Merge pull request #3268 from tink2123/autolog_rec

add autolog for infer_rec

doc/doc_en/update_en.md

@@ -15,8 +15,6 @@
 - 2020.6.8 Add [datasets](./datasets_en.md) and keep updating
 - 2020.6.5 Support exporting `attention` model to `inference_model`
 - 2020.6.5 Support separate prediction and recognition, output result score
-- 2020.6.5 Support exporting `attention` model to `inference_model`
-- 2020.6.5 Support separate prediction and recognition, output result score
 - 2020.5.30 Provide Lightweight Chinese OCR online experience
 - 2020.5.30 Model prediction and training support on Windows system
 - 2020.5.30 Open source general Chinese OCR model

test/ocr_rec_params.txt

+model_name:ocr_rec
+python:python
+gpu_list:0|0,1
+Global.auto_cast:null
+Global.epoch_num:10
+Global.save_model_dir:./output/
+Train.loader.batch_size_per_card:
+Global.use_gpu:
+Global.pretrained_model:null
+
+trainer:norm|pact
+norm_train:tools/train.py -c configs/rec/rec_mv3_none_bilstm_ctc.yml
+quant_train:deploy/slim/quantization/quant.py -c configs/rec/rec_mv3_none_bilstm_ctc.yml
+fpgm_train:null
+distill_train:null
+
+eval:tools/eval.py -c configs/rec/rec_mv3_none_bilstm_ctc.yml -o
+
+Global.save_inference_dir:./output/
+Global.pretrained_model:
+norm_export:tools/export_model.py -c configs/rec/rec_mv3_none_bilstm_ctc.yml -o
+quant_export:deploy/slim/quantization/export_model.py -c configs/rec/rec_mv3_none_bilstm_ctc.yml -o
+fpgm_export:null
+distill_export:null
+
+inference:tools/infer/predict_rec.py
+--use_gpu:True|False
+--enable_mkldnn:True|False
+--cpu_threads:1|6
+--rec_batch_num:1
+--use_tensorrt:True|False
+--precision:fp32|fp16|int8
+--rec_model_dir:./inference/ch_ppocr_mobile_v2.0_rec_infer/
+--image_dir:./inference/rec_inference
+--save_log_path:./test/output/
\ No newline at end of file

test/prepare.sh

@@ -29,19 +29,21 @@ train_model_list=$(func_parser_value "${lines[0]}")
 
 trainer_list=$(func_parser_value "${lines[10]}")
 
-
 # MODE be one of ['lite_train_infer' 'whole_infer' 'whole_train_infer']
 MODE=$2
-# prepare pretrained weights and dataset 
-wget -nc -P  ./pretrain_models/ https://paddle-imagenet-models-name.bj.bcebos.com/dygraph/MobileNetV3_large_x0_5_pretrained.pdparams
-wget -nc -P ./pretrain_models/ https://paddleocr.bj.bcebos.com/dygraph_v2.0/en/det_mv3_db_v2.0_train.tar
-cd pretrain_models && tar xf det_mv3_db_v2.0_train.tar && cd ../
-
+# prepare pretrained weights and dataset
+if [ ${train_model_list[*]} = "ocr_det" ]; then
+  wget -nc -P  ./pretrain_models/ https://paddle-imagenet-models-name.bj.bcebos.com/dygraph/MobileNetV3_large_x0_5_pretrained.pdparams
+  wget -nc -P ./pretrain_models/ https://paddleocr.bj.bcebos.com/dygraph_v2.0/en/det_mv3_db_v2.0_train.tar
+  cd pretrain_models && tar xf det_mv3_db_v2.0_train.tar && cd ../
+  fi
 if [ ${MODE} = "lite_train_infer" ];then
     # pretrain lite train data
     rm -rf ./train_data/icdar2015
     wget -nc -P ./train_data/ https://paddleocr.bj.bcebos.com/dygraph_v2.0/test/icdar2015_lite.tar
-    cd ./train_data/ && tar xf icdar2015_lite.tar
+    wget -nc -P ./train_data/ https://paddleocr.bj.bcebos.com/dygraph_v2.0/test/ic15_data.tar # todo change to bcebos
+
+    cd ./train_data/ && tar xf icdar2015_lite.tar && tar xf ic15_data.tar
     ln -s ./icdar2015_lite ./icdar2015
     cd ../
     epoch=10
@@ -49,13 +51,15 @@ if [ ${MODE} = "lite_train_infer" ];then
 elif [ ${MODE} = "whole_train_infer" ];then
     rm -rf ./train_data/icdar2015
     wget -nc -P ./train_data/ https://paddleocr.bj.bcebos.com/dygraph_v2.0/test/icdar2015.tar
-    cd ./train_data/ && tar xf icdar2015.tar && cd ../
+    wget -nc -P ./train_data/ https://paddleocr.bj.bcebos.com/dygraph_v2.0/test/ic15_data.tar
+    cd ./train_data/ && tar xf icdar2015.tar && tar xf ic15_data.tar && cd ../
     epoch=500
     eval_batch_step=200
 elif [ ${MODE} = "whole_infer" ];then
     rm -rf ./train_data/icdar2015
     wget -nc -P ./train_data/ https://paddleocr.bj.bcebos.com/dygraph_v2.0/test/icdar2015_infer.tar
-    cd ./train_data/ && tar xf icdar2015_infer.tar
+    wget -nc -P ./train_data/ https://paddleocr.bj.bcebos.com/dygraph_v2.0/test/ic15_data.tar
+    cd ./train_data/ && tar xf icdar2015_infer.tar && tar xf ic15_data.tar
     ln -s ./icdar2015_infer ./icdar2015
     cd ../
     epoch=10
@@ -88,9 +92,11 @@ for train_model in ${train_model_list[*]}; do
     elif [ ${train_model} = "ocr_rec" ];then
         model_name="ocr_rec"
         yml_file="configs/rec/rec_mv3_none_bilstm_ctc.yml"
-        wget -nc -P ./inference https://paddleocr.bj.bcebos.com/dygraph_v2.0/test/ch_rec_data_200.tar 
-        cd ./inference && tar xf ch_rec_data_200.tar  && cd ../
-        img_dir="./inference/ch_rec_data_200/"
+        wget -nc -P ./inference https://paddleocr.bj.bcebos.com/dygraph_v2.0/test/rec_inference.tar
+        cd ./inference && tar xf rec_inference.tar  && cd ../
+        img_dir="./inference/rec_inference/"
+        data_dir=./inference/rec_inference
+        data_label_file=[./inference/rec_inference/rec_gt_test.txt]
     fi
 
     # eval 

tools/infer/predict_rec.py

@@ -64,6 +64,24 @@ class TextRecognizer(object):
         self.postprocess_op = build_post_process(postprocess_params)
         self.predictor, self.input_tensor, self.output_tensors, self.config = \
             utility.create_predictor(args, 'rec', logger)
+        self.benchmark = args.benchmark
+        if args.benchmark:
+            import auto_log
+            pid = os.getpid()
+            self.autolog = auto_log.AutoLogger(
+                model_name="rec",
+                model_precision=args.precision,
+                batch_size=args.rec_batch_num,
+                data_shape="dynamic",
+                save_path=args.save_log_path,
+                inference_config=self.config,
+                pids=pid,
+                process_name=None,
+                gpu_ids=0 if args.use_gpu else None,
+                time_keys=[
+                    'preprocess_time', 'inference_time', 'postprocess_time'
+                ],
+                warmup=10)
 
     def resize_norm_img(self, img, max_wh_ratio):
         imgC, imgH, imgW = self.rec_image_shape
@@ -168,6 +186,8 @@ class TextRecognizer(object):
         rec_res = [['', 0.0]] * img_num
         batch_num = self.rec_batch_num
         st = time.time()
+        if self.benchmark:
+            self.autolog.times.start()
         for beg_img_no in range(0, img_num, batch_num):
             end_img_no = min(img_num, beg_img_no + batch_num)
             norm_img_batch = []
@@ -196,6 +216,8 @@ class TextRecognizer(object):
                     norm_img_batch.append(norm_img[0])
             norm_img_batch = np.concatenate(norm_img_batch)
             norm_img_batch = norm_img_batch.copy()
+            if self.benchmark:
+                self.autolog.times.stamp()
 
             if self.rec_algorithm == "SRN":
                 encoder_word_pos_list = np.concatenate(encoder_word_pos_list)
@@ -222,6 +244,8 @@ class TextRecognizer(object):
                 for output_tensor in self.output_tensors:
                     output = output_tensor.copy_to_cpu()
                     outputs.append(output)
+                if self.benchmark:
+                    self.autolog.times.stamp()
                 preds = {"predict": outputs[2]}
             else:
                 self.input_tensor.copy_from_cpu(norm_img_batch)
@@ -231,11 +255,14 @@ class TextRecognizer(object):
                 for output_tensor in self.output_tensors:
                     output = output_tensor.copy_to_cpu()
                     outputs.append(output)
+                if self.benchmark:
+                    self.autolog.times.stamp()
                 preds = outputs[0]
             rec_result = self.postprocess_op(preds)
             for rno in range(len(rec_result)):
                 rec_res[indices[beg_img_no + rno]] = rec_result[rno]
-
+            if self.benchmark:
+                self.autolog.times.end(stamp=True)
         return rec_res, time.time() - st
 
 
@@ -251,9 +278,6 @@ def main(args):
         for i in range(10):
             res = text_recognizer([img])
 
-    cpu_mem, gpu_mem, gpu_util = 0, 0, 0
-    count = 0
-
     for image_file in image_file_list:
         img, flag = check_and_read_gif(image_file)
         if not flag:
@@ -273,6 +297,8 @@ def main(args):
     for ino in range(len(img_list)):
         logger.info("Predicts of {}:{}".format(valid_image_file_list[ino],
                                                rec_res[ino]))
+    if args.benchmark:
+        text_recognizer.autolog.report()
 
 
 if __name__ == "__main__":