Merge remote-tracking branch 'origin/dygraph' into dygraph

deploy/cpp_infer/CMakeLists.txt

@@ -1,4 +1,5 @@
 project(ppocr CXX C)
+cmake_minimum_required(VERSION 3.14)
 
 option(WITH_MKL        "Compile demo with MKL/OpenBlas support, default use MKL."       ON)
 option(WITH_GPU        "Compile demo with GPU/CPU, default use CPU."                    OFF)
@@ -206,13 +207,12 @@ endif()
 
 set(DEPS ${DEPS} ${OpenCV_LIBS})
 
-include(ExternalProject)
+include(FetchContent)
 include(external-cmake/auto-log.cmake)
-include_directories(${CMAKE_CURRENT_BINARY_DIR}/autolog/src/extern_Autolog/auto_log)
+include_directories(${FETCHCONTENT_BASE_DIR}/extern_autolog-src)
 
 AUX_SOURCE_DIRECTORY(./src SRCS)
 add_executable(${DEMO_NAME} ${SRCS})
-
 target_link_libraries(${DEMO_NAME} ${DEPS})
 
 if (WIN32 AND WITH_MKL)

deploy/cpp_infer/external-cmake/auto-log.cmake

@@ -1,14 +1,13 @@
 find_package(Git REQUIRED)
-message("${CMAKE_BUILD_TYPE}")
+include(FetchContent)
 
-set(AUTOLOG_REPOSITORY     https://github.com/LDOUBLEV/AutoLog.git)
-SET(AUTOLOG_INSTALL_DIR   ${CMAKE_CURRENT_BINARY_DIR}/install/Autolog)
+set(FETCHCONTENT_BASE_DIR "${CMAKE_CURRENT_BINARY_DIR}/third-party")
 
-ExternalProject_Add(
-    extern_Autolog
-    PREFIX autolog
-    GIT_REPOSITORY ${AUTOLOG_REPOSITORY}
-    GIT_TAG main
-    DOWNLOAD_NO_EXTRACT True
-    INSTALL_COMMAND cmake -E echo "Skipping install step."
+FetchContent_Declare(
+  extern_Autolog
+  PREFIX autolog
+  GIT_REPOSITORY https://github.com/LDOUBLEV/AutoLog.git
+  GIT_TAG        main
 )
+FetchContent_MakeAvailable(extern_Autolog)
+

deploy/cpp_infer/src/main.cpp

@@ -35,6 +35,7 @@
 #include <sys/stat.h>
 
 #include <gflags/gflags.h>
+#include "auto_log/autolog.h"
 
 DEFINE_bool(use_gpu, false, "Infering with GPU or CPU.");
 DEFINE_int32(gpu_id, 0, "Device id of GPU to execute.");

tests/compare_results.py

@@ -0,0 +1,133 @@
+import numpy as np
+import os
+import subprocess
+import json
+import argparse
+import glob
+
+
+def init_args():
+    parser = argparse.ArgumentParser()
+    # params for testing assert allclose
+    parser.add_argument("--atol", type=float, default=1e-3)
+    parser.add_argument("--rtol", type=float, default=1e-3)
+    parser.add_argument("--gt_file", type=str, default="")
+    parser.add_argument("--log_file", type=str, default="")
+    parser.add_argument("--precision", type=str, default="fp32")
+    return parser
+
+
+def parse_args():
+    parser = init_args()
+    return parser.parse_args()
+
+
+def run_shell_command(cmd):
+    p = subprocess.Popen(
+        cmd, stdout=subprocess.PIPE, stderr=subprocess.PIPE, shell=True)
+    out, err = p.communicate()
+
+    if p.returncode == 0:
+        return out.decode('utf-8')
+    else:
+        return None
+
+
+def parser_results_from_log_by_name(log_path, names_list):
+    if not os.path.exists(log_path):
+        raise ValueError("The log file {} does not exists!".format(log_path))
+
+    if names_list is None or len(names_list) < 1:
+        return []
+
+    parser_results = {}
+    for name in names_list:
+        cmd = "grep {} {}".format(name, log_path)
+        outs = run_shell_command(cmd)
+        outs = outs.split("\n")[0]
+        result = outs.split("{}".format(name))[-1]
+        result = json.loads(result)
+        parser_results[name] = result
+    return parser_results
+
+
+def load_gt_from_file(gt_file):
+    if not os.path.exists(gt_file):
+        raise ValueError("The log file {} does not exists!".format(gt_file))
+    with open(gt_file, 'r') as f:
+        data = f.readlines()
+        f.close()
+    parser_gt = {}
+    for line in data:
+        image_name, result = line.strip("\n").split("\t")
+        result = json.loads(result)
+        parser_gt[image_name] = result
+    return parser_gt
+
+
+def load_gt_from_txts(gt_file):
+    gt_list = glob.glob(gt_file)
+    gt_collection = {}
+    for gt_f in gt_list:
+        gt_dict = load_gt_from_file(gt_f)
+        basename = os.path.basename(gt_f)
+        if "fp32" in basename:
+            gt_collection["fp32"] = [gt_dict, gt_f]
+        elif "fp16" in basename:
+            gt_collection["fp16"] = [gt_dict, gt_f]
+        elif "int8" in basename:
+            gt_collection["int8"] = [gt_dict, gt_f]
+        else:
+            continue
+    return gt_collection
+
+
+def collect_predict_from_logs(log_path, key_list):
+    log_list = glob.glob(log_path)
+    pred_collection = {}
+    for log_f in log_list:
+        pred_dict = parser_results_from_log_by_name(log_f, key_list)
+        key = os.path.basename(log_f)
+        pred_collection[key] = pred_dict
+
+    return pred_collection
+
+
+def testing_assert_allclose(dict_x, dict_y, atol=1e-7, rtol=1e-7):
+    for k in dict_x:
+        np.testing.assert_allclose(
+            np.array(dict_x[k]), np.array(dict_y[k]), atol=atol, rtol=rtol)
+
+
+if __name__ == "__main__":
+    # Usage:
+    # python3.7 tests/compare_results.py --gt_file=./tests/results/*.txt  --log_file=./tests/output/infer_*.log
+
+    args = parse_args()
+
+    gt_collection = load_gt_from_txts(args.gt_file)
+    key_list = gt_collection["fp32"][0].keys()
+
+    pred_collection = collect_predict_from_logs(args.log_file, key_list)
+    for filename in pred_collection.keys():
+        if "fp32" in filename:
+            gt_dict, gt_filename = gt_collection["fp32"]
+        elif "fp16" in filename:
+            gt_dict, gt_filename = gt_collection["fp16"]
+        elif "int8" in filename:
+            gt_dict, gt_filename = gt_collection["int8"]
+        else:
+            continue
+        pred_dict = pred_collection[filename]
+
+        try:
+            testing_assert_allclose(
+                gt_dict, pred_dict, atol=args.atol, rtol=args.rtol)
+            print(
+                "Assert allclose passed! The results of {} and {} are consistent!".
+                format(filename, gt_filename))
+        except Exception as E:
+            print(E)
+            raise ValueError(
+                "The results of {} and the results of {} are inconsistent!".
+                format(filename, gt_filename))

