Merge branch 'dygraph' of https://github.com/PaddlePaddle/PaddleOCR into dygraph

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/det_mv3_db.yml

-Global:
-  use_gpu: false
-  epoch_num: 5
-  log_smooth_window: 20
-  print_batch_step: 1
-  save_model_dir: ./output/db_mv3/
-  save_epoch_step: 1200
-  # evaluation is run every 2000 iterations
-  eval_batch_step: [0, 400]
-  cal_metric_during_train: False
-  pretrained_model: ./pretrain_models/MobileNetV3_large_x0_5_pretrained
-  checkpoints:
-  save_inference_dir:
-  use_visualdl: False
-  infer_img: doc/imgs_en/img_10.jpg
-  save_res_path: ./output/det_db/predicts_db.txt
-
-Architecture:
-  model_type: det
-  algorithm: DB
-  Transform:
-  Backbone:
-    name: MobileNetV3
-    scale: 0.5
-    model_name: large
-    disable_se: False
-  Neck:
-    name: DBFPN
-    out_channels: 256
-  Head:
-    name: DBHead
-    k: 50
-
-Loss:
-  name: DBLoss
-  balance_loss: true
-  main_loss_type: DiceLoss
-  alpha: 5 
-  beta: 10 
-  ohem_ratio: 3
-
-Optimizer:
-  name: Adam #Momentum
-  #momentum: 0.9
-  beta1: 0.9
-  beta2: 0.999
-  lr:
-    learning_rate: 0.001
-  regularizer:
-    name: 'L2'
-    factor: 0
-
-PostProcess:
-  name: DBPostProcess
-  thresh: 0.3
-  box_thresh: 0.6
-  max_candidates: 1000
-  unclip_ratio: 1.5
-
-Metric:
-  name: DetMetric
-  main_indicator: hmean
-
-Train:
-  dataset:
-    name: SimpleDataSet
-    data_dir: ./train_data/icdar2015/text_localization/
-    label_file_list:
-      - ./train_data/icdar2015/text_localization/train_icdar2015_label.txt
-    ratio_list: [1.0]
-    transforms:
-      - DecodeImage: # load image
-          img_mode: BGR
-          channel_first: False
-      - DetLabelEncode: # Class handling label
-      - Resize:
-          size: [640, 640]
-      - MakeBorderMap:
-          shrink_ratio: 0.4
-          thresh_min: 0.3
-          thresh_max: 0.7
-      - MakeShrinkMap:
-          shrink_ratio: 0.4
-          min_text_size: 8
-      - NormalizeImage:
-          scale: 1./255.
-          mean: [0.485, 0.456, 0.406]
-          std: [0.229, 0.224, 0.225]
-          order: 'hwc'
-      - ToCHWImage:
-      - KeepKeys:
-          keep_keys: ['image', 'threshold_map', 'threshold_mask', 'shrink_map', 'shrink_mask'] # the order of the dataloader list
-  loader:
-    shuffle: False
-    drop_last: False
-    batch_size_per_card: 1
-    num_workers: 0
-    use_shared_memory: False
-
-Eval:
-  dataset:
-    name: SimpleDataSet
-    data_dir: ./train_data/icdar2015/text_localization/
-    label_file_list:
-      - ./train_data/icdar2015/text_localization/test_icdar2015_label.txt
-    transforms:
-      - DecodeImage: # load image
-          img_mode: BGR
-          channel_first: False
-      - DetLabelEncode: # Class handling label
-      - DetResizeForTest:
-          image_shape: [736, 1280]
-      - NormalizeImage:
-          scale: 1./255.
-          mean: [0.485, 0.456, 0.406]
-          std: [0.229, 0.224, 0.225]
-          order: 'hwc'
-      - ToCHWImage:
-      - KeepKeys:
-          keep_keys: ['image', 'shape', 'polys', 'ignore_tags']
-  loader:
-    shuffle: False
-    drop_last: False
-    batch_size_per_card: 1 # must be 1
-    num_workers: 0
-    use_shared_memory: False

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]}]

