Improve Ascend

CMakeLists.txt

@@ -66,7 +66,6 @@ option(ENABLE_TEXT "Whether to enable text models usage." OFF)
 option(ENABLE_FLYCV "Whether to enable flycv to boost image preprocess." OFF)
 option(ENABLE_TIMVX "Whether to compile for TIMVX deploy." OFF)
 option(WITH_ASCEND "Whether to compile for Huawei Ascend deploy." OFF)
-option(WITH_ASCEND_PYTHON "Whether to compile for Huawei Ascend deploy using python." OFF)
 option(WITH_TIMVX "Whether to compile for TIMVX deploy." OFF)
 option(WITH_XPU "Whether to compile for KunlunXin XPU deploy." OFF)
 option(WITH_TESTING "Whether to compile with unittest." OFF)
@@ -147,37 +146,7 @@ if (WITH_TIMVX)
 endif()
 
 if (WITH_ASCEND)
-  if(NOT ${ENABLE_LITE_BACKEND})
+  include(${PROJECT_SOURCE_DIR}/cmake/ascend.cmake)
-    set(ENABLE_LITE_BACKEND ON)
-  endif()
-  if(NOT CMAKE_HOST_SYSTEM_PROCESSOR MATCHES "aarch64")
-    message(FATAL_ERROR "Huawei Ascend NPU is supported on Linux aarch64 platform for now.")
-  endif()
-  if(NOT PADDLELITE_URL)
-    set(PADDLELITE_URL "https://bj.bcebos.com/fastdeploy/test/lite-linux_arm64_huawei_ascend_npu_1121.tgz")
-  endif()
-endif()
-
-if (WITH_ASCEND_PYTHON)
-  message(WARNING "This is only for Ascend python version")
-  if(NOT ${ENABLE_LITE_BACKEND})
-      set(ENABLE_LITE_BACKEND ON)
-  endif()
-  if(NOT CMAKE_HOST_SYSTEM_PROCESSOR MATCHES "aarch64")
-    message(FATAL_ERROR "Huawei Ascend NPU is supported on Linux aarch64 platform for now.")
-  endif()
-  if(NOT PADDLELITE_URL)
-    set(PADDLELITE_URL "https://bj.bcebos.com/fastdeploy/test/lite-linux_arm64_huawei_ascend_npu_python_1207.tgz")
-  endif()
-  execute_process(COMMAND sh -c "ls *.so*" WORKING_DIRECTORY ${CMAKE_CURRENT_BINARY_DIR}/third_libs/install/paddlelite/lib
-  COMMAND sh -c "xargs ${PATCHELF_EXE} --set-rpath '$ORIGIN'" WORKING_DIRECTORY ${CMAKE_CURRENT_BINARY_DIR}/third_libs/install/paddlelite/lib
-          RESULT_VARIABLE result
-                OUTPUT_VARIABLE curr_out
-                ERROR_VARIABLE  curr_out)
-  if(ret EQUAL "1")
-    message(FATAL_ERROR "Failed to patchelf Paddle Lite libraries when using Ascend.")
-  endif()
-  message(STATUS "result:${result} out:${curr_out}")
 endif()
 
 if (WITH_XPU)

cmake/summary.cmake

@@ -38,7 +38,6 @@ function(fastdeploy_summary)
   message(STATUS "  ENABLE_TRT_BACKEND        : ${ENABLE_TRT_BACKEND}")
   message(STATUS "  ENABLE_OPENVINO_BACKEND   : ${ENABLE_OPENVINO_BACKEND}")
   message(STATUS "  WITH_ASCEND               : ${WITH_ASCEND}")
-  message(STATUS "  WITH_ASCEND_PYTHON              : ${WITH_ASCEND_PYTHON}") 
   message(STATUS "  WITH_TIMVX                : ${WITH_TIMVX}")
   message(STATUS "  WITH_XPU                  : ${WITH_XPU}")
   if(ENABLE_ORT_BACKEND)

docs/cn/build_and_install/README.md

@@ -27,7 +27,6 @@
 | ENABLE_LITE_BACKEND     | 默认OFF，是否编译集成Paddle Lite后端(编译Android库时需要设置为ON)                          |
 | ENABLE_RKNPU2_BACKEND   | 默认OFF，是否编译集成RKNPU2后端(RK3588/RK3568/RK3566上推荐打开)                           |
 | WITH_ASCEND             | 默认OFF，当在华为昇腾NPU上部署时, 需要设置为ON                                              |
-| WITH_ASCEND_PYTHON      | 默认OFF，当在华为昇腾NPU上,并使用Python部署时, 需要设置为ON                                  |
 | ENABLE_TIMVX            | 默认OFF，需要在RV1126/RV1109上部署时，需设置为ON                                          |
 | WITH_XPU                | 默认OFF，当在昆仑芯XPU上部署时，需设置为ON                                                |
 | WITH_TIMVX              | 默认OFF，需要在RV1126/RV1109/A311D上部署时，需设置为ON                                   |

docs/cn/build_and_install/huawei_ascend.md

@@ -46,9 +46,9 @@ $ npu-smi info
 # 下载 Dockerfile
 $ wget https://bj.bcebos.com/fastdeploy/test/Ascend_ubuntu18.04_aarch64_5.1.rc2.Dockerfile
 # 通过 Dockerfile 生成镜像
-$ docker build --network=host -f Ascend_ubuntu18.04_aarch64_5.1.rc2.Dockerfile -t paddlelite/ascend_aarch64:cann_5.1.rc2 .
+$ docker build --network=host -f Ascend_ubuntu18.04_aarch64_5.1.rc2.Dockerfile -t Paddle Lite/ascend_aarch64:cann_5.1.rc2 .
 # 创建容器
-$ docker run -itd --privileged --name=ascend-aarch64 --net=host -v $PWD:/Work -w /Work --device=/dev/davinci0 --device=/dev/davinci_manager --device=/dev/hisi_hdc --device /dev/devmm_svm -v /usr/local/bin/npu-smi:/usr/local/bin/npu-smi  -v /usr/local/Ascend/driver/:/usr/local/Ascend/driver/ paddlelite/ascend_aarch64:cann_5.1.rc2 /bin/bash
+$ docker run -itd --privileged --name=ascend-aarch64 --net=host -v $PWD:/Work -w /Work --device=/dev/davinci0 --device=/dev/davinci_manager --device=/dev/hisi_hdc --device /dev/devmm_svm -v /usr/local/bin/npu-smi:/usr/local/bin/npu-smi  -v /usr/local/Ascend/driver/:/usr/local/Ascend/driver/ Paddle Lite/ascend_aarch64:cann_5.1.rc2 /bin/bash
 # 进入容器
 $ docker exec -it ascend-aarch64 /bin/bash
 # 确认容器的 Ascend 环境是否创建成功
@@ -86,7 +86,7 @@ make install
 # Download the latest source code
 git clone https://github.com/PaddlePaddle/FastDeploy.git
 cd FastDeploy/python
-export WITH_ASCEND_PYTHON=ON
+export WITH_ASCEND=ON
 export ENABLE_VISION=ON
 