tools/export_model.py

@@ -93,6 +93,9 @@ def main():
             for key in config["Architecture"]["Models"]:
                 config["Architecture"]["Models"][key]["Head"][
                     "out_channels"] = char_num
+                # just one final tensor needs to to exported for inference
+                config["Architecture"]["Models"][key][
+                    "return_all_feats"] = False
         else:  # base rec model
             config["Architecture"]["Head"]["out_channels"] = char_num
     model = build_model(config["Architecture"])

tools/infer/predict_det.py

@@ -30,7 +30,7 @@ from ppocr.utils.logging import get_logger
 from ppocr.utils.utility import get_image_file_list, check_and_read_gif
 from ppocr.data import create_operators, transform
 from ppocr.postprocess import build_post_process
-
+import json
 logger = get_logger()
 
 
@@ -243,6 +243,7 @@ if __name__ == "__main__":
 
     if not os.path.exists(draw_img_save):
         os.makedirs(draw_img_save)
+    save_results = []
     for image_file in image_file_list:
         img, flag = check_and_read_gif(image_file)
         if not flag:
@@ -256,8 +257,11 @@ if __name__ == "__main__":
         if count > 0:
             total_time += elapse
         count += 1
-
-        logger.info("Predict time of {}: {}".format(image_file, elapse))
+        save_pred = os.path.basename(image_file) + "\t" + str(
+            json.dumps(np.array(dt_boxes).astype(np.int32).tolist())) + "\n"
+        save_results.append(save_pred)
+        logger.info(save_pred)
+        logger.info("The predict time of {}: {}".format(image_file, elapse))
         src_im = utility.draw_text_det_res(dt_boxes, image_file)
         img_name_pure = os.path.split(image_file)[-1]
         img_path = os.path.join(draw_img_save,
@@ -265,5 +269,8 @@ if __name__ == "__main__":
         cv2.imwrite(img_path, src_im)
         logger.info("The visualized image saved in {}".format(img_path))
 
+    with open(os.path.join(draw_img_save, "det_results.txt"), 'w') as f:
+        f.writelines(save_results)
+        f.close()
     if args.benchmark:
         text_detector.autolog.report()

tools/infer/utility.py

@@ -35,7 +35,7 @@ def init_args():
     parser.add_argument("--use_gpu", type=str2bool, default=True)
     parser.add_argument("--ir_optim", type=str2bool, default=True)
     parser.add_argument("--use_tensorrt", type=str2bool, default=False)
-    parser.add_argument("--min_subgraph_size", type=int, default=10)
+    parser.add_argument("--min_subgraph_size", type=int, default=15)
     parser.add_argument("--precision", type=str, default="fp32")
     parser.add_argument("--gpu_mem", type=int, default=500)
 

tools/infer_rec.py

@@ -121,7 +121,7 @@ def main():
                     if len(post_result[key][0]) >= 2:
                         rec_info[key] = {
                             "label": post_result[key][0][0],
-                            "score": post_result[key][0][1],
+                            "score": float(post_result[key][0][1]),
                         }
                 info = json.dumps(rec_info)
             else: