diff --git a/docs/cn/faq/rknpu2/rknpu2.md b/docs/cn/faq/rknpu2/rknpu2.md index c3a424af4..a1ff99946 100644 --- a/docs/cn/faq/rknpu2/rknpu2.md +++ b/docs/cn/faq/rknpu2/rknpu2.md @@ -16,21 +16,12 @@ ONNX模型不能直接调用RK芯片中的NPU进行运算，需要把ONNX模型 |------------------|-------------------|-------------------------------|--------------------| | Detection | Picodet | Picodet-s | 162/112 | | Detection | RKYOLOV5 | YOLOV5-S-Relu(int8) | -/57 | +| Detection | RKYOLOX | - | -/- | +| Detection | RKYOLOV7 | - | -/- | | Segmentation | Unet | Unet-cityscapes | -/- | -| Segmentation | PP-LiteSeg | PP_LiteSeg_T_STDC1_cityscapes | -/- | -| Segmentation | PP-HumanSegV2Lite | portrait | 53/50 | -| Segmentation | PP-HumanSegV2Lite | human | 53/50 | -| Face Detection | SCRFD | SCRFD-2.5G-kps-640 | 112/108 | - -## TODO -以下为TODO计划，表示还正在准备支持，但是还存在问题或还可以改进的模型。 - -| 任务场景 | 模型 | 模型版本(表示已经测试的版本) | ARM CPU/RKNN速度(ms) | -|------------------|---------|---------------------|--------------------| -| Detection | PPYOLOE | PPYOLOE(int8) | -/- | -| Detection | YOLOv5 | YOLOv5-s_v6.2(int8) | -/- | -| Face Recognition | ArcFace | ArcFace_r18 | 600/3 | -| Face Recognition | cosFace | cosFace_r18 | 600/3 | +| Segmentation | PP-HumanSegV2Lite | portrait | 133/43 | +| Segmentation | PP-HumanSegV2Lite | human | 133/43 | +| Face Detection | SCRFD | SCRFD-2.5G-kps-640 | 108/42 | ## RKNPU2 Backend推理使用教程 diff --git a/examples/vision/segmentation/paddleseg/rknpu2/README.md b/examples/vision/segmentation/paddleseg/rknpu2/README.md index cf708fe2c..d083fa049 100644 --- a/examples/vision/segmentation/paddleseg/rknpu2/README.md +++ b/examples/vision/segmentation/paddleseg/rknpu2/README.md @@ -25,80 +25,7 @@ RKNPU部署模型前需要将Paddle模型转换成RKNN模型，具体步骤如 ## 模型转换example -下面以Portait-PP-HumanSegV2_Lite(肖像分割模型)为例子，教大家如何转换PPSeg模型到RKNN模型。 -```bash -# 下载Paddle2ONNX仓库 -git clone https://github.com/PaddlePaddle/Paddle2ONNX - -# 下载Paddle静态图模型并为Paddle静态图模型固定输入shape -## 进入为Paddle静态图模型固定输入shape的目录 -cd Paddle2ONNX/tools/paddle -## 下载Paddle静态图模型并解压 -wget https://bj.bcebos.com/paddlehub/fastdeploy/Portrait_PP_HumanSegV2_Lite_256x144_infer.tgz -tar xvf Portrait_PP_HumanSegV2_Lite_256x144_infer.tgz -python paddle_infer_shape.py --model_dir Portrait_PP_HumanSegV2_Lite_256x144_infer/ \ - --model_filename model.pdmodel \ - --params_filename model.pdiparams \ - --save_dir Portrait_PP_HumanSegV2_Lite_256x144_infer \ - --input_shape_dict="{'x':[1,3,144,256]}" - -# 静态图转ONNX模型，注意，这里的save_file请和压缩包名对齐 -paddle2onnx --model_dir Portrait_PP_HumanSegV2_Lite_256x144_infer \ - --model_filename model.pdmodel \ - --params_filename model.pdiparams \ - --save_file Portrait_PP_HumanSegV2_Lite_256x144_infer/Portrait_PP_HumanSegV2_Lite_256x144_infer.onnx \ - --enable_dev_version True - -# ONNX模型转RKNN模型 -# 将ONNX模型目录拷贝到Fastdeploy根目录 -cp -r ./Portrait_PP_HumanSegV2_Lite_256x144_infer /path/to/Fastdeploy -# 转换模型,模型将生成在Portrait_PP_HumanSegV2_Lite_256x144_infer目录下 -python tools/rknpu2/export.py --config_path tools/rknpu2/config/RK3588/Portrait_PP_HumanSegV2_Lite_256x144_infer.yaml -``` - -## 修改yaml配置文件 - -在**模型转换example**中，我们对模型的shape进行了固定，因此对应的yaml文件也要进行修改，如下: - -**原yaml文件** -```yaml -Deploy: - input_shape: - - -1 - - 3 - - -1 - - -1 - model: model.pdmodel - output_dtype: float32 - output_op: none - params: model.pdiparams - transforms: - - target_size: - - 256 - - 144 - type: Resize - - type: Normalize -``` - -**修改后的yaml文件** -```yaml -Deploy: - input_shape: - - 1 - - 3 - - 144 - - 256 - model: model.pdmodel - output_dtype: float32 - output_op: none - params: model.pdiparams - transforms: - - target_size: - - 256 - - 144 - type: Resize - - type: Normalize -``` +* [PPHumanSeg](./pp_humanseg.md) ## 详细部署文档 - [RKNN总体部署教程](../../../../../docs/cn/faq/rknpu2/rknpu2.md) diff --git a/examples/vision/segmentation/paddleseg/rknpu2/cpp/README.md b/examples/vision/segmentation/paddleseg/rknpu2/cpp/README.md index 0b47f0baf..5a9bf2dae 100644 --- a/examples/vision/segmentation/paddleseg/rknpu2/cpp/README.md +++ b/examples/vision/segmentation/paddleseg/rknpu2/cpp/README.md @@ -62,16 +62,12 @@ make install ```bash cd ./build/install -./rknpu_test +./rknpu_test model/Portrait_PP_HumanSegV2_Lite_256x144_infer/ images/portrait_heng.jpg ``` -## 运行结果展示 -运行后将在install文件夹下生成human_pp_humansegv2_lite_npu_result.jpg文件，如下图: -![](https://user-images.githubusercontent.com/58363586/198875853-72821ad1-d4f7-41e3-b616-bef43027de3c.jpg) - ## 注意事项 RKNPU上对模型的输入要求是使用NHWC格式，且图片归一化操作会在转RKNN模型时，内嵌到模型中，因此我们在使用FastDeploy部署时， -需要先调用DisableNormalizePermute(C++)或`disable_normalize_permute(Python)，在预处理阶段禁用归一化以及数据格式的转换。 +需要先调用DisableNormalizeAndPermute(C++)或`disable_normalize_and_permute(Python)，在预处理阶段禁用归一化以及数据格式的转换。 - [模型介绍](../../) - [Python部署](../python) diff --git a/examples/vision/segmentation/paddleseg/rknpu2/cpp/infer.cc b/examples/vision/segmentation/paddleseg/rknpu2/cpp/infer.cc index 4e02ae32e..834b2ccb3 100644 --- a/examples/vision/segmentation/paddleseg/rknpu2/cpp/infer.cc +++ b/examples/vision/segmentation/paddleseg/rknpu2/cpp/infer.cc @@ -92,7 +92,7 @@ int main(int argc, char* argv[]) { } RKNPU2Infer(argv[1], argv[2]); - ONNXInfer(argv[1], argv[2]); +// ONNXInfer(argv[1], argv[2]); return 0; } diff --git a/examples/vision/segmentation/paddleseg/rknpu2/pp_humanseg.md b/examples/vision/segmentation/paddleseg/rknpu2/pp_humanseg.md new file mode 100644 index 000000000..d012bffb6 --- /dev/null +++ b/examples/vision/segmentation/paddleseg/rknpu2/pp_humanseg.md @@ -0,0 +1,80 @@ +# PPHumanSeg模型部署 + +## 转换模型 +下面以Portait-PP-HumanSegV2_Lite(肖像分割模型)为例子，教大家如何转换PPSeg模型到RKNN模型。 + +```bash +# 下载Paddle2ONNX仓库 +git clone https://github.com/PaddlePaddle/Paddle2ONNX + +# 下载Paddle静态图模型并为Paddle静态图模型固定输入shape +## 进入为Paddle静态图模型固定输入shape的目录 +cd Paddle2ONNX/tools/paddle +## 下载Paddle静态图模型并解压 +wget https://bj.bcebos.com/paddlehub/fastdeploy/Portrait_PP_HumanSegV2_Lite_256x144_infer.tgz +tar xvf Portrait_PP_HumanSegV2_Lite_256x144_infer.tgz +python paddle_infer_shape.py --model_dir Portrait_PP_HumanSegV2_Lite_256x144_infer/ \ + --model_filename model.pdmodel \ + --params_filename model.pdiparams \ + --save_dir Portrait_PP_HumanSegV2_Lite_256x144_infer \ + --input_shape_dict="{'x':[1,3,144,256]}" + +# 静态图转ONNX模型，注意，这里的save_file请和压缩包名对齐 +paddle2onnx --model_dir Portrait_PP_HumanSegV2_Lite_256x144_infer \ + --model_filename model.pdmodel \ + --params_filename model.pdiparams \ + --save_file Portrait_PP_HumanSegV2_Lite_256x144_infer/Portrait_PP_HumanSegV2_Lite_256x144_infer.onnx \ + --enable_dev_version True + +# ONNX模型转RKNN模型 +# 将ONNX模型目录拷贝到Fastdeploy根目录 +cp -r ./Portrait_PP_HumanSegV2_Lite_256x144_infer /path/to/Fastdeploy +# 转换模型,模型将生成在Portrait_PP_HumanSegV2_Lite_256x144_infer目录下 +python tools/rknpu2/export.py \ + --config_path tools/rknpu2/config/Portrait_PP_HumanSegV2_Lite_256x144_infer.yaml \ + --target_platform rk3588 +``` + +## 修改yaml配置文件 + +在**模型转换example**中，我们对模型的shape进行了固定，因此对应的yaml文件也要进行修改，如下: + +**原yaml文件** +```yaml +Deploy: + input_shape: + - -1 + - 3 + - -1 + - -1 + model: model.pdmodel + output_dtype: float32 + output_op: none + params: model.pdiparams + transforms: + - target_size: + - 256 + - 144 + type: Resize + - type: Normalize +``` + +**修改后的yaml文件** +```yaml +Deploy: + input_shape: + - 1 + - 3 + - 144 + - 256 + model: model.pdmodel + output_dtype: float32 + output_op: none + params: model.pdiparams + transforms: + - target_size: + - 256 + - 144 + type: Resize + - type: Normalize +``` \ No newline at end of file diff --git a/examples/vision/segmentation/paddleseg/rknpu2/python/README.md b/examples/vision/segmentation/paddleseg/rknpu2/python/README.md index 64460c68e..522744b1d 100644 --- a/examples/vision/segmentation/paddleseg/rknpu2/python/README.md +++ b/examples/vision/segmentation/paddleseg/rknpu2/python/README.md @@ -23,15 +23,11 @@ python3 infer.py --model_file ./Portrait_PP_HumanSegV2_Lite_256x144_infer/Portra --image images/portrait_heng.jpg ``` -运行完成可视化结果如下图所示 -
- -
- ## 注意事项 RKNPU上对模型的输入要求是使用NHWC格式，且图片归一化操作会在转RKNN模型时，内嵌到模型中，因此我们在使用FastDeploy部署时， -需要先调用DisableNormalizePermute(C++)或`disable_normalize_permute(Python)，在预处理阶段禁用归一化以及数据格式的转换。 +需要先调用DisableNormalizeAndPermute(C++)或`disable_normalize_and_permute(Python)，在预处理阶段禁用归一化以及数据格式的转换。 + ## 其它文档 - [PaddleSeg 模型介绍](..) diff --git a/fastdeploy/backends/rknpu/rknpu2/rknpu2_backend.cc b/fastdeploy/backends/rknpu/rknpu2/rknpu2_backend.cc index e018ecc64..bfda43451 100644 --- a/fastdeploy/backends/rknpu/rknpu2/rknpu2_backend.cc +++ b/fastdeploy/backends/rknpu/rknpu2/rknpu2_backend.cc @@ -12,7 +12,7 @@ // See the License for the specific language governing permissions and // limitations under the License. #include "fastdeploy/backends/rknpu/rknpu2/rknpu2_backend.h" - +#include "fastdeploy/utils/perf.h" namespace fastdeploy { RKNPU2Backend::~RKNPU2Backend() { // Release memory uniformly here @@ -178,9 +178,14 @@ bool RKNPU2Backend::GetModelInputOutputInfos() { // get input info and copy to input tensor info for (uint32_t i = 0; i < io_num.n_input; i++) { input_attrs_[i].index = i; + // query info - ret = rknn_query(ctx, RKNN_QUERY_INPUT_ATTR, &(input_attrs_[i]), + ret = rknn_query(ctx, + RKNN_QUERY_INPUT_ATTR, + &(input_attrs_[i]), sizeof(rknn_tensor_attr)); + DumpTensorAttr(input_attrs_[i]); + if (ret != RKNN_SUCC) { printf("rknn_init