Merge https://github.com/PaddlePaddle/PaddleOCR into dygraph

doc/doc_en/angle_class_en.md

@@ -119,7 +119,7 @@ Use `Global.infer_img` to specify the path of the predicted picture or folder, a
 
 ```
 # Predict English results
-python3 tools/infer_cls.py -c configs/cls/cls_mv3.yml -o Global.checkpoints={path/to/weights}/best_accuracy Global.infer_img=doc/imgs_words_en/word_10.png
+python3 tools/infer_cls.py -c configs/cls/cls_mv3.yml -o Global.pretrained_model={path/to/weights}/best_accuracy Global.load_static_weights=false Global.infer_img=doc/imgs_words_en/word_10.png
 ```
 
 Input image:

doc/doc_en/detection_en.md

@@ -113,16 +113,16 @@ python3 tools/eval.py -c configs/det/det_mv3_db.yml  -o Global.checkpoints="{pat
 
 Test the detection result on a single image:
 ```shell
-python3 tools/infer_det.py -c configs/det/det_mv3_db.yml -o Global.infer_img="./doc/imgs_en/img_10.jpg" Global.checkpoints="./output/det_db/best_accuracy"
+python3 tools/infer_det.py -c configs/det/det_mv3_db.yml -o Global.infer_img="./doc/imgs_en/img_10.jpg" Global.pretrained_model="./output/det_db/best_accuracy" Global.load_static_weights=false
 ```
 
 When testing the DB model, adjust the post-processing threshold:
 ```shell
-python3 tools/infer_det.py -c configs/det/det_mv3_db.yml -o Global.infer_img="./doc/imgs_en/img_10.jpg" Global.checkpoints="./output/det_db/best_accuracy" PostProcess.box_thresh=0.6 PostProcess.unclip_ratio=1.5
+python3 tools/infer_det.py -c configs/det/det_mv3_db.yml -o Global.infer_img="./doc/imgs_en/img_10.jpg" Global.pretrained_model="./output/det_db/best_accuracy" Global.load_static_weights=false PostProcess.box_thresh=0.6 PostProcess.unclip_ratio=1.5
 ```
 
 
 Test the detection result on all images in the folder:
 ```shell
-python3 tools/infer_det.py -c configs/det/det_mv3_db.yml -o Global.infer_img="./doc/imgs_en/" Global.checkpoints="./output/det_db/best_accuracy"
+python3 tools/infer_det.py -c configs/det/det_mv3_db.yml -o Global.infer_img="./doc/imgs_en/" Global.pretrained_model="./output/det_db/best_accuracy" Global.load_static_weights=false
 ```

doc/doc_en/inference_en.md

@@ -255,15 +255,18 @@ The following will introduce the lightweight Chinese recognition model inference
 For lightweight Chinese recognition model inference, you can execute the following commands:
 
 ```
-python3 tools/infer/predict_rec.py --image_dir="./doc/imgs_words/ch/word_4.jpg" --rec_model_dir="./inference/rec_crnn/"
+# download CRNN text recognition inference model
+wget  https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_mobile_v2.0_rec_infer.tar
+tar xf ch_ppocr_mobile_v2.0_rec_infer.tar
+python3 tools/infer/predict_rec.py --image_dir="./doc/imgs_words_en/word_10.png" --rec_model_dir="ch_ppocr_mobile_v2.0_rec_infer"
 ```
 
-![](../imgs_words/ch/word_4.jpg)
+![](../imgs_words_en/word_10.png)
 
 After executing the command, the prediction results (recognized text and score) of the above image will be printed on the screen.
 
 ```bash
-Predicts of ./doc/imgs_words/ch/word_4.jpg:('实力活力', 0.98458153)
+Predicts of ./doc/imgs_words_en/word_10.png:('PAIN', 0.9897658)
 ```
 
 <a name="CTC-BASED_RECOGNITION"></a>
@@ -339,7 +342,12 @@ For angle classification model inference, you can execute the following commands
 ```
 python3 tools/infer/predict_cls.py --image_dir="./doc/imgs_words_en/word_10.png" --cls_model_dir="./inference/cls/"
 ```
-
+```
+# download text angle class inference model：
+wget  https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_mobile_v2.0_cls_infer.tar
+tar xf ch_ppocr_mobile_v2.0_cls_infer.tar
+python3 tools/infer/predict_cls.py --image_dir="./doc/imgs_words_en/word_10.png" --cls_model_dir="ch_ppocr_mobile_v2.0_cls_infer"
+```
 ![](../imgs_words_en/word_10.png)
 
 After executing the command, the prediction results (classification angle and score) of the above image will be printed on the screen.

doc/doc_en/recognition_en.md

@@ -317,11 +317,11 @@ Eval:
 <a name="EVALUATION"></a>
 ### EVALUATION
 
-The evaluation data set can be modified via `configs/rec/rec_icdar15_reader.yml` setting of `label_file_path` in EvalReader.
+The evaluation dataset can be set by modifying the `Eval.dataset.label_file_list` field in the `configs/rec/rec_icdar15_train.yml` file.
 
 ```
 # GPU evaluation, Global.checkpoints is the weight to be tested
-python3 -m paddle.distributed.launch --gpus '0' tools/eval.py -c configs/rec/rec_icdar15_reader.yml -o Global.checkpoints={path/to/weights}/best_accuracy
+python3 -m paddle.distributed.launch --gpus '0' tools/eval.py -c configs/rec/rec_icdar15_train.yml -o Global.checkpoints={path/to/weights}/best_accuracy
 ```
 
 <a name="PREDICTION"></a>
@@ -336,7 +336,7 @@ The default prediction picture is stored in `infer_img`, and the weight is speci
 
 ```
 # Predict English results
-python3 tools/infer_rec.py -c configs/rec/ch_ppocr_v2.0/rec_chinese_lite_train_v2.0.yml -o Global.checkpoints={path/to/weights}/best_accuracy TestReader.infer_img=doc/imgs_words/en/word_1.jpg
+python3 tools/infer_rec.py -c configs/rec/ch_ppocr_v2.0/rec_chinese_lite_train_v2.0.yml -o Global.pretrained_model={path/to/weights}/best_accuracy Global.load_static_weights=false Global.infer_img=doc/imgs_words/en/word_1.jpg
 ```
 
 Input image:
@@ -354,7 +354,7 @@ The configuration file used for prediction must be consistent with the training.
 
 ```
 # Predict Chinese results
-python3 tools/infer_rec.py -c configs/rec/ch_ppocr_v2.0/rec_chinese_lite_train_v2.0.yml -o Global.checkpoints={path/to/weights}/best_accuracy TestReader.infer_img=doc/imgs_words/ch/word_1.jpg
+python3 tools/infer_rec.py -c configs/rec/ch_ppocr_v2.0/rec_chinese_lite_train_v2.0.yml -o Global.pretrained_model={path/to/weights}/best_accuracy Global.load_static_weights=false Global.infer_img=doc/imgs_words/ch/word_1.jpg
 ```
 
 Input image:

paddleocr.py

@@ -262,8 +262,8 @@ class PaddleOCR(predict_system.TextSystem):
             logger.error('rec_algorithm must in {}'.format(SUPPORT_REC_MODEL))
             sys.exit(0)
 
-        postprocess_params.rec_char_dict_path = Path(
-            __file__).parent / postprocess_params.rec_char_dict_path
+        postprocess_params.rec_char_dict_path = str(
+            Path(__file__).parent / postprocess_params.rec_char_dict_path)
 
         # init det_model and rec_model
         super().__init__(postprocess_params)

setup.py

@@ -32,7 +32,7 @@ setup(
     package_dir={'paddleocr': ''},
     include_package_data=True,
     entry_points={"console_scripts": ["paddleocr= paddleocr.paddleocr:main"]},
-    version='2.0.1',
+    version='2.0.2',
     install_requires=requirements,
     license='Apache License 2.0',
     description='Awesome OCR toolkits based on PaddlePaddle （8.6M ultra-lightweight pre-trained model, support training and deployment among server, mobile, embeded and IoT devices',

tools/infer/predict_det.py

@@ -35,6 +35,7 @@ logger = get_logger()
 
 class TextDetector(object):
     def __init__(self, args):
+        self.args = args
         self.det_algorithm = args.det_algorithm
         self.use_zero_copy_run = args.use_zero_copy_run
         pre_process_list = [{
@@ -70,6 +71,9 @@ class TextDetector(object):
             postprocess_params["cover_thresh"] = args.det_east_cover_thresh
             postprocess_params["nms_thresh"] = args.det_east_nms_thresh
         elif self.det_algorithm == "SAST":
+            pre_process_list[0] = {
+                'DetResizeForTest': {'resize_long': args.det_limit_side_len}
+            }
             postprocess_params['name'] = 'SASTPostProcess'
             postprocess_params["score_thresh"] = args.det_sast_score_thresh
             postprocess_params["nms_thresh"] = args.det_sast_nms_thresh

tools/infer/utility.py

@@ -33,6 +33,7 @@ def parse_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("--use_fp16", type=str2bool, default=False)
     parser.add_argument("--gpu_mem", type=int, default=8000)
 