 python setup.py build

docs/en/build_and_install/huawei_ascend.md

@@ -43,9 +43,9 @@ In order to ensure consistency with the FastDeploy verified build environment, i
 # Download Dockerfile
 $ wget https://bj.bcebos.com/fastdeploy/test/Ascend_ubuntu18.04_aarch64_5.1.rc2.Dockerfile
 # Create docker images
-$ docker build --network=host -f Ascend_ubuntu18.04_aarch64_5.1.rc2.Dockerfile -t paddlelite/ascend_aarch64:cann_5.1.rc2 .
+$ docker build --network=host -f Ascend_ubuntu18.04_aarch64_5.1.rc2.Dockerfile -t Paddle Lite/ascend_aarch64:cann_5.1.rc2 .
 # Create container
-$ docker run -itd --privileged --name=ascend-aarch64 --net=host -v $PWD:/Work -w /Work --device=/dev/davinci0 --device=/dev/davinci_manager --device=/dev/hisi_hdc --device /dev/devmm_svm -v /usr/local/bin/npu-smi:/usr/local/bin/npu-smi  -v /usr/local/Ascend/driver/:/usr/local/Ascend/driver/ paddlelite/ascend_aarch64:cann_5.1.rc2 /bin/bash
+$ docker run -itd --privileged --name=ascend-aarch64 --net=host -v $PWD:/Work -w /Work --device=/dev/davinci0 --device=/dev/davinci_manager --device=/dev/hisi_hdc --device /dev/devmm_svm -v /usr/local/bin/npu-smi:/usr/local/bin/npu-smi  -v /usr/local/Ascend/driver/:/usr/local/Ascend/driver/ Paddle Lite/ascend_aarch64:cann_5.1.rc2 /bin/bash
 # Enter the container
 $ docker exec -it ascend-aarch64 /bin/bash
 # Verify that the Ascend environment for the container is created successfully
@@ -84,7 +84,7 @@ When the compilation is complete, the fastdeploy-ascend directory is created in
 # Download the latest source code
 git clone https://github.com/PaddlePaddle/FastDeploy.git
 cd FastDeploy/python
-export WITH_ASCEND_PYTHON=ON
+export WITH_ASCEND=ON
 export ENABLE_VISION=ON
 
 python setup.py build

fastdeploy/vision/ocr/ppocr/dbdetector.cc

@@ -70,14 +70,7 @@ bool DBDetector::BatchPredict(const std::vector<cv::Mat>& images,
     return false;
   }
 
-  reused_input_tensors_[0].name = InputInfoOfRuntime(0).name
+  reused_input_tensors_[0].name = InputInfoOfRuntime(0).name;
-  ;
-
-  for (int i = 0 ; i < reused_input_tensors_.size() ; i ++){
-    std::cout<<"begin to print tensor info in DET"<<std::endl;
-    reused_input_tensors_[i].PrintInfo("TensorInfo[i] IN DET: ") ;
-  }
-
   if (!Infer(reused_input_tensors_, &reused_output_tensors_)) {
     FDERROR << "Failed to inference by runtime." << std::endl;
     return false;

fastdeploy/vision/ocr/ppocr/ocrmodel_pybind.cc

@@ -172,6 +172,7 @@ void BindPPOCRModel(pybind11::module& m) {
     .def_readwrite("mean", &vision::ocr::RecognizerPreprocessor::mean_)
     .def_readwrite("scale", &vision::ocr::RecognizerPreprocessor::scale_)
     .def_readwrite("is_scale", &vision::ocr::RecognizerPreprocessor::is_scale_)
+    .def_readwrite("static_shape", &vision::ocr::RecognizerPreprocessor::static_shape_) 
     .def("run", [](vision::ocr::RecognizerPreprocessor& self, std::vector<pybind11::array>& im_list) {
       std::vector<vision::FDMat> images;
       for (size_t i = 0; i < im_list.size(); ++i) {

fastdeploy/vision/ocr/ppocr/rec_preprocessor.cc

@@ -22,15 +22,16 @@ namespace vision {
 namespace ocr {
 
 void OcrRecognizerResizeImage(FDMat* mat, float max_wh_ratio,
-                              const std::vector<int>& rec_image_shape) {
+                              const std::vector<int>& rec_image_shape, bool static_shape) {
-  int img_c, img_h, img_w;
+  int img_h, img_w;
-  img_c = rec_image_shape[0];
   img_h = rec_image_shape[1];
   img_w = rec_image_shape[2];
 
-  img_w = int(img_h * max_wh_ratio);
+  if (!static_shape) {
 
+    img_w = int(img_h * max_wh_ratio);
     float ratio = float(mat->Width()) / float(mat->Height());
+
     int resize_w;
     if (ceilf(img_h * ratio) > img_w) {
       resize_w = img_w;
@@ -40,6 +41,16 @@ void OcrRecognizerResizeImage(FDMat* mat, float max_wh_ratio,
     Resize::Run(mat, resize_w, img_h);
     std::vector<float> value = {0, 0, 0};
     Pad::Run(mat, 0, 0, 0, int(img_w - mat->Width()), value);
+
+  } else {
+    if (mat->Width() >= img_w) {
+      Resize::Run(mat, img_w, img_h); // Reszie W to 320
+    } else {
+      Resize::Run(mat, mat->Width(), img_h);
+      Pad::Run(mat, 0, 0, 0, int(img_w - mat->Width()), {0,0,0});
+      // Pad to 320
+    } 
+  }
 }
 