error! ret=%d\n", ret); return false; @@ -214,8 +219,12 @@ bool RKNPU2Backend::GetModelInputOutputInfos() { for (uint32_t i = 0; i < io_num.n_output; i++) { output_attrs_[i].index = i; // query info - ret = rknn_query(ctx, RKNN_QUERY_OUTPUT_ATTR, &(output_attrs_[i]), + ret = rknn_query(ctx, + RKNN_QUERY_OUTPUT_ATTR, + &(output_attrs_[i]), sizeof(rknn_tensor_attr)); + DumpTensorAttr(output_attrs_[i]); + if (ret != RKNN_SUCC) { FDERROR << "rknn_query fail! ret = " << ret << std::endl; return false; @@ -254,11 +263,12 @@ bool RKNPU2Backend::GetModelInputOutputInfos() { void RKNPU2Backend::DumpTensorAttr(rknn_tensor_attr& attr) { printf("index=%d, name=%s, n_dims=%d, dims=[%d, %d, %d, %d], " "n_elems=%d, size=%d, fmt=%s, type=%s, " - "qnt_type=%s, zp=%d, scale=%f\n", + "qnt_type=%s, zp=%d, scale=%f, pass_through=%d\n", attr.index, attr.name, attr.n_dims, attr.dims[0], attr.dims[1], attr.dims[2], attr.dims[3], attr.n_elems, attr.size, get_format_string(attr.fmt), get_type_string(attr.type), - get_qnt_type_string(attr.qnt_type), attr.zp, attr.scale); + get_qnt_type_string(attr.qnt_type), attr.zp, attr.scale, + attr.pass_through); } TensorInfo RKNPU2Backend::GetInputInfo(int index) { @@ -309,7 +319,12 @@ bool RKNPU2Backend::Infer(std::vector& inputs, input_attrs_[i].type = input_type; input_attrs_[i].size = inputs[0].Nbytes(); input_attrs_[i].size_with_stride = inputs[0].Nbytes(); - input_attrs_[i].pass_through = 0; + if(input_attrs_[i].type == RKNN_TENSOR_FLOAT16 || + input_attrs_[i].type == RKNN_TENSOR_FLOAT32){ + FDINFO << "The input model is not a quantitative model. " + "Close the normalize operation." << std::endl; + } + input_mems_[i] = rknn_create_mem(ctx, inputs[i].Nbytes()); if (input_mems_[i] == nullptr) { FDERROR << "rknn_create_mem input_mems_ error." << std::endl; @@ -340,6 +355,7 @@ bool RKNPU2Backend::Infer(std::vector& inputs, // default output type is depend on model, this requires float32 to compute top5 ret = rknn_set_io_mem(ctx, output_mems_[i], &output_attrs_[i]); + // set output memory and attribute if (ret != RKNN_SUCC) { FDERROR << "output tensor memory rknn_set_io_mem fail! ret=" << ret @@ -350,7 +366,7 @@ bool RKNPU2Backend::Infer(std::vector& inputs, this->infer_init = true; } - + // Copy input data to input tensor memory for (uint32_t i = 0; i < io_num.n_input; i++) { uint32_t width = input_attrs_[i].dims[2]; diff --git a/tools/rknpu2/config/Portrait_PP_HumanSegV2_Lite_256x144_infer.yaml b/tools/rknpu2/config/Portrait_PP_HumanSegV2_Lite_256x144_infer.yaml new file mode 100644 index 000000000..ee5c7212c --- /dev/null +++ b/tools/rknpu2/config/Portrait_PP_HumanSegV2_Lite_256x144_infer.yaml @@ -0,0 +1,15 @@ +mean: + - + - 128.5 + - 128.5 + - 128.5 +std: + - + - 128.5 + - 128.5 + - 128.5 +model_path: ./Portrait_PP_HumanSegV2_Lite_256x144_infer/Portrait_PP_HumanSegV2_Lite_256x144_infer.onnx +outputs_nodes: +do_quantization: True +dataset: "./Portrait_PP_HumanSegV2_Lite_256x144_infer/dataset.txt" +output_folder: "./Portrait_PP_HumanSegV2_Lite_256x144_infer" \ No newline at end of file