Merge pull request #5693 from WenmuZhou/fix_cpp_lite_android

[Cpp Infer] fix bug in mem copy

deploy/cpp_infer/src/ocr_rec.cpp

@@ -16,10 +16,14 @@
 
 namespace PaddleOCR {
 
-void CRNNRecognizer::Run(std::vector<cv::Mat> img_list, std::vector<double> *times) {
-    std::chrono::duration<float> preprocess_diff = std::chrono::steady_clock::now() - std::chrono::steady_clock::now();
-    std::chrono::duration<float> inference_diff = std::chrono::steady_clock::now() - std::chrono::steady_clock::now();
-    std::chrono::duration<float> postprocess_diff = std::chrono::steady_clock::now() - std::chrono::steady_clock::now();
+void CRNNRecognizer::Run(std::vector<cv::Mat> img_list,
+                         std::vector<double> *times) {
+  std::chrono::duration<float> preprocess_diff =
+      std::chrono::steady_clock::now() - std::chrono::steady_clock::now();
+  std::chrono::duration<float> inference_diff =
+      std::chrono::steady_clock::now() - std::chrono::steady_clock::now();
+  std::chrono::duration<float> postprocess_diff =
+      std::chrono::steady_clock::now() - std::chrono::steady_clock::now();
 
   int img_num = img_list.size();
   std::vector<float> width_list;
@@ -28,27 +32,31 @@ void CRNNRecognizer::Run(std::vector<cv::Mat> img_list, std::vector<double> *tim
   }
   std::vector<int> indices = Utility::argsort(width_list);
 
-    for (int beg_img_no = 0; beg_img_no < img_num; beg_img_no += this->rec_batch_num_) {
+  for (int beg_img_no = 0; beg_img_no < img_num;
+       beg_img_no += this->rec_batch_num_) {
     auto preprocess_start = std::chrono::steady_clock::now();
     int end_img_no = min(img_num, beg_img_no + this->rec_batch_num_);
     float max_wh_ratio = 0;
-        for (int ino = beg_img_no; ino < end_img_no; ino ++) {
+    for (int ino = beg_img_no; ino < end_img_no; ino++) {
       int h = img_list[indices[ino]].rows;
       int w = img_list[indices[ino]].cols;
       float wh_ratio = w * 1.0 / h;
       max_wh_ratio = max(max_wh_ratio, wh_ratio);
     }
+    int batch_width = 0;
     std::vector<cv::Mat> norm_img_batch;
-        for (int ino = beg_img_no; ino < end_img_no; ino ++) {
+    for (int ino = beg_img_no; ino < end_img_no; ino++) {
       cv::Mat srcimg;
       img_list[indices[ino]].copyTo(srcimg);
       cv::Mat resize_img;
-            this->resize_op_.Run(srcimg, resize_img, max_wh_ratio, this->use_tensorrt_);
-            this->normalize_op_.Run(&resize_img, this->mean_, this->scale_, this->is_scale_);
+      this->resize_op_.Run(srcimg, resize_img, max_wh_ratio,
+                           this->use_tensorrt_);
+      this->normalize_op_.Run(&resize_img, this->mean_, this->scale_,
+                              this->is_scale_);
       norm_img_batch.push_back(resize_img);
+      batch_width = max(resize_img.cols, batch_width);
     }
 
-        int batch_width = int(ceilf(32 * max_wh_ratio)) - 1;
     std::vector<float> input(this->rec_batch_num_ * 3 * 32 * batch_width, 0.0f);
     this->permute_op_.Run(norm_img_batch, input.data());
     auto preprocess_end = std::chrono::steady_clock::now();
@@ -86,11 +94,11 @@ void CRNNRecognizer::Run(std::vector<cv::Mat> img_list, std::vector<double> *tim
       float max_value = 0.0f;
 
       for (int n = 0; n < predict_shape[1]; n++) {
-                argmax_idx =
-                    int(Utility::argmax(&predict_batch[(m * predict_shape[1] + n) * predict_shape[2]],
+        argmax_idx = int(Utility::argmax(
+            &predict_batch[(m * predict_shape[1] + n) * predict_shape[2]],
             &predict_batch[(m * predict_shape[1] + n + 1) * predict_shape[2]]));
-                max_value =
-                    float(*std::max_element(&predict_batch[(m * predict_shape[1] + n) * predict_shape[2]],
+        max_value = float(*std::max_element(
+            &predict_batch[(m * predict_shape[1] + n) * predict_shape[2]],
             &predict_batch[(m * predict_shape[1] + n + 1) * predict_shape[2]]));
 
         if (argmax_idx > 0 && (!(n > 0 && argmax_idx == last_index))) {
@@ -116,7 +124,6 @@ void CRNNRecognizer::Run(std::vector<cv::Mat> img_list, std::vector<double> *tim
   times->push_back(double(postprocess_diff.count() * 1000));
 }
 
-    
 void CRNNRecognizer::LoadModel(const std::string &model_dir) {
   //   AnalysisConfig config;
   paddle_infer::Config config;
@@ -133,20 +140,14 @@ void CRNNRecognizer::LoadModel(const std::string &model_dir) {
       if (this->precision_ == "int8") {
         precision = paddle_infer::Config::Precision::kInt8;
       }
-      config.EnableTensorRtEngine(
-          1 << 20, 10, 3,
-          precision,
-          false, false);
+      config.EnableTensorRtEngine(1 << 20, 10, 3, precision, false, false);
 
       std::map<std::string, std::vector<int>> min_input_shape = {
-          {"x", {1, 3, 32, 10}},
-          {"lstm_0.tmp_0", {10, 1, 96}}};
+          {"x", {1, 3, 32, 10}}, {"lstm_0.tmp_0", {10, 1, 96}}};
       std::map<std::string, std::vector<int>> max_input_shape = {
-          {"x", {1, 3, 32, 2000}},
-          {"lstm_0.tmp_0", {1000, 1, 96}}};
+          {"x", {1, 3, 32, 2000}}, {"lstm_0.tmp_0", {1000, 1, 96}}};
       std::map<std::string, std::vector<int>> opt_input_shape = {
-          {"x", {1, 3, 32, 320}},
-          {"lstm_0.tmp_0", {25, 1, 96}}};
+          {"x", {1, 3, 32, 320}}, {"lstm_0.tmp_0", {25, 1, 96}}};
 
       config.SetTRTDynamicShapeInfo(min_input_shape, max_input_shape,
                                     opt_input_shape);
@@ -168,7 +169,7 @@ void CRNNRecognizer::LoadModel(const std::string &model_dir) {
   config.SwitchIrOptim(true);
 
   config.EnableMemoryOptim();
-//   config.DisableGlogInfo();
+  //   config.DisableGlogInfo();
 
   this->predictor_ = CreatePredictor(config);
 }