 void OcrRecognizerResizeImageOnAscend(FDMat* mat,
@@ -91,11 +102,7 @@ bool RecognizerPreprocessor::Run(std::vector<FDMat>* images, std::vector<FDTenso
       real_index = indices[i];
     }
     FDMat* mat = &(images->at(real_index));
-#if defined(WITH_ASCEND) || defined(WITH_ASCEND_PYTHON)
+    OcrRecognizerResizeImage(mat, max_wh_ratio, rec_image_shape_, static_shape_);
-    OcrRecognizerResizeImageOnAscend(mat, rec_image_shape_); 
-#else
-    OcrRecognizerResizeImage(mat, max_wh_ratio, rec_image_shape_);
-#endif
     NormalizeAndPermute::Run(mat, mean_, scale_, is_scale_);
   }
   // Only have 1 output Tensor.

fastdeploy/vision/ocr/ppocr/rec_preprocessor.h

@@ -39,6 +39,7 @@ class FASTDEPLOY_DECL RecognizerPreprocessor {
   std::vector<float> mean_ = {0.5f, 0.5f, 0.5f};
   std::vector<float> scale_ = {0.5f, 0.5f, 0.5f};
   bool is_scale_ = true;
+  bool static_shape_ = false;
 };
 
 }  // namespace ocr

fastdeploy/vision/ocr/ppocr/recognizer.cc

@@ -85,12 +85,6 @@ bool Recognizer::BatchPredict(const std::vector<cv::Mat>& images,
     return false;
   }
 
-  for (int i = 0 ; i < reused_input_tensors_.size() ; i ++){
-    std::cout<<"begin to print tensor info in REC"<<std::endl;
-    reused_input_tensors_[i].PrintInfo("TensorInfo[i] IN REC: ") ;
-  }
-
-
   reused_input_tensors_[0].name = InputInfoOfRuntime(0).name;
   if (!Infer(reused_input_tensors_, &reused_output_tensors_)) {
     FDERROR << "Failed to inference by runtime." << std::endl;

python/fastdeploy/vision/ocr/ppocr/__init__.py

@@ -508,6 +508,17 @@ class RecognizerPreprocessor:
         """
         return self._preprocessor.run(input_ims)
 
+    @property
+    def static_shape(self):
+        return self._preprocessor.static_shape
+
+    @static_shape.setter
+    def static_shape(self, value):
+        assert isinstance(
+            value,
+            bool), "The value to set `static_shape` must be type of bool."
+        self._preprocessor.static_shape = value
+
     @property
     def is_scale(self):
         return self._preprocessor.is_scale
@@ -626,6 +637,17 @@ class Recognizer(FastDeployModel):
     def postprocessor(self, value):
         self._model.postprocessor = value
 
+    @property
+    def static_shape(self):
+        return self._model.preprocessor.static_shape
+
+    @static_shape.setter
+    def static_shape(self, value):
+        assert isinstance(
+            value,
+            bool), "The value to set `static_shape` must be type of bool."
+        self._model.preprocessor.static_shape = value
+
     @property
     def is_scale(self):
         return self._model.preprocessor.is_scale

python/setup.py

@@ -56,7 +56,7 @@ if os.getenv("BUILD_ON_CPU", "OFF") == "ON":
 setup_configs = dict()
 setup_configs["ENABLE_RKNPU2_BACKEND"] = os.getenv("ENABLE_RKNPU2_BACKEND",
                                                    "OFF")
-setup_configs["WITH_ASCEND_PYTHON"] = os.getenv("WITH_ASCEND_PYTHON", "OFF")
+setup_configs["WITH_ASCEND"] = os.getenv("WITH_ASCEND", "OFF")
 setup_configs["ENABLE_ORT_BACKEND"] = os.getenv("ENABLE_ORT_BACKEND", "OFF")
 setup_configs["ENABLE_OPENVINO_BACKEND"] = os.getenv("ENABLE_OPENVINO_BACKEND",
                                                      "OFF")