     # params for text detector
@@ -46,7 +47,7 @@ def parse_args():
     parser.add_argument("--det_db_thresh", type=float, default=0.3)
     parser.add_argument("--det_db_box_thresh", type=float, default=0.5)
     parser.add_argument("--det_db_unclip_ratio", type=float, default=1.6)
-
+    parser.add_argument("--max_batch_size", type=int, default=10)
     # EAST parmas
     parser.add_argument("--det_east_score_thresh", type=float, default=0.8)
     parser.add_argument("--det_east_cover_thresh", type=float, default=0.1)
@@ -62,7 +63,7 @@ def parse_args():
     parser.add_argument("--rec_model_dir", type=str)
     parser.add_argument("--rec_image_shape", type=str, default="3, 32, 320")
     parser.add_argument("--rec_char_type", type=str, default='ch')
-    parser.add_argument("--rec_batch_num", type=int, default=6)
+    parser.add_argument("--rec_batch_num", type=int, default=1)
     parser.add_argument("--max_text_length", type=int, default=25)
     parser.add_argument(
         "--rec_char_dict_path",
@@ -78,7 +79,7 @@ def parse_args():
     parser.add_argument("--cls_model_dir", type=str)
     parser.add_argument("--cls_image_shape", type=str, default="3, 48, 192")
     parser.add_argument("--label_list", type=list, default=['0', '180'])
-    parser.add_argument("--cls_batch_num", type=int, default=30)
+    parser.add_argument("--cls_batch_num", type=int, default=6)
     parser.add_argument("--cls_thresh", type=float, default=0.9)
 
     parser.add_argument("--enable_mkldnn", type=str2bool, default=False)
@@ -113,6 +114,11 @@ def create_predictor(args, mode, logger):
 
     if args.use_gpu:
         config.enable_use_gpu(args.gpu_mem, 0)
+        if args.use_tensorrt:
+            config.enable_tensorrt_engine(
+                precision_mode=AnalysisConfig.Precision.Half
+                if args.use_fp16 else AnalysisConfig.Precision.Float32,
+                max_batch_size=args.max_batch_size)
     else:
         config.disable_gpu()
         config.set_cpu_math_library_num_threads(6)

tools/program.py

@@ -332,7 +332,7 @@ def eval(model, valid_dataloader, post_process_class, eval_class):
     return metirc
 
 
-def preprocess():
+def preprocess(is_train=False):
     FLAGS = ArgsParser().parse_args()
     config = load_config(FLAGS.config)
     merge_config(FLAGS.opt)
@@ -350,15 +350,17 @@ def preprocess():
     device = paddle.set_device(device)
 
     config['Global']['distributed'] = dist.get_world_size() != 1
-
-    # save_config
-    save_model_dir = config['Global']['save_model_dir']
-    os.makedirs(save_model_dir, exist_ok=True)
-    with open(os.path.join(save_model_dir, 'config.yml'), 'w') as f:
-        yaml.dump(dict(config), f, default_flow_style=False, sort_keys=False)
-
-    logger = get_logger(
-        name='root', log_file='{}/train.log'.format(save_model_dir))
+    if is_train:
+        # save_config
+        save_model_dir = config['Global']['save_model_dir']
+        os.makedirs(save_model_dir, exist_ok=True)
+        with open(os.path.join(save_model_dir, 'config.yml'), 'w') as f:
+            yaml.dump(
+                dict(config), f, default_flow_style=False, sort_keys=False)
+        log_file = '{}/train.log'.format(save_model_dir)
+    else:
+        log_file = None
+    logger = get_logger(name='root', log_file=log_file)
     if config['Global']['use_visualdl']:
         from visualdl import LogWriter
         vdl_writer_path = '{}/vdl/'.format(save_model_dir)

tools/train.py

@@ -110,6 +110,6 @@ def test_reader(config, device, logger):
 
 
 if __name__ == '__main__':
-    config, device, logger, vdl_writer = program.preprocess()
+    config, device, logger, vdl_writer = program.preprocess(is_train=True)
     main(config, device, logger, vdl_writer)
     # test_reader(config, device, logger)