add ppocrv3 tipc & test=document_fix

deploy/cpp_infer/src/main.cpp

@@ -77,13 +77,19 @@ int main(int argc, char **argv) {
  for (int i = 0; i < cv_all_img_names.size(); ++i) {
  if (FLAGS_benchmark) {
  cout << cv_all_img_names[i] << '\t';
- for (int n = 0; n < ocr_results[i].size(); n++) {
- for (int m = 0; m < ocr_results[i][n].box.size(); m++) {
- cout << ocr_results[i][n].box[m][0] << ' '
- << ocr_results[i][n].box[m][1] << ' ';
+ if (FLAGS_rec && FLAGS_det) {
+ Utility::print_result(ocr_results[i]);
+ } else if (FLAGS_det) {
+ for (int n = 0; n < ocr_results[i].size(); n++) {
+ for (int m = 0; m < ocr_results[i][n].box.size(); m++) {
+ cout << ocr_results[i][n].box[m][0] << ' '
+ << ocr_results[i][n].box[m][1] << ' ';
+ }
  }
+ cout << endl;
+ } else {
+ Utility::print_result(ocr_results[i]);
  }
- cout << endl;
  } else {
  cout << cv_all_img_names[i] << "\n";
  Utility::print_result(ocr_results[i]);

deploy/cpp_infer/src/ocr_det.cpp

@@ -32,40 +32,46 @@ void DBDetector::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, 1, 20, precision, false, false);
  std::map<std::string, std::vector<int>> min_input_shape = {
  {"x", {1, 3, 50, 50}},
- {"conv2d_92.tmp_0", {1, 96, 20, 20}},
- {"conv2d_91.tmp_0", {1, 96, 10, 10}},
- {"nearest_interp_v2_1.tmp_0", {1, 96, 10, 10}},
- {"nearest_interp_v2_2.tmp_0", {1, 96, 20, 20}},
- {"nearest_interp_v2_3.tmp_0", {1, 24, 20, 20}},
- {"nearest_interp_v2_4.tmp_0", {1, 24, 20, 20}},
- {"nearest_interp_v2_5.tmp_0", {1, 24, 20, 20}},
+ {"conv2d_92.tmp_0", {1, 120, 20, 20}},
+ {"conv2d_91.tmp_0", {1, 24, 10, 10}},
+ {"conv2d_59.tmp_0", {1, 96, 20, 20}},
+ {"nearest_interp_v2_1.tmp_0", {1, 256, 10, 10}},
+ {"nearest_interp_v2_2.tmp_0", {1, 256, 20, 20}},
+ {"conv2d_124.tmp_0", {1, 256, 20, 20}},
+ {"nearest_interp_v2_3.tmp_0", {1, 64, 20, 20}},
+ {"nearest_interp_v2_4.tmp_0", {1, 64, 20, 20}},
+ {"nearest_interp_v2_5.tmp_0", {1, 64, 20, 20}},
  {"elementwise_add_7", {1, 56, 2, 2}},
- {"nearest_interp_v2_0.tmp_0", {1, 96, 2, 2}}};
+ {"nearest_interp_v2_0.tmp_0", {1, 256, 2, 2}}};
  std::map<std::string, std::vector<int>> max_input_shape = {
  {"x", {1, 3, this->max_side_len_, this->max_side_len_}},
- {"conv2d_92.tmp_0", {1, 96, 400, 400}},
- {"conv2d_91.tmp_0", {1, 96, 200, 200}},
- {"nearest_interp_v2_1.tmp_0", {1, 96, 200, 200}},
- {"nearest_interp_v2_2.tmp_0", {1, 96, 400, 400}},
- {"nearest_interp_v2_3.tmp_0", {1, 24, 400, 400}},
- {"nearest_interp_v2_4.tmp_0", {1, 24, 400, 400}},
- {"nearest_interp_v2_5.tmp_0", {1, 24, 400, 400}},
+ {"conv2d_92.tmp_0", {1, 120, 400, 400}},
+ {"conv2d_91.tmp_0", {1, 24, 200, 200}},
+ {"conv2d_59.tmp_0", {1, 96, 400, 400}},
+ {"nearest_interp_v2_1.tmp_0", {1, 256, 200, 200}},
+ {"nearest_interp_v2_2.tmp_0", {1, 256, 400, 400}},
+ {"conv2d_124.tmp_0", {1, 256, 400, 400}},
+ {"nearest_interp_v2_3.tmp_0", {1, 64, 400, 400}},
+ {"nearest_interp_v2_4.tmp_0", {1, 64, 400, 400}},
+ {"nearest_interp_v2_5.tmp_0", {1, 64, 400, 400}},
  {"elementwise_add_7", {1, 56, 400, 400}},
- {"nearest_interp_v2_0.tmp_0", {1, 96, 400, 400}}};
+ {"nearest_interp_v2_0.tmp_0", {1, 256, 400, 400}}};
  std::map<std::string, std::vector<int>> opt_input_shape = {
  {"x", {1, 3, 640, 640}},
- {"conv2d_92.tmp_0", {1, 96, 160, 160}},
- {"conv2d_91.tmp_0", {1, 96, 80, 80}},
- {"nearest_interp_v2_1.tmp_0", {1, 96, 80, 80}},
- {"nearest_interp_v2_2.tmp_0", {1, 96, 160, 160}},
- {"nearest_interp_v2_3.tmp_0", {1, 24, 160, 160}},
- {"nearest_interp_v2_4.tmp_0", {1, 24, 160, 160}},
- {"nearest_interp_v2_5.tmp_0", {1, 24, 160, 160}},
+ {"conv2d_92.tmp_0", {1, 120, 160, 160}},
+ {"conv2d_91.tmp_0", {1, 24, 80, 80}},
+ {"conv2d_59.tmp_0", {1, 96, 160, 160}},
+ {"nearest_interp_v2_1.tmp_0", {1, 256, 80, 80}},
+ {"nearest_interp_v2_2.tmp_0", {1, 256, 160, 160}},
+ {"conv2d_124.tmp_0", {1, 256, 160, 160}},
+ {"nearest_interp_v2_3.tmp_0", {1, 64, 160, 160}},
+ {"nearest_interp_v2_4.tmp_0", {1, 64, 160, 160}},
+ {"nearest_interp_v2_5.tmp_0", {1, 64, 160, 160}},
  {"elementwise_add_7", {1, 56, 40, 40}},
- {"nearest_interp_v2_0.tmp_0", {1, 96, 40, 40}}};
+ {"nearest_interp_v2_0.tmp_0", {1, 256, 40, 40}}};
 
  config.SetTRTDynamicShapeInfo(min_input_shape, max_input_shape,
  opt_input_shape);

deploy/cpp_infer/src/ocr_rec.cpp

@@ -143,15 +143,17 @@ 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, 15, precision, false, false);
  int imgH = this->rec_image_shape_[1];
  int imgW = this->rec_image_shape_[2];
  std::map<std::string, std::vector<int>> min_input_shape = {
  {"x", {1, 3, imgH, 10}}, {"lstm_0.tmp_0", {10, 1, 96}}};
  std::map<std::string, std::vector<int>> max_input_shape = {
- {"x", {1, 3, imgH, 2000}}, {"lstm_0.tmp_0", {1000, 1, 96}}};
+ {"x", {this->rec_batch_num_, 3, imgH, 2500}},
+ {"lstm_0.tmp_0", {1000, 1, 96}}};
  std::map<std::string, std::vector<int>> opt_input_shape = {
- {"x", {1, 3, imgH, imgW}}, {"lstm_0.tmp_0", {25, 1, 96}}};
+ {"x", {this->rec_batch_num_, 3, imgH, imgW}},
+ {"lstm_0.tmp_0", {25, 1, 96}}};
 
  config.SetTRTDynamicShapeInfo(min_input_shape, max_input_shape,
  opt_input_shape);

deploy/pdserving/pipeline_http_client.py

@@ -19,8 +19,16 @@
 import os
 
 import argparse
+
+
+def str2bool(v):
+ return v.lower() in ("true", "t", "1")
+
+
 parser = argparse.ArgumentParser(description="args for paddleserving")
 parser.add_argument("--image_dir", type=str, default="../../doc/imgs/")
+parser.add_argument("--det", type=str2bool, default=True)
+parser.add_argument("--rec", type=str2bool, default=True)
 args = parser.parse_args()
 
 
@@ -46,13 +54,17 @@ def cv2_to_base64(image):
  # check success
  if result["err_no"] == 0:
  ocr_result = result["value"][0]
- try:
- for item in eval(ocr_result):
- # return transcription and points
- print("{}, {}".format(item[0], item[1]))
- except Exception as e:
- print("No results")
- continue
+ if not args.det:
+ print(ocr_result)
+ else:
+ try:
+ for item in eval(ocr_result):
+ # return transcription and points
+ print("{}, {}".format(item[0], item[1]))
+ except Exception as e:
+ print(ocr_result)
+ print("No results")
+ continue
 
  else:
  print(

test_tipc/configs/ch_PP-OCRv3/model_linux_gpu_normal_normal_infer_cpp_linux_gpu_cpu.txt