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:

tools/export_model.py

@@ -55,6 +55,18 @@ def export_single_model(model, arch_config, save_path, logger):
                 shape=[None, 3, 48, 160], dtype="float32"),
         ]
         model = to_static(model, input_spec=other_shape)
+    elif arch_config["algorithm"] == "SVTR":
+        if arch_config["Head"]["name"] == 'MultiHead':
+            other_shape = [
+                paddle.static.InputSpec(
+                    shape=[None, 3, 48, -1], dtype="float32"),
+            ]
+        else:
+            other_shape = [
+                paddle.static.InputSpec(
+                    shape=[None, 3, 64, 256], dtype="float32"),
+            ]
+        model = to_static(model, input_spec=other_shape)
     elif arch_config["algorithm"] == "PREN":
         other_shape = [
             paddle.static.InputSpec(
@@ -105,13 +117,36 @@ 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':  # 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
+                    loss_list = config['Loss']['loss_config_list']
+                    config['Architecture']['Models'][key]['Head'][
+                        'out_channels_list'] = out_channels_list
+                else:
+                    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
+        elif config['Architecture']['Head'][
+                'name'] == 'MultiHead':  # multi head
+            out_channels_list = {}
+            char_num = len(getattr(post_process_class, 'character'))
+            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"])
     load_model(config, model)
     model.eval()

tools/infer/predict_rec.py

@@ -107,7 +107,7 @@ class TextRecognizer(object):
             return norm_img.astype(np.float32) / 128. - 1.
 
         assert imgC == img.shape[2]
-        imgW = int((32 * max_wh_ratio))
+        imgW = int((imgH * max_wh_ratio))
         if self.use_onnx:
             w = self.input_tensor.shape[3:][0]
             if w is not None and w > 0:
@@ -131,6 +131,17 @@ class TextRecognizer(object):
         padding_im = np.zeros((imgC, imgH, imgW), dtype=np.float32)
         padding_im[:, :, 0:resized_w] = resized_image
         return padding_im
+    
+    def resize_norm_img_svtr(self, img, image_shape):
+
+        imgC, imgH, imgW = image_shape
+        resized_image = cv2.resize(
+            img, (imgW, imgH), interpolation=cv2.INTER_LINEAR)
+        resized_image = resized_image.astype('float32')
+        resized_image = resized_image.transpose((2, 0, 1)) / 255
+        resized_image -= 0.5
+        resized_image /= 0.5
+        return resized_image
 
     def resize_norm_img_srn(self, img, image_shape):
         imgC, imgH, imgW = image_shape
@@ -255,18 +266,16 @@ class TextRecognizer(object):
         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 = []
-            max_wh_ratio = 0
+            imgC, imgH, imgW = self.rec_image_shape
+            max_wh_ratio = imgW / imgH
+            # max_wh_ratio = 0
             for ino in range(beg_img_no, end_img_no):
                 h, w = img_list[indices[ino]].shape[0:2]
                 wh_ratio = w * 1.0 / h
                 max_wh_ratio = max(max_wh_ratio, wh_ratio)
             for ino in range(beg_img_no, end_img_no):
-                if self.rec_algorithm != "SRN" and self.rec_algorithm != "SAR":
-                    norm_img = self.resize_norm_img(img_list[indices[ino]],
-                                                    max_wh_ratio)
-                    norm_img = norm_img[np.newaxis, :]
-                    norm_img_batch.append(norm_img)
-                elif self.rec_algorithm == "SAR":
+               
+                if self.rec_algorithm == "SAR":
                     norm_img, _, _, valid_ratio = self.resize_norm_img_sar(
                         img_list[indices[ino]], self.rec_image_shape)
                     norm_img = norm_img[np.newaxis, :]
@@ -274,7 +283,7 @@ class TextRecognizer(object):
                     valid_ratios = []
                     valid_ratios.append(valid_ratio)
                     norm_img_batch.append(norm_img)
-                else:
+                elif self.rec_algorithm == "SRN":
                     norm_img = self.process_image_srn(
                         img_list[indices[ino]], self.rec_image_shape, 8, 25)
                     encoder_word_pos_list = []
@@ -286,6 +295,16 @@ class TextRecognizer(object):
                     gsrm_slf_attn_bias1_list.append(norm_img[3])
                     gsrm_slf_attn_bias2_list.append(norm_img[4])
                     norm_img_batch.append(norm_img[0])
+                elif self.rec_algorithm == "SVTR":
+                    norm_img = self.resize_norm_img_svtr(
+                        img_list[indices[ino]], self.rec_image_shape)
+                    norm_img = norm_img[np.newaxis, :]
+                    norm_img_batch.append(norm_img)
+                else:
+                    norm_img = self.resize_norm_img(img_list[indices[ino]],
+                                                    max_wh_ratio)
+                    norm_img = norm_img[np.newaxis, :]
+                    norm_img_batch.append(norm_img)
             norm_img_batch = np.concatenate(norm_img_batch)
             norm_img_batch = norm_img_batch.copy()
             if self.benchmark:

tools/infer/utility.py

@@ -271,9 +271,10 @@ def create_predictor(args, mode, logger):
             elif mode == "rec":
                 if args.rec_algorithm != "CRNN":
                     use_dynamic_shape = False
-                min_input_shape = {"x": [1, 3, 32, 10]}
-                max_input_shape = {"x": [args.rec_batch_num, 3, 32, 1536]}
-                opt_input_shape = {"x": [args.rec_batch_num, 3, 32, 320]}
+                imgH = int(args.rec_image_shape.split(',')[-2])
+                min_input_shape = {"x": [1, 3, imgH, 10]}
+                max_input_shape = {"x": [args.rec_batch_num, 3, imgH, 1536]}
+                opt_input_shape = {"x": [args.rec_batch_num, 3, imgH, 320]}
             elif mode == "cls":
                 min_input_shape = {"x": [1, 3, 48, 10]}
                 max_input_shape = {"x": [args.rec_batch_num, 3, 48, 1024]}
@@ -300,7 +301,8 @@ def create_predictor(args, mode, logger):
         # enable memory optim
         config.enable_memory_optim()
         config.disable_glog_info()
-
+        config.delete_pass("reshape_transpose_matmul_v2_mkldnn_fuse_pass")
+        config.delete_pass("reshape_transpose_matmul_mkldnn_fuse_pass")
         config.delete_pass("conv_transpose_eltwiseadd_bn_fuse_pass")
         if mode == 'table':
             config.delete_pass("fc_fuse_pass")  # not supported for table

tools/infer_rec.py

@@ -51,8 +51,28 @@ 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 loss
+            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
 

tools/program.py

@@ -201,12 +201,19 @@ def train(config,
     model.train()
 
     use_srn = config['Architecture']['algorithm'] == "SRN"
-    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
     try:
         model_type = config['Architecture']['model_type']
     except:
         model_type = None
+
     algorithm = config['Architecture']['algorithm']
 
     start_epoch = best_model_dict[
@@ -269,7 +276,12 @@ def train(config,
                 if model_type in ['table', 'kie']:
                     eval_class(preds, batch)
                 else:
-                    post_result = post_process_class(preds, batch[1])
+                    if config['Loss']['name'] in ['MultiLoss', 'MultiLoss_v2'
+                                                  ]:  # for multi head loss
+                        post_result = post_process_class(
+                            preds['ctc'], batch[1])  # for CTC head out
+                    else:
+                        post_result = post_process_class(preds, batch[1])
                     eval_class(post_result, batch)
                 metric = eval_class.get_metric()
                 train_stats.update(metric)
@@ -541,7 +553,7 @@ def preprocess(is_train=False):
     assert alg in [
         'EAST', 'DB', 'SAST', 'Rosetta', 'CRNN', 'STARNet', 'RARE', 'SRN',
         'CLS', 'PGNet', 'Distillation', 'NRTR', 'TableAttn', 'SAR', 'PSE',
-        'SEED', 'SDMGR', 'LayoutXLM', 'LayoutLM', 'PREN', 'FCE'
+        'SEED', 'SDMGR', 'LayoutXLM', 'LayoutLM', 'PREN', 'FCE', 'SVTR'
     ]
 
     device = 'cpu'

tools/train.py

@@ -74,11 +74,49 @@ def main(config, device, logger, vdl_writer):
         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
+                    if config['PostProcess'][
+                            'name'] == 'DistillationSARLabelDecode':
+                        char_num = char_num - 2
+                    # update SARLoss params
+                    assert list(config['Loss']['loss_config_list'][-1].keys())[
+                        0] == 'DistillationSARLoss'
+                    config['Loss']['loss_config_list'][-1][
+                        'DistillationSARLoss']['ignore_index'] = char_num + 1
+                    out_channels_list = {}
+                    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
+            if config['PostProcess']['name'] == 'SARLabelDecode':
+                char_num = char_num - 2
+            # update SARLoss params
+            assert list(config['Loss']['loss_config_list'][1].keys())[
+                0] == 'SARLoss'
+            if config['Loss']['loss_config_list'][1]['SARLoss'] is None:
+                config['Loss']['loss_config_list'][1]['SARLoss'] = {
+                    'ignore_index': char_num + 1
+                }
+            else:
+                config['Loss']['loss_config_list'][1]['SARLoss'][
+                    'ignore_index'] = char_num + 1
+            out_channels_list = {}
+            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
 
+        if config['PostProcess']['name'] == 'SARLabelDecode':  # for SAR model
+            config['Loss']['ignore_index'] = char_num - 1
+
     model = build_model(config['Architecture'])
     if config['Global']['distributed']:
         model = paddle.DataParallel(model)
@@ -91,7 +129,7 @@ def main(config, device, logger, vdl_writer):
         config['Optimizer'],
         epochs=config['Global']['epoch_num'],
         step_each_epoch=len(train_dataloader),
-        parameters=model.parameters())
+        model=model)
 
     # build metric
     eval_class = build_metric(config['Metric'])