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

ppstructure/table/predict_table.py

@@ -54,16 +54,20 @@ def expand(pix, det_box, shape):
 
 class TableSystem(object):
     def __init__(self, args, text_detector=None, text_recognizer=None):
-        self.text_detector = predict_det.TextDetector(args) if text_detector is None else text_detector
-        self.text_recognizer = predict_rec.TextRecognizer(args) if text_recognizer is None else text_recognizer
+        self.text_detector = predict_det.TextDetector(
+            args) if text_detector is None else text_detector
+        self.text_recognizer = predict_rec.TextRecognizer(
+            args) if text_recognizer is None else text_recognizer
         self.table_structurer = predict_strture.TableStructurer(args)
 
-    def __call__(self, img):
+    def __call__(self, img, return_ocr_result_in_table=False):
+        result = dict()
         ori_im = img.copy()
         structure_res, elapse = self.table_structurer(copy.deepcopy(img))
         dt_boxes, elapse = self.text_detector(copy.deepcopy(img))
         dt_boxes = sorted_boxes(dt_boxes)
-
+        if return_ocr_result_in_table:
+            result['boxes'] = [x.tolist() for x in dt_boxes]
         r_boxes = []
         for box in dt_boxes:
             x_min = box[:, 0].min() - 1
@@ -88,14 +92,17 @@ class TableSystem(object):
         rec_res, elapse = self.text_recognizer(img_crop_list)
         logger.debug("rec_res num  : {}, elapse : {}".format(
             len(rec_res), elapse))
-
+        if return_ocr_result_in_table:
+            result['rec_res'] = rec_res
         pred_html, pred = self.rebuild_table(structure_res, dt_boxes, rec_res)
-        return pred_html
+        result['html'] = pred_html
+        return result
 
     def rebuild_table(self, structure_res, dt_boxes, rec_res):
         pred_structures, pred_bboxes = structure_res
         matched_index = self.match_result(dt_boxes, pred_bboxes)
-        pred_html, pred = self.get_pred_html(pred_structures, matched_index, rec_res)
+        pred_html, pred = self.get_pred_html(pred_structures, matched_index,
+                                             rec_res)
         return pred_html, pred
 
     def match_result(self, dt_boxes, pred_bboxes):
@@ -104,11 +111,13 @@ class TableSystem(object):
             # gt_box = [np.min(gt_box[:, 0]), np.min(gt_box[:, 1]), np.max(gt_box[:, 0]), np.max(gt_box[:, 1])]
             distances = []
             for j, pred_box in enumerate(pred_bboxes):
-                distances.append(
-                    (distance(gt_box, pred_box), 1. - compute_iou(gt_box, pred_box)))  # 获取两两cell之间的L1距离和 1- IOU
+                distances.append((distance(gt_box, pred_box),
+                                  1. - compute_iou(gt_box, pred_box)
+                                  ))  # 获取两两cell之间的L1距离和 1- IOU
             sorted_distances = distances.copy()
             # 根据距离和IOU挑选最"近"的cell
-            sorted_distances = sorted(sorted_distances, key=lambda item: (item[1], item[0]))
+            sorted_distances = sorted(
+                sorted_distances, key=lambda item: (item[1], item[0]))
             if distances.index(sorted_distances[0]) not in matched.keys():
                 matched[distances.index(sorted_distances[0])] = [i]
             else:
@@ -122,7 +131,8 @@ class TableSystem(object):
             if '</td>' in tag:
                 if td_index in matched_index.keys():
                     b_with = False
-                    if '<b>' in ocr_contents[matched_index[td_index][0]] and len(matched_index[td_index]) > 1:
+                    if '<b>' in ocr_contents[matched_index[td_index][
+                            0]] and len(matched_index[td_index]) > 1:
                         b_with = True
                         end_html.extend('<b>')
                     for i, td_index_index in enumerate(matched_index[td_index]):
@@ -138,7 +148,8 @@ class TableSystem(object):
                                 content = content[:-4]
                             if len(content) == 0:
                                 continue
-                            if i != len(matched_index[td_index]) - 1 and ' ' != content[-1]:
+                            if i != len(matched_index[
+                                    td_index]) - 1 and ' ' != content[-1]:
                                 content += ' '
                         end_html.extend(content)
                     if b_with:
@@ -187,18 +198,19 @@ def main(args):
     for i, image_file in enumerate(image_file_list):
         logger.info("[{}/{}] {}".format(i, img_num, image_file))
         img, flag = check_and_read_gif(image_file)
-        excel_path = os.path.join(args.output, os.path.basename(image_file).split('.')[0] + '.xlsx')
+        excel_path = os.path.join(
+            args.output, os.path.basename(image_file).split('.')[0] + '.xlsx')
         if not flag:
             img = cv2.imread(image_file)
         if img is None:
             logger.error("error in loading image:{}".format(image_file))
             continue
         starttime = time.time()
-        pred_html = text_sys(img)
-
+        pred_res = text_sys(img)
+        pred_html = pred_res['html']
+        logger.info(pred_html)
         to_excel(pred_html, excel_path)
         logger.info('excel saved to {}'.format(excel_path))
-        logger.info(pred_html)
         elapse = time.time() - starttime
         logger.info("Predict time : {:.3f}s".format(elapse))
 