@@ -0,0 +1,20 @@
+===========================cpp_infer_params===========================
+model_name:ocr_system_v3.0
+use_opencv:True
+infer_model:./inference/ch_PP-OCRv3_det_infer/
+infer_quant:False
+inference:./deploy/cpp_infer/build/ppocr --rec_img_h=48 --rec_char_dict_path=./ppocr/utils/ppocr_keys_v1.txt
+--use_gpu:True|False
+--enable_mkldnn:True|False
+--cpu_threads:1|6
+--rec_batch_num:1
+--use_tensorrt:False|True
+--precision:fp32|fp16
+--det_model_dir:
+--image_dir:./inference/ch_det_data_50/all-sum-510/
+--rec_model_dir:./inference/ch_PP-OCRv3_rec_infer/
+--benchmark:True
+--det:True
+--rec:True
+--cls:False
+--use_angle_cls:False

test_tipc/configs/ch_PP-OCRv3/model_linux_gpu_normal_normal_infer_python_linux_gpu_cpu.txt

@@ -0,0 +1,19 @@
+===========================ch_PP-OCRv2===========================
+model_name:ch_PP-OCRv3
+python:python3.7
+infer_model:./inference/ch_PP-OCRv3_det_infer/
+infer_export:null
+infer_quant:False
+inference:tools/infer/predict_system.py --rec_image_shape="3,48,320"
+--use_gpu:False|True
+--enable_mkldnn:False|True
+--cpu_threads:1|6
+--rec_batch_num:1
+--use_tensorrt:False|True
+--precision:fp32
+--det_model_dir:
+--image_dir:./inference/ch_det_data_50/all-sum-510/
+--rec_model_dir:./inference/ch_PP-OCRv3_rec_infer/
+--benchmark:True
+null:null
+null:null

test_tipc/configs/ch_PP-OCRv3/model_linux_gpu_normal_normal_lite_cpp_arm_cpu.txt

@@ -0,0 +1,13 @@
+===========================lite_params===========================
+inference:./ocr_db_crnn system
+runtime_device:ARM_CPU
+det_infer_model:ch_PP-OCRv3_det_infer|ch_PP-OCRv3_det_slim_quant_infer
+rec_infer_model:ch_PP-OCRv3_rec_infer|ch_PP-OCRv3_rec_slim_quant_infer
+cls_infer_model:ch_ppocr_mobile_v2.0_cls_infer|ch_ppocr_mobile_v2.0_cls_slim_infer
+--cpu_threads:1|4
+--det_batch_size:1
+--rec_batch_size:1
+--image_dir:./test_data/icdar2015_lite/text_localization/ch4_test_images/
+--config_dir:./config.txt
+--rec_dict_dir:./ppocr_keys_v1.txt
+--benchmark:True

test_tipc/configs/ch_PP-OCRv3/model_linux_gpu_normal_normal_lite_cpp_arm_gpu_opencl.txt

@@ -0,0 +1,13 @@
+===========================lite_params===========================
+inference:./ocr_db_crnn system
+runtime_device:ARM_GPU_OPENCL
+det_infer_model:ch_PP-OCRv3_det_infer|ch_PP-OCRv3_det_slim_quant_infer
+rec_infer_model:ch_PP-OCRv3_rec_infer|ch_PP-OCRv3_rec_slim_quant_infer
+cls_infer_model:ch_ppocr_mobile_v2.0_cls_infer|ch_ppocr_mobile_v2.0_cls_slim_infer
+--cpu_threads:1|4
+--det_batch_size:1
+--rec_batch_size:1
+--image_dir:./test_data/icdar2015_lite/text_localization/ch4_test_images/
+--config_dir:./config.txt
+--rec_dict_dir:./ppocr_keys_v1.txt
+--benchmark:True

test_tipc/configs/ch_PP-OCRv3_det/model_linux_gpu_normal_normal_infer_cpp_linux_gpu_cpu.txt

@@ -0,0 +1,20 @@
+===========================cpp_infer_params===========================
+model_name:ocr_det_v3.0
+use_opencv:True
+infer_model:./inference/ch_PP-OCRv3_det_infer/
+infer_quant:False
+inference:./deploy/cpp_infer/build/ppocr
+--use_gpu:True|False
+--enable_mkldnn:True|False
+--cpu_threads:1|6
+--rec_batch_num:1
+--use_tensorrt:False|True
+--precision:fp32|fp16
+--det_model_dir:
+--image_dir:./inference/ch_det_data_50/all-sum-510/
+null:null
+--benchmark:True
+--det:True
+--rec:False
+--cls:False
+--use_angle_cls:False

test_tipc/configs/ch_PP-OCRv3_det/model_linux_gpu_normal_normal_lite_cpp_arm_cpu.txt

@@ -0,0 +1,13 @@
+===========================lite_params===========================
+inference:./ocr_db_crnn det
+runtime_device:ARM_CPU
+det_infer_model:ch_PP-OCRv3_det_infer|ch_PP-OCRv3_det_slim_quant_infer
+null:null
+null:null
+--cpu_threads:1|4
+--det_batch_size:1
+null:null
+--image_dir:./test_data/icdar2015_lite/text_localization/ch4_test_images/
+--config_dir:./config.txt
+null:null
+--benchmark:True

test_tipc/configs/ch_PP-OCRv3_det/model_linux_gpu_normal_normal_lite_cpp_arm_gpu_opencl.txt

