nh:%u", W, H, newInputWidth, newInputHeight);    float scaleRatio = 0.0;    float inputWidth = 0.0;    float inputHeight = 0.0;    float resizeMax = 0.0;    bool maxWidthFlag = false; inputWidth = (float)W; inputHeight = (float)H; resizeMax = (float)(416); maxWidthFlag = (W >= H) ? true : false; if (maxWidthFlag == true) { newInputWidth = resizeMax; scaleRatio = resizeMax / W; // 高度2对齐 newInputHeight = scaleRatio * H; newInputHeight = ALIGN_UP2(newInputHeight); INFO_LOG("scaleRatio: %.3f, modelInputWidth: %u, modelInputHeight: %d, newInputWidth: %d, newInputHeight: %d", scaleRatio, W, H, newInputWidth, newInputHeight); } else { scaleRatio = resizeMax / H; // 如果高度是长边，建议宽度在等比例缩放后再做一次16对齐。因为vpc在输出时宽有16字节对齐约束，当贴图的宽非16对齐时，会导致在贴图的时候， // 芯片会自动进行16字节对齐，导致每次写入数据的时候都会引入部分无效数据，从而导致精度下降。 newInputWidth = scaleRatio * W; newInputWidth = ALIGN_UP16(newInputWidth); newInputHeight = resizeMax; INFO_LOG("scaleRatio: %.3f, modelInputWidth: %u, modelInputHeight: %d, newInputWidth: %d, newInputHeight: %d", scaleRatio, W, H, newInputWidth, newInputHeight); }}// 设置贴图的范围左偏移要求16对齐acldvppRoiConfig *InitVpcOutConfig(uint32_t width, uint32_t height, uint32_t modelInputWidth, uint32_t modelInputHeight){    uint32_t right = 0;    uint32_t bottom = 0;    uint32_t left = 0;    uint32_t top = 0;    uint32_t left_stride; acldvppRoiConfig *cropConfig;    uint32_t small = width < height ? width : height;    uint32_t padded_size_half; if (small == width) { padded_size_half = (modelInputWidth - width) / 2; // 贴图区域距离左边界的距离        left = padded_size_half; left_stride = ALIGN_UP16(left);        right = (left_stride + width) % 2 == 0 ? (left_stride + width - 1) : (left_stride + width); if (left_stride + right > modelInputWidth) { while (true) { left_stride = left_stride - 16;                right = (left_stride + width) % 2 == 0 ? (left_stride + width - 1) : (left_stride + width); if (left_stride + right < modelInputWidth) break; } }        right = (left_stride + width) % 2 == 0 ? (left_stride + width - 1) : (left_stride + width);        bottom = (modelInputHeight % 2 == 0 ? modelInputHeight - 1 : modelInputHeight);        top = bottom - height + 1; } else { padded_size_half = (modelInputHeight - height) / 2;        right = (modelInputWidth % 2 == 0 ? modelInputWidth - 1 : modelInputWidth);        left = right + 1 - width; left_stride = ALIGN_UP16(left);        top = (padded_size_half % 2 == 0 ? padded_size_half : padded_size_half + 1);        bottom = (height + top - 1) % 2 == 0 ? (height + top - 2) : (height + top - 1); } INFO_LOG("left_stride=%d, right=%d, top=%d, bottom=%d\n", left_stride, right, top, bottom); cropConfig = acldvppCreateRoiConfig(left_stride, right, top, bottom); if (cropConfig == nullptr) { ERROR_LOG("acldvppCreateRoiConfig failed"); return nullptr; } return cropConfig;}// 设置最后完成等比例缩放后的图像的信息void* output_ptr = nullptr;uint32_t output_size = YUV420SP_SIZE(ALIGN_UP16(model_width), ALIGN_UP2(model_height));ret = acldvppMalloc(&output_ptr, output_size); // 申请模板内存if (ret != ACL_SUCCESS) {ERROR_LOG("acl malloc output is failed");}ret = aclrtMemset(output_ptr, output_size, 128, output_size);if (ret != ACL_SUCCESS) {ERROR_LOG("mem set 128 is failed");}acldvppPicDesc *output_Desc = acldvppCreatePicDesc();acldvppSetPicDescData(output_Desc, output_ptr);acldvppSetPicDescSize(output_Desc, output_size);acldvppSetPicDescFormat(output_Desc, PIXEL_FORMAT_YUV_SEMIPLANAR_420);acldvppSetPicDescWidth(output_Desc, model_width);acldvppSetPicDescHeight(output_Desc, model_height);acldvppSetPicDescWidthStride(output_Desc, ALIGN_UP16(model_width));acldvppSetPicDescHeightStride(output_Desc, ALIGN_UP2(model_height));// 执行裁剪加贴图的操作ret = acldvppVpcCropAndPasteAsync(dvppChannelDesc, JpegdOutputPicDesc, output_Desc, cropArea, pasteArea, stream);