ppstructure/utility.py

@@ -15,7 +15,7 @@
 import ast
 from PIL import Image
 import numpy as np
-from tools.infer.utility import draw_ocr_box_txt, init_args as infer_args
+from tools.infer.utility import draw_ocr_box_txt, str2bool, init_args as infer_args
 
 
 def init_args():
@@ -30,6 +30,7 @@ def init_args():
         "--table_char_dict_path",
         type=str,
         default="../ppocr/utils/dict/table_structure_dict.txt")
+    # params for layout
     parser.add_argument(
         "--layout_path_model",
         type=str,
@@ -39,11 +40,27 @@ def init_args():
         type=ast.literal_eval,
         default=None,
         help='label map according to ppstructure/layout/README_ch.md')
+    # params for inference
     parser.add_argument(
         "--mode",
         type=str,
         default='structure',
         help='structure and vqa is supported')
+    parser.add_argument(
+        "--layout",
+        type=str2bool,
+        default=True,
+        help='Whether to enable layout analysis')
+    parser.add_argument(
+        "--table",
+        type=str2bool,
+        default=True,
+        help='In the forward, whether the table area uses table recognition')
+    parser.add_argument(
+        "--ocr",
+        type=str2bool,
+        default=True,
+        help='In the forward, whether the non-table area is recognition by ocr')
     return parser
 
 

ppstructure/vqa/README.md

@@ -51,9 +51,10 @@ We evaluate the algorithm on the Chinese dataset of [XFUND](https://github.com/d
 
 **Note:** The test images are from the XFUND dataset.
 
+<a name="31"></a>
 ### 3.1 SER
 
-![](../../doc/vqa/result_ser/zh_val_0_ser.jpg) | ![](../../doc/vqa/result_ser/zh_val_42_ser.jpg)
+![](../docs/vqa/result_ser/zh_val_0_ser.jpg) | ![](../docs/vqa/result_ser/zh_val_42_ser.jpg)
 ---|---
 
 Boxes with different colors in the figure represent different categories. For the XFUND dataset, there are 3 categories: `QUESTION`, `ANSWER`, `HEADER`
@@ -64,9 +65,10 @@ Boxes with different colors in the figure represent different categories. For th
 
 The corresponding categories and OCR recognition results are also marked on the upper left of the OCR detection frame.
 
+<a name="32"></a>
 ### 3.2 RE
 
-![](../../doc/vqa/result_re/zh_val_21_re.jpg) | ![](../../doc/vqa/result_re/zh_val_40_re.jpg)
+![](../docs/vqa/result_re/zh_val_21_re.jpg) | ![](../docs/vqa/result_re/zh_val_40_re.jpg)
 ---|---
 
 
@@ -150,6 +152,7 @@ wget https://paddleocr.bj.bcebos.com/pplayout/re_LayoutXLM_xfun_zh.tar && tar -x
 cd ../
 ````
 
+<a name="52"></a>
 ### 5.2 SER
 
 Before starting training, you need to modify the following four fields
@@ -203,6 +206,7 @@ export CUDA_VISIBLE_DEVICES=0
 python3 tools/eval_with_label_end2end.py --gt_json_path XFUND/zh_val/xfun_normalize_val.json --pred_json_path output_res/infer_results.txt
 ````
 
