Merge pull request #6441 from andyjpaddle/add_kl_pact

[TIPC] add KL and PACT

ppstructure/table/predict_table.py

@@ -28,6 +28,7 @@ import numpy as np
 import time
 import tools.infer.predict_rec as predict_rec
 import tools.infer.predict_det as predict_det
+import tools.infer.utility as utility
 from ppocr.utils.utility import get_image_file_list, check_and_read_gif
 from ppocr.utils.logging import get_logger
 from ppstructure.table.matcher import distance, compute_iou
@@ -59,11 +60,37 @@ class TableSystem(object):
         self.text_recognizer = predict_rec.TextRecognizer(
             args) if text_recognizer is None else text_recognizer
         self.table_structurer = predict_strture.TableStructurer(args)
+        self.benchmark = args.benchmark
+        self.predictor, self.input_tensor, self.output_tensors, self.config = utility.create_predictor(
+            args, 'table', logger)
+        if args.benchmark:
+            import auto_log
+            pid = os.getpid()
+            gpu_id = utility.get_infer_gpuid()
+            self.autolog = auto_log.AutoLogger(
+                model_name="table",
+                model_precision=args.precision,
+                batch_size=1,
+                data_shape="dynamic",
+                save_path=None,  #args.save_log_path,
+                inference_config=self.config,
+                pids=pid,
+                process_name=None,
+                gpu_ids=gpu_id if args.use_gpu else None,
+                time_keys=[
+                    'preprocess_time', 'inference_time', 'postprocess_time'
+                ],
+                warmup=0,
+                logger=logger)
 
     def __call__(self, img, return_ocr_result_in_table=False):
         result = dict()
         ori_im = img.copy()
+        if self.benchmark:
+            self.autolog.times.start()
         structure_res, elapse = self.table_structurer(copy.deepcopy(img))
+        if self.benchmark:
+            self.autolog.times.stamp()
         dt_boxes, elapse = self.text_detector(copy.deepcopy(img))
         dt_boxes = sorted_boxes(dt_boxes)
         if return_ocr_result_in_table:
@@ -77,13 +104,11 @@ class TableSystem(object):
             box = [x_min, y_min, x_max, y_max]
             r_boxes.append(box)
         dt_boxes = np.array(r_boxes)
-
         logger.debug("dt_boxes num : {}, elapse : {}".format(
             len(dt_boxes), elapse))
         if dt_boxes is None:
             return None, None
         img_crop_list = []
-
         for i in range(len(dt_boxes)):
             det_box = dt_boxes[i]
             x0, y0, x1, y1 = expand(2, det_box, ori_im.shape)
@@ -92,10 +117,14 @@ class TableSystem(object):
         rec_res, elapse = self.text_recognizer(img_crop_list)
         logger.debug("rec_res num  : {}, elapse : {}".format(
             len(rec_res), elapse))
+        if self.benchmark:
+            self.autolog.times.stamp()
         if return_ocr_result_in_table:
             result['rec_res'] = rec_res
         pred_html, pred = self.rebuild_table(structure_res, dt_boxes, rec_res)
         result['html'] = pred_html
+        if self.benchmark:
+            self.autolog.times.end(stamp=True)
         return result
 
     def rebuild_table(self, structure_res, dt_boxes, rec_res):
@@ -213,6 +242,8 @@ def main(args):
         logger.info('excel saved to {}'.format(excel_path))
         elapse = time.time() - starttime
         logger.info("Predict time : {:.3f}s".format(elapse))
+    if args.benchmark:
+        text_sys.autolog.report()
 
 
 if __name__ == "__main__":

test_tipc/common_func.sh

@@ -57,10 +57,11 @@ function status_check(){
     last_status=$1   # the exit code
     run_command=$2
     run_log=$3
+    model_name=$4
     if [ $last_status -eq 0 ]; then
-        echo -e "\033[33m Run successfully with command - ${run_command}!  \033[0m" | tee -a ${run_log}
+        echo -e "\033[33m Run successfully with command - ${model_name} - ${run_command}!  \033[0m" | tee -a ${run_log}
     else
-        echo -e "\033[33m Run failed with command - ${run_command}!  \033[0m" | tee -a ${run_log}
+        echo -e "\033[33m Run failed with command - ${model_name} - ${run_command}!  \033[0m" | tee -a ${run_log}
     fi
 }
 

test_tipc/configs/ch_PP-OCRv2_det_KL/model_linux_gpu_normal_normal_infer_python_linux_gpu_cpu.txt

