add benckmark

Evezerest · Jul 30, 2022 · dd1e17f · dd1e17f
1 parent f6250d6
commit dd1e17f
Show file tree

Hide file tree

Showing 28 changed files with 425 additions and 59 deletions.
diff --git a/configs/det/det_mv3_db.yml b/configs/det/det_mv3_db.yml
@@ -101,7 +101,7 @@ Train:
  drop_last: False
  batch_size_per_card: 16
  num_workers: 8
- use_shared_memory: False
+ use_shared_memory: True
 
 Eval:
  dataset:
@@ -129,4 +129,4 @@ Eval:
  drop_last: False
  batch_size_per_card: 1 # must be 1
  num_workers: 8
- use_shared_memory: False
+ use_shared_memory: True
diff --git a/test_tipc/configs/ch_PP-OCRv2_det/train_infer_python.txt b/test_tipc/configs/ch_PP-OCRv2_det/train_infer_python.txt
@@ -13,7 +13,7 @@ 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 
+norm_train:tools/train.py -c configs/det/ch_PP-OCRv2/ch_PP-OCRv2_det_cml.yml -o Global.print_batch_step=1 Train.loader.shuffle=false
 pact_train:null
 fpgm_train:null
 distill_train:null
@@ -51,3 +51,9 @@ null:null
 null:null
 ===========================infer_benchmark_params==========================
 random_infer_input:[{float32,[3,640,640]}];[{float32,[3,960,960]}]
+===========================train_benchmark_params==========================
+batch_size:8
+fp_items:fp32|fp16
+epoch:2
+--profiler_options:batch_range=[10,20];state=GPU;tracer_option=Default;profile_path=model.profile
+flags:FLAGS_eager_delete_tensor_gb=0.0;FLAGS_fraction_of_gpu_memory_to_use=0.98;FLAGS_conv_workspace_size_limit=4096
diff --git a/test_tipc/configs/ch_PP-OCRv2_rec/ch_PP-OCRv2_rec_distillation.yml b/test_tipc/configs/ch_PP-OCRv2_rec/ch_PP-OCRv2_rec_distillation.yml
@@ -6,7 +6,7 @@ Global:
  print_batch_step: 10
  save_model_dir: ./output/rec_pp-OCRv2_distillation
  save_epoch_step: 3
- eval_batch_step: [0, 2000]
+ eval_batch_step: [0, 200000]
  cal_metric_during_train: true
  pretrained_model:
  checkpoints:
@@ -114,7 +114,7 @@ Train:
  name: SimpleDataSet
  data_dir: ./train_data/ic15_data/
  label_file_list:
- - ./train_data/ic15_data/rec_gt_train.txt
+ - ./train_data/ic15_data/rec_gt_train4w.txt
  transforms:
  - DecodeImage:
  img_mode: BGR

diff --git a/test_tipc/configs/ch_PP-OCRv2_rec/train_infer_python.txt b/test_tipc/configs/ch_PP-OCRv2_rec/train_infer_python.txt
@@ -13,7 +13,7 @@ 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 
+norm_train:tools/train.py -c test_tipc/configs/ch_PP-OCRv2_rec/ch_PP-OCRv2_rec_distillation.yml -o Global.print_batch_step=4 Train.loader.shuffle=false
 pact_train:null
 fpgm_train:null
 distill_train:null
@@ -51,3 +51,9 @@ null:null
 null:null
 ===========================infer_benchmark_params==========================
 random_infer_input:[{float32,[3,32,320]}]
+===========================train_benchmark_params==========================
+batch_size:64
+fp_items:fp32|fp16
+epoch:1
+--profiler_options:batch_range=[10,20];state=GPU;tracer_option=Default;profile_path=model.profile
+flags:FLAGS_eager_delete_tensor_gb=0.0;FLAGS_fraction_of_gpu_memory_to_use=0.98;FLAGS_conv_workspace_size_limit=4096
diff --git a/test_tipc/configs/ch_PP-OCRv3_det/train_infer_python.txt b/test_tipc/configs/ch_PP-OCRv3_det/train_infer_python.txt
@@ -13,7 +13,7 @@ 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-OCRv3/ch_PP-OCRv3_det_cml.yml -o 
+norm_train:tools/train.py -c configs/det/ch_PP-OCRv3/ch_PP-OCRv3_det_cml.yml -o Global.print_batch_step=1 Train.loader.shuffle=false Global.eval_batch_step=[4000,400]
 pact_train:null
 fpgm_train:null
 distill_train:null
@@ -51,3 +51,9 @@ null:null
 null:null
 ===========================infer_benchmark_params==========================
 random_infer_input:[{float32,[3,640,640]}];[{float32,[3,960,960]}]
+===========================train_benchmark_params==========================
+batch_size:8
+fp_items:fp32|fp16
+epoch:2
+--profiler_options:batch_range=[10,20];state=GPU;tracer_option=Default;profile_path=model.profile
+flags:FLAGS_eager_delete_tensor_gb=0.0;FLAGS_fraction_of_gpu_memory_to_use=0.98;FLAGS_conv_workspace_size_limit=4096
diff --git a/test_tipc/configs/ch_PP-OCRv3_rec/ch_PP-OCRv3_rec_distillation.yml b/test_tipc/configs/ch_PP-OCRv3_rec/ch_PP-OCRv3_rec_distillation.yml
@@ -153,7 +153,7 @@ Train:
  data_dir: ./train_data/ic15_data/
  ext_op_transform_idx: 1
  label_file_list:
- - ./train_data/ic15_data/rec_gt_train_lite.txt
+ - ./train_data/ic15_data/rec_gt_train4w.txt
  transforms:
  - DecodeImage:
  img_mode: BGR
@@ -183,7 +183,7 @@ Eval:
  name: SimpleDataSet
  data_dir: ./train_data/ic15_data
  label_file_list:
- - ./train_data/ic15_data/rec_gt_test_lite.txt
+ - ./train_data/ic15_data/rec_gt_test.txt
  transforms:
  - DecodeImage:
  img_mode: BGR

diff --git a/test_tipc/configs/ch_PP-OCRv3_rec/train_infer_python.txt b/test_tipc/configs/ch_PP-OCRv3_rec/train_infer_python.txt