+<a name="53"></a>
 ### 5.3 RE
 
 * start training

requirements.txt

@@ -12,3 +12,4 @@ cython
 lxml
 premailer
 openpyxl
+attrdict

test_tipc/configs/ch_PP-OCRv2_det/train_linux_gpu_normal_amp_infer_python_linux_gpu_cpu.txt

+===========================train_params===========================
+model_name:ch_PPOCRv2_det
+python:python3.7
+gpu_list:0|0,1
+Global.use_gpu:True|True
+Global.auto_cast:amp
+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-OCRv2/ch_PP-OCRv2_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-OCRv2/ch_PP-OCRv2_det_cml.yml -o 
+quant_export:null
+fpgm_export: 
+distill_export:null
+export1:null
+export2:null
+inference_dir:Student
+infer_model:./inference/ch_PP-OCRv2_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]}]

test_tipc/configs/ch_PP-OCRv2_det_PACT/train_infer_python.txt

@@ -6,7 +6,7 @@ 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
+Train.loader.batch_size_per_card:lite_train_lite_infer=1|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/

test_tipc/configs/ch_PP-OCRv2_det_PACT/train_linux_gpu_normal_amp_infer_python_linux_gpu_cpu.txt

+===========================train_params===========================
+model_name:ch_PPOCRv2_det_PACT
+python:python3.7
+gpu_list:0|0,1
+Global.use_gpu:True|True
+Global.auto_cast:amp
+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:pact_train
+norm_train:null
+pact_train:deploy/slim/quantization/quant.py -c configs/det/ch_PP-OCRv2/ch_PP-OCRv2_det_cml.yml -o
+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:null
+quant_export:deploy/slim/quantization/export_model.py -c configs/det/ch_PP-OCRv2/ch_PP-OCRv2_det_cml.yml -o 
+fpgm_export: 
+distill_export:null
+export1:null
+export2:null
+inference_dir:Student
+infer_model:./inference/ch_PP-OCRv2_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]}]

test_tipc/configs/ch_PP-OCRv2_rec/train_linux_gpu_normal_amp_infer_python_linux_gpu_cpu.txt

+===========================train_params===========================
+model_name:PPOCRv2_ocr_rec
+python:python3.7
+gpu_list:0|0,1
+Global.use_gpu:True|True
+Global.auto_cast:amp
+Global.epoch_num:lite_train_lite_infer=3|whole_train_whole_infer=300
+Global.save_model_dir:./output/
+Train.loader.batch_size_per_card:lite_train_lite_infer=16|whole_train_whole_infer=128
+Global.pretrained_model:null
+train_model_name:latest
+train_infer_img_dir:./inference/rec_inference
+null:null
+##
+trainer:norm_train
+norm_train:tools/train.py -c test_tipc/configs/ch_PP-OCRv2_rec/ch_PP-OCRv2_rec_distillation.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 test_tipc/configs/ch_PP-OCRv2_rec/ch_PP-OCRv2_rec_distillation.yml -o 
+quant_export:
+fpgm_export: 
+distill_export:null
+export1:null
+export2:null
+inference_dir:Student
+infer_model:./inference/ch_PP-OCRv2_rec_infer
+infer_export:null
+infer_quant:False
+inference:tools/infer/predict_rec.py
+--use_gpu:True|False
+--enable_mkldnn:True|False
+--cpu_threads:1|6
+--rec_batch_num:1|6
+--use_tensorrt:False|True
+--precision:fp32|int8
+--rec_model_dir:
+--image_dir:./inference/rec_inference
+null:null
+--benchmark:True
+null:null
+===========================infer_benchmark_params==========================
+random_infer_input:[{float32,[3,32,320]}]

test_tipc/configs/ch_PP-OCRv2_rec_PACT/train_linux_gpu_normal_amp_infer_python_linux_gpu_cpu.txt

+===========================train_params===========================
+model_name:ch_PPOCRv2_rec_PACT
+python:python3.7
+gpu_list:0|0,1
+Global.use_gpu:True|True
+Global.auto_cast:amp
+Global.epoch_num:lite_train_lite_infer=3|whole_train_whole_infer=300
+Global.save_model_dir:./output/
+Train.loader.batch_size_per_card:lite_train_lite_infer=16|whole_train_whole_infer=128
+Global.pretrained_model:null
+train_model_name:latest
+train_infer_img_dir:./inference/rec_inference
+null:null
+##
+trainer:pact_train
+norm_train:null
+pact_train:deploy/slim/quantization/quant.py -c test_tipc/configs/ch_PP-OCRv2_rec/ch_PP-OCRv2_rec_distillation.yml -o 
+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:null
+quant_export:deploy/slim/quantization/export_model.py -c test_tipc/configs/ch_PP-OCRv2_rec/ch_PP-OCRv2_rec_distillation.yml -o 
+fpgm_export: null
+distill_export:null
+export1:null
+export2:null
+inference_dir:Student
+infer_model:./inference/ch_PP-OCRv2_rec_slim_quant_infer
+infer_export:null
+infer_quant:True
+inference:tools/infer/predict_rec.py
+--use_gpu:True|False
+--enable_mkldnn:True|False
+--cpu_threads:1|6
+--rec_batch_num:1|6
+--use_tensorrt:False|True
+--precision:fp32|int8
+--rec_model_dir:
+--image_dir:./inference/rec_inference
+null:null
+--benchmark:True
+null:null
+===========================infer_benchmark_params==========================
+random_infer_input:[{float32,[3,32,320]}]

test_tipc/configs/ch_ppocr_mobile_v2.0_det/train_linux_gpu_normal_amp_infer_python_linux_gpu_cpu.txt

 ===========================train_params===========================
-model_name:ocr_det
+model_name:ch_ppocr_mobile_v2.0_det
 python:python3.7
 gpu_list:0|0,1
 Global.use_gpu:True|True
 Global.auto_cast:amp
-Global.epoch_num:lite_train_lite_infer=1|whole_train_whole_infer=300
+Global.epoch_num:lite_train_lite_infer=100|whole_train_whole_infer=300
 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
@@ -12,10 +12,10 @@ train_model_name:latest
 train_infer_img_dir:./train_data/icdar2015/text_localization/ch4_test_images/
 null:null
 ##
-trainer:norm_train|pact_train|fpgm_train
-norm_train:tools/train.py -c test_tipc/configs/ppocr_det_mobile/det_mv3_db.yml -o Global.pretrained_model=./pretrain_models/MobileNetV3_large_x0_5_pretrained
-pact_train:deploy/slim/quantization/quant.py -c test_tipc/configs/ppocr_det_mobile/det_mv3_db.yml -o
-fpgm_train:deploy/slim/prune/sensitivity_anal.py -c test_tipc/configs/ppocr_det_mobile/det_mv3_db.yml -o Global.pretrained_model=./pretrain_models/det_mv3_db_v2.0_train/best_accuracy
+trainer:norm_train
+norm_train:tools/train.py -c configs/det/ch_ppocr_v2.0/ch_det_mv3_db_v2.0.yml -o Global.pretrained_model=./pretrain_models/MobileNetV3_large_x0_5_pretrained
+pact_train:null
+fpgm_train:null
 distill_train:null
 null:null
 null:null
@@ -26,10 +26,10 @@ null:null
 ##
 ===========================infer_params===========================
 Global.save_inference_dir:./output/
-Global.pretrained_model:
-norm_export:tools/export_model.py -c test_tipc/configs/ppocr_det_mobile/det_mv3_db.yml -o 
-quant_export:deploy/slim/quantization/export_model.py -c test_tipc/configs/ppocr_det_mobile/det_mv3_db.yml -o 
-fpgm_export:deploy/slim/prune/export_prune_model.py -c test_tipc/configs/ppocr_det_mobile/det_mv3_db.yml -o 
+Global.checkpoints:
+norm_export:tools/export_model.py -c configs/det/ch_ppocr_v2.0/ch_det_mv3_db_v2.0.yml -o 
+quant_export:null
+fpgm_export:null
 distill_export:null
 export1:null
 export2:null
@@ -49,3 +49,5 @@ inference:tools/infer/predict_det.py
 null:null
 --benchmark:True
 null:null
+===========================infer_benchmark_params==========================
+random_infer_input:[{float32,[3,640,640]}];[{float32,[3,960,960]}]
\ No newline at end of file

test_tipc/configs/ch_ppocr_mobile_V2.0_det_FPGM/train_infer_python.txt → test_tipc/configs/ch_ppocr_mobile_v2.0_det_FPGM/train_infer_python.txt