 ===========================kl_quant_params===========================
-model_name:PPOCRv2_ocr_det_kl
+model_name:ch_PP-OCRv2_det_KL
 python:python3.7
 Global.pretrained_model:null
 Global.save_inference_dir:null
@@ -8,10 +8,10 @@ infer_export:deploy/slim/quantization/quant_kl.py -c configs/det/ch_PP-OCRv2/ch_
 infer_quant:True
 inference:tools/infer/predict_det.py
 --use_gpu:False|True
---enable_mkldnn:True
---cpu_threads:1|6
+--enable_mkldnn:False
+--cpu_threads:6
 --rec_batch_num:1
---use_tensorrt:False|True
+--use_tensorrt:False
 --precision:int8
 --det_model_dir:
 --image_dir:./inference/ch_det_data_50/all-sum-510/

test_tipc/configs/ch_PP-OCRv2_rec_KL/model_linux_gpu_normal_normal_infer_python_linux_gpu_cpu.txt

 ===========================kl_quant_params===========================
-model_name:PPOCRv2_ocr_rec_kl
+model_name:ch_PP-OCRv2_rec_KL
 python:python3.7
 Global.pretrained_model:null
 Global.save_inference_dir:null
 infer_model:./inference/ch_PP-OCRv2_rec_infer/
 infer_export:deploy/slim/quantization/quant_kl.py -c test_tipc/configs/ch_PP-OCRv2_rec/ch_PP-OCRv2_rec_distillation.yml -o
 infer_quant:True
-inference:tools/infer/predict_rec.py
+inference:tools/infer/predict_rec.py --rec_image_shape="3,32,320"
 --use_gpu:False|True
---enable_mkldnn:False|True
---cpu_threads:1|6
+--enable_mkldnn:False
+--cpu_threads:6
 --rec_batch_num:1|6
---use_tensorrt:True
+--use_tensorrt:False
 --precision:int8
 --rec_model_dir:
 --image_dir:./inference/rec_inference

test_tipc/configs/ch_PP-OCRv2_rec_PACT/train_infer_python.txt

@@ -4,7 +4,7 @@ python:python3.7
 gpu_list:0|0,1
 Global.use_gpu:True|True
 Global.auto_cast:fp32
-Global.epoch_num:lite_train_lite_infer=6|whole_train_whole_infer=50
+Global.epoch_num:lite_train_lite_infer=1|whole_train_whole_infer=50
 Global.save_model_dir:./output/
 Train.loader.batch_size_per_card:lite_train_lite_infer=16|whole_train_whole_infer=128
 Global.pretrained_model:pretrain_models/ch_PP-OCRv2_rec_train/best_accuracy

test_tipc/configs/ch_PP-OCRv3_det_KL/model_linux_gpu_normal_normal_infer_python_linux_gpu_cpu.txt

 ===========================kl_quant_params===========================
-model_name:PPOCRv3_ocr_det_kl
+model_name:ch_PP-OCRv3_det_KL
 python:python3.7
 Global.pretrained_model:null
 Global.save_inference_dir:null
@@ -8,10 +8,10 @@ infer_export:deploy/slim/quantization/quant_kl.py -c configs/det/ch_PP-OCRv3/ch_
 infer_quant:True
 inference:tools/infer/predict_det.py
 --use_gpu:False|True
---enable_mkldnn:True
---cpu_threads:1|6
+--enable_mkldnn:False
+--cpu_threads:6
 --rec_batch_num:1
---use_tensorrt:False|True
+--use_tensorrt:False
 --precision:int8
 --det_model_dir:
 --image_dir:./inference/ch_det_data_50/all-sum-510/

test_tipc/configs/ch_PP-OCRv3_rec_KL/model_linux_gpu_normal_normal_infer_python_linux_gpu_cpu.txt