@@ -0,0 +1,13 @@
+===========================lite_params===========================
+inference:./ocr_db_crnn det
+runtime_device:ARM_GPU_OPENCL
+det_infer_model:ch_PP-OCRv3_det_infer|ch_PP-OCRv3_det_slim_quant_infer
+null:null
+null:null
+--cpu_threads:1|4
+--det_batch_size:1
+null:null
+--image_dir:./test_data/icdar2015_lite/text_localization/ch4_test_images/
+--config_dir:./config.txt
+null:null
+--benchmark:True

test_tipc/configs/ch_PP-OCRv3_det/model_linux_gpu_normal_normal_paddle2onnx_python_linux_cpu.txt

@@ -0,0 +1,14 @@
+===========================paddle2onnx_params===========================
+model_name:ocr_det_v3
+python:python3.7
+2onnx: paddle2onnx
+--model_dir:./inference/ch_PP-OCRv3_det_infer/
+--model_filename:inference.pdmodel
+--params_filename:inference.pdiparams
+--save_file:./inference/det_v3_onnx/model.onnx
+--opset_version:10
+--enable_onnx_checker:True
+inference:tools/infer/predict_det.py
+--use_gpu:True|False
+--det_model_dir:
+--image_dir:./inference/ch_det_data_50/all-sum-510/

test_tipc/configs/ch_PP-OCRv3_det/model_linux_gpu_normal_normal_serving_python_linux_gpu_cpu.txt

@@ -0,0 +1,18 @@
+===========================serving_params===========================
+model_name:ocr_det_v3
+python:python3.7
+trans_model:-m paddle_serving_client.convert
+--dirname:./inference/ch_PP-OCRv3_det_infer/
+--model_filename:inference.pdmodel
+--params_filename:inference.pdiparams
+--serving_server:./deploy/pdserving/ppocr_det_v3_serving/
+--serving_client:./deploy/pdserving/ppocr_det_v3_client/
+serving_dir:./deploy/pdserving
+web_service:web_service_det.py --config=config.yml --opt op.det.concurrency="1"
+op.det.local_service_conf.devices:gpu|null
+op.det.local_service_conf.use_mkldnn:True|False
+op.det.local_service_conf.thread_num:1|6
+op.det.local_service_conf.use_trt:False|True
+op.det.local_service_conf.precision:fp32|fp16|int8
+pipline:pipeline_rpc_client.py|pipeline_http_client.py
+--image_dir:../../doc/imgs

test_tipc/configs/ch_PP-OCRv3_det/train_infer_python.txt

@@ -0,0 +1,53 @@
+===========================train_params===========================
+model_name:ch_PPOCRv3_det
+python:python3.7
+gpu_list:0|0,1
+Global.use_gpu:True|True
+Global.auto_cast:fp32
+Global.epoch_num:lite_train_lite_infer=1|whole_train_whole_infer=500
+Global.save_model_dir:./output/
+Train.loader.batch_size_per_card:lite_train_lite_infer=2|whole_train_whole_infer=4
+Global.pretrained_model:null
+train_model_name:latest
+train_infer_img_dir:./train_data/icdar2015/text_localization/ch4_test_images/
+null:null
+##
+trainer:norm_train
+norm_train:tools/train.py -c configs/det/ch_PP-OCRv3/ch_PP-OCRv3_det_cml.yml -o 
+pact_train:null
+fpgm_train:null
+distill_train:null
+null:null
+null:null
+##
+===========================eval_params=========================== 
+eval:null
+null:null
+##
+===========================infer_params===========================
+Global.save_inference_dir:./output/
+Global.checkpoints:
+norm_export:tools/export_model.py -c configs/det/ch_PP-OCRv3/ch_PP-OCRv3_det_cml.yml -o 
+quant_export:null
+fpgm_export: 
+distill_export:null
+export1:null
+export2:null
+inference_dir:Student
+infer_model:./inference/ch_PP-OCRv3_det_infer/
+infer_export:null
+infer_quant:False
+inference:tools/infer/predict_det.py
+--use_gpu:True|False
+--enable_mkldnn:True|False
+--cpu_threads:1|6
+--rec_batch_num:1
+--use_tensorrt:False|True
+--precision:fp32|fp16|int8
+--det_model_dir:
+--image_dir:./inference/ch_det_data_50/all-sum-510/
+null:null
+--benchmark:True
+null:null
+===========================infer_benchmark_params==========================
+random_infer_input:[{float32,[3,640,640]}];[{float32,[3,960,960]}]