 ===========================train_params===========================
-model_name:ocr_det
+model_name:ch_ppocr_mobile_v2.0_det_FPGM
 python:python3.7
 gpu_list:0|0,1
 Global.use_gpu:True|True

test_tipc/configs/ch_ppocr_mobile_v2.0_det_FPGM/train_linux_gpu_normal_amp_infer_python_linux_gpu_cpu.txt

+===========================train_params===========================
+model_name:ch_ppocr_mobile_v2.0_det_FPGM
+python:python3.7
+gpu_list:0|0,1
+Global.use_gpu:True|True
+Global.auto_cast:amp
+Global.epoch_num:lite_train_lite_infer=5|whole_train_whole_infer=300
+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:fpgm_train
+norm_train:null
+pact_train:null
+fpgm_train:deploy/slim/prune/sensitivity_anal.py -c configs/det/ch_ppocr_v2.0/ch_det_mv3_db_v2.0.yml -o Global.pretrained_model=./pretrain_models/det_mv3_db_v2.0_train/best_accuracy
+distill_train:null
+null:null
+null:null
+##
+===========================eval_params=========================== 
+eval:null
+null:null
+##
+===========================infer_params===========================
+Global.save_inference_dir:./output/
+Global.checkpoints:
+norm_export:null
+quant_export:null
+fpgm_export:deploy/slim/prune/export_prune_model.py -c configs/det/ch_ppocr_v2.0/ch_det_mv3_db_v2.0.yml -o 
+distill_export:null
+export1:null
+export2:null
+inference_dir:null
+train_model:null
+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]}]
\ No newline at end of file

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

+===========================train_params===========================
+model_name:ch_ppocr_mobile_v2.0_det_PACT
+python:python3.7
+gpu_list:0|0,1
+Global.use_gpu:True|True
+Global.auto_cast:amp
+Global.epoch_num:lite_train_lite_infer=20|whole_train_whole_infer=300
+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:pact_train
+norm_train:null
+pact_train:deploy/slim/quantization/quant.py -c configs/det/ch_ppocr_v2.0/ch_det_mv3_db_v2.0.yml -o
+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:null
+quant_export:deploy/slim/quantization/export_model.py -c configs/det/ch_ppocr_v2.0/ch_det_mv3_db_v2.0.yml -o 
+fpgm_export:null
+distill_export:null
+export1:null
+export2:null
+inference_dir:null
+train_model:./inference/ch_ppocr_mobile_v2.0_det_prune_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]}]

test_tipc/configs/ch_ppocr_mobile_v2.0_rec/train_linux_gpu_normal_amp_infer_python_linux_gpu_cpu.txt

+===========================train_params===========================
+model_name:ch_ppocr_mobile_v2.0_rec
+python:python3.7
+gpu_list:0|0,1
+Global.use_gpu:True|True
+Global.auto_cast:amp
+Global.epoch_num:lite_train_lite_infer=2|whole_train_whole_infer=300
+Global.save_model_dir:./output/
+Train.loader.batch_size_per_card:lite_train_lite_infer=128|whole_train_whole_infer=128
+Global.pretrained_model:null
+train_model_name:latest
+train_infer_img_dir:./inference/rec_inference
+null:null
+##
+trainer:norm_train
+norm_train:tools/train.py -c configs/rec/rec_icdar15_train.yml -o
+pact_train:null
+fpgm_train:null
+distill_train:null
+null:null
+null:null
+##
+===========================eval_params===========================
+eval:tools/eval.py -c configs/rec/rec_icdar15_train.yml -o
+null:null
+##
+===========================infer_params===========================
+Global.save_inference_dir:./output/
+Global.checkpoints:
+norm_export:tools/export_model.py -c configs/rec/rec_icdar15_train.yml -o
+quant_export:null
+fpgm_export:null
+distill_export:null
+export1:null
+export2:null
+##
+train_model:./inference/ch_ppocr_mobile_v2.0_rec_train/best_accuracy
+infer_export:tools/export_model.py -c configs/rec/rec_icdar15_train.yml -o
+infer_quant:False
+inference:tools/infer/predict_rec.py
+--use_gpu:True|False
+--enable_mkldnn:True|False
+--cpu_threads:1|6
+--rec_batch_num:1|6
+--use_tensorrt:True|False
+--precision:fp32|int8
+--rec_model_dir:
+--image_dir:./inference/rec_inference
+--save_log_path:./test/output/
+--benchmark:True
+null:null
+===========================infer_benchmark_params==========================
+random_infer_input:[{float32,[3,32,100]}]