 ===========================kl_quant_params===========================
-model_name:PPOCRv3_ocr_rec_kl
+model_name:ch_PP-OCRv3_rec_KL
 python:python3.7
-Global.pretrained_model:null
+Global.pretrained_model:
 Global.save_inference_dir:null
 infer_model:./inference/ch_PP-OCRv3_rec_infer/
 infer_export:deploy/slim/quantization/quant_kl.py -c test_tipc/configs/ch_PP-OCRv3_rec/ch_PP-OCRv3_rec_distillation.yml -o
 infer_quant:True
 inference:tools/infer/predict_rec.py --rec_image_shape="3,48,320"
 --use_gpu:False|True
---enable_mkldnn:False|True
---cpu_threads:1|6
+--enable_mkldnn:False
+--cpu_threads:6
 --rec_batch_num:1|6
---use_tensorrt:True
+--use_tensorrt:False
 --precision:int8
 --rec_model_dir:
 --image_dir:./inference/rec_inference

test_tipc/configs/ch_PP-OCRv3_rec_PACT/train_infer_python.txt

@@ -4,7 +4,7 @@ python:python3.7
 gpu_list:0|0,1
 Global.use_gpu:True|True
 Global.auto_cast:fp32
-Global.epoch_num:lite_train_lite_infer=6|whole_train_whole_infer=50
+Global.epoch_num:lite_train_lite_infer=1|whole_train_whole_infer=50
 Global.save_model_dir:./output/
 Train.loader.batch_size_per_card:lite_train_lite_infer=16|whole_train_whole_infer=128
 Global.pretrained_model:pretrain_models/ch_PP-OCRv3_rec_train/best_accuracy

test_tipc/configs/ch_ppocr_mobile_v2.0_det_KL/model_linux_gpu_normal_normal_infer_python_linux_gpu_cpu.txt

@@ -8,10 +8,10 @@ infer_export:deploy/slim/quantization/quant_kl.py -c configs/det/ch_ppocr_v2.0/c
 infer_quant:True
 inference:tools/infer/predict_det.py
 --use_gpu:False|True
---enable_mkldnn:True
---cpu_threads:1|6
+--enable_mkldnn:False
+--cpu_threads:6
 --rec_batch_num:1
---use_tensorrt:False|True
+--use_tensorrt:False
 --precision:int8
 --det_model_dir:
 --image_dir:./inference/ch_det_data_50/all-sum-510/

test_tipc/configs/ch_ppocr_mobile_v2.0_det_PACT/train_infer_python.txt

@@ -4,7 +4,7 @@ python:python3.7
 gpu_list:0|0,1
 Global.use_gpu:True|True
 Global.auto_cast:null
-Global.epoch_num:lite_train_lite_infer=20|whole_train_whole_infer=50
+Global.epoch_num:lite_train_lite_infer=2|whole_train_whole_infer=50
 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

test_tipc/configs/ch_ppocr_mobile_v2.0_rec_KL/model_linux_gpu_normal_normal_infer_python_linux_gpu_cpu.txt

@@ -6,12 +6,12 @@ Global.save_inference_dir:null
 infer_model:./inference/ch_ppocr_mobile_v2.0_rec_infer/
 infer_export:deploy/slim/quantization/quant_kl.py -c test_tipc/configs/ch_ppocr_mobile_v2.0_rec_KL/rec_chinese_lite_train_v2.0.yml -o
 infer_quant:True
-inference:tools/infer/predict_rec.py
+inference:tools/infer/predict_rec.py --rec_image_shape="3,32,320"
 --use_gpu:False|True
---enable_mkldnn:True
---cpu_threads:1|6
+--enable_mkldnn:False
+--cpu_threads:6
 --rec_batch_num:1
---use_tensorrt:False|True
+--use_tensorrt:False
 --precision:int8
 --rec_model_dir:
 --image_dir:./inference/rec_inference