test_tipc/configs/ch_ppocr_mobile_v2.0_rec_FPGM/train_linux_gpu_normal_amp_infer_python_linux_gpu_cpu.txt

+===========================train_params===========================
+model_name:ch_ppocr_mobile_v2.0_rec_FPGM
+python:python3.7
+gpu_list:0
+Global.use_gpu:True|True
+Global.auto_cast:amp
+Global.epoch_num:lite_train_lite_infer=1|whole_train_whole_infer=300
+Global.save_model_dir:./output/
+Train.loader.batch_size_per_card:lite_train_lite_infer=128|whole_train_whole_infer=128
+Global.pretrained_model:null
+train_model_name:latest
+train_infer_img_dir:./train_data/ic15_data/test/word_1.png
+null:null
+##
+trainer:fpgm_train
+norm_train:null
+pact_train:null
+fpgm_train:deploy/slim/prune/sensitivity_anal.py -c test_tipc/configs/ch_ppocr_mobile_v2.0_rec_FPGM/rec_chinese_lite_train_v2.0.yml -o Global.pretrained_model=./pretrain_models/ch_ppocr_mobile_v2.0_rec_train/best_accuracy
+distill_train:null
+null:null
+null:null
+##
+===========================eval_params=========================== 
+eval:null
+null:null
+##
+===========================infer_params===========================
+Global.save_inference_dir:./output/
+Global.checkpoints:
+norm_export:null
+quant_export:null
+fpgm_export:deploy/slim/prune/export_prune_model.py -c test_tipc/configs/ch_ppocr_mobile_v2.0_rec_FPGM/rec_chinese_lite_train_v2.0.yml -o 
+distill_export:null
+export1:null
+export2:null
+inference_dir:null
+train_model:null
+infer_export:null
+infer_quant:False
+inference:tools/infer/predict_rec.py
+--use_gpu:True|False
+--enable_mkldnn:True|False
+--cpu_threads:1|6
+--rec_batch_num:1
+--use_tensorrt:False|True
+--precision:fp32|int8
+--rec_model_dir:
+--image_dir:./inference/rec_inference
+null:null
+--benchmark:True
+null:null
+===========================infer_benchmark_params==========================
+random_infer_input:[{float32,[3,32,320]}]
\ No newline at end of file

test_tipc/configs/ch_ppocr_mobile_v2.0_rec_PACT/train_linux_gpu_normal_amp_infer_python_linux_gpu_cpu.txt

+===========================train_params===========================
+model_name:ch_ppocr_mobile_v2.0_rec_PACT
+python:python3.7
+gpu_list:0
+Global.use_gpu:True|True
+Global.auto_cast:amp
+Global.epoch_num:lite_train_lite_infer=1|whole_train_whole_infer=300
+Global.save_model_dir:./output/
+Train.loader.batch_size_per_card:lite_train_lite_infer=128|whole_train_whole_infer=128
+Global.checkpoints:null
+train_model_name:latest
+train_infer_img_dir:./train_data/ic15_data/test/word_1.png
+null:null
+##
+trainer:pact_train
+norm_train:null
+pact_train:deploy/slim/quantization/quant.py -c test_tipc/configs/ch_ppocr_mobile_v2.0_rec_PACT/rec_chinese_lite_train_v2.0.yml -o
+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:null
+quant_export:deploy/slim/quantization/export_model.py -c test_tipc/configs/ch_ppocr_mobile_v2.0_rec_PACT/rec_chinese_lite_train_v2.0.yml -o 
+fpgm_export:null
+distill_export:null
+export1:null
+export2:null
+inference_dir:null
+infer_model:./inference/ch_ppocr_mobile_v2.0_rec_slim_infer/
+infer_export:null
+infer_quant:False
+inference:tools/infer/predict_rec.py --rec_char_dict_path=./ppocr/utils/ppocr_keys_v1.txt --rec_image_shape="3,32,100"
+--use_gpu:True|False
+--enable_mkldnn:True|False
+--cpu_threads:1|6
+--rec_batch_num:1|6
+--use_tensorrt:False|True
+--precision:fp32|int8
+--rec_model_dir:
+--image_dir:./inference/rec_inference
+--save_log_path:./test/output/
+--benchmark:True
+null:null
+===========================infer_benchmark_params==========================
+random_infer_input:[{float32,[3,32,320]}]

test_tipc/configs/ch_ppocr_server_v2.0_det/train_linux_gpu_normal_amp_infer_python_linux_gpu_cpu.txt

+===========================train_params===========================
+model_name:ch_ppocr_server_v2.0_det
+python:python3.7
+gpu_list:0|0,1
+Global.use_gpu:True|True
+Global.auto_cast:amp
+Global.epoch_num:lite_train_lite_infer=2|whole_train_whole_infer=300
+Global.save_model_dir:./output/
+Train.loader.batch_size_per_card:lite_train_lite_infer=2|whole_train_lite_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 test_tipc/configs/ch_ppocr_server_v2.0_det/det_r50_vd_db.yml -o 
+quant_train:null
+fpgm_train:null
+distill_train:null
+null:null
+null:null
+##
+===========================eval_params=========================== 
+eval:tools/eval.py -c test_tipc/configs/ch_ppocr_server_v2.0_det/det_r50_vd_db.yml -o
+null:null
+##
+===========================infer_params===========================
+Global.save_inference_dir:./output/
+Global.checkpoints:
+norm_export:tools/export_model.py -c test_tipc/configs/ch_ppocr_server_v2.0_det/det_r50_vd_db.yml -o 
+quant_export:null 
+fpgm_export:null
+distill_export:null
+export1:null
+export2:null
+##
+train_model:./inference/ch_ppocr_server_v2.0_det_train/best_accuracy
+infer_export:tools/export_model.py -c configs/det/ch_ppocr_v2.0/ch_det_res18_db_v2.0.yml -o
+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/
+--save_log_path:null
+--benchmark:True
+null:null
+===========================infer_benchmark_params==========================
+random_infer_input:[{float32,[3,640,640]}];[{float32,[3,960,960]}]
\ No newline at end of file

test_tipc/configs/ch_ppocr_server_v2.0_rec/train_linux_gpu_normal_amp_infer_python_linux_gpu_cpu.txt

+===========================train_params===========================
+model_name:ch_ppocr_server_v2.0_rec
+python:python3.7
+gpu_list:0|0,1
+Global.use_gpu:True|True
+Global.auto_cast:amp
+Global.epoch_num:lite_train_lite_infer=5|whole_train_whole_infer=100
+Global.save_model_dir:./output/
+Train.loader.batch_size_per_card:lite_train_lite_infer=128|whole_train_whole_infer=128
+Global.pretrained_model:null
+train_model_name:latest
+train_infer_img_dir:./inference/rec_inference
+null:null
+##
+trainer:norm_train
+norm_train:tools/train.py -c test_tipc/configs/ch_ppocr_server_v2.0_rec/rec_icdar15_train.yml -o
+pact_train:null
+fpgm_train:null
+distill_train:null
+null:null
+null:null
+##
+===========================eval_params===========================
+eval:tools/eval.py -c test_tipc/configs/ch_ppocr_server_v2.0_rec/rec_icdar15_train.yml -o
+null:null
+##
+===========================infer_params===========================
+Global.save_inference_dir:./output/
+Global.checkpoints:
+norm_export:tools/export_model.py -c test_tipc/configs/ch_ppocr_server_v2.0_rec/rec_icdar15_train.yml -o
+quant_export:null
+fpgm_export:null
+distill_export:null
+export1:null
+export2:null
+##
+train_model:./inference/ch_ppocr_server_v2.0_rec_train/best_accuracy
+infer_export:tools/export_model.py -c test_tipc/configs/ch_ppocr_server_v2.0_rec/rec_icdar15_train.yml -o
+infer_quant:False
+inference:tools/infer/predict_rec.py
+--use_gpu:True|False
+--enable_mkldnn:True|False
+--cpu_threads:1|6
+--rec_batch_num:1|6
+--use_tensorrt:True|False
+--precision:fp32|int8
+--rec_model_dir:
+--image_dir:./inference/rec_inference
+--save_log_path:./test/output/
+--benchmark:True
+null:null
+===========================infer_benchmark_params==========================
+random_infer_input:[{float32,[3,32,100]}]

test_tipc/configs/rec_mv3_tps_bilstm_att_v2.0/train_infer_python.txt

@@ -37,7 +37,7 @@ export2:null
 train_model:./inference/rec_mv3_tps_bilstm_att_v2.0_train/best_accuracy
 infer_export:tools/export_model.py -c test_tipc/configs/rec_mv3_tps_bilstm_att_v2.0/rec_mv3_tps_bilstm_att.yml -o
 infer_quant:False
-inference:tools/infer/predict_rec.py --rec_char_dict_path=./ppocr/utils/ic15_dict.txt --rec_image_shape="3,32,100" --rec_algorithm="RARE"
+inference:tools/infer/predict_rec.py --rec_char_dict_path=./ppocr/utils/ic15_dict.txt --rec_image_shape="3,32,100" --rec_algorithm="RARE" --min_subgraph_size=5
 --use_gpu:True|False
 --enable_mkldnn:True|False
 --cpu_threads:1|6

tools/eval.py

@@ -47,14 +47,40 @@ def main():
         if config['Architecture']["algorithm"] in ["Distillation",
                                                    ]:  # distillation model
             for key in config['Architecture']["Models"]:
-                config['Architecture']["Models"][key]["Head"][
-                    'out_channels'] = char_num
+                if config['Architecture']['Models'][key]['Head'][
+                        'name'] == 'MultiHead':  # for multi head
+                    out_channels_list = {}
+                    if config['PostProcess'][
+                            'name'] == 'DistillationSARLabelDecode':
+                        char_num = char_num - 2
+                    out_channels_list['CTCLabelDecode'] = char_num
+                    out_channels_list['SARLabelDecode'] = char_num + 2
+                    config['Architecture']['Models'][key]['Head'][
+                        'out_channels_list'] = out_channels_list
+                else:
+                    config['Architecture']["Models"][key]["Head"][
+                        'out_channels'] = char_num
+        elif config['Architecture']['Head'][
+                'name'] == 'MultiHead':  # for multi head
+            out_channels_list = {}
+            if config['PostProcess']['name'] == 'SARLabelDecode':
+                char_num = char_num - 2
+            out_channels_list['CTCLabelDecode'] = char_num
+            out_channels_list['SARLabelDecode'] = char_num + 2
+            config['Architecture']['Head'][
+                'out_channels_list'] = out_channels_list
         else:  # base rec model
             config['Architecture']["Head"]['out_channels'] = char_num
 
     model = build_model(config['Architecture'])
-    extra_input = config['Architecture'][
-        'algorithm'] in ["SRN", "NRTR", "SAR", "SEED"]
+    extra_input_models = ["SRN", "NRTR", "SAR", "SEED", "SVTR"]
+    extra_input = False
+    if config['Architecture']['algorithm'] == 'Distillation':
+        for key in config['Architecture']["Models"]:
+            extra_input = extra_input or config['Architecture']['Models'][key][
+                'algorithm'] in extra_input_models
+    else:
+        extra_input = config['Architecture']['algorithm'] in extra_input_models
     if "model_type" in config['Architecture'].keys():
         model_type = config['Architecture']['model_type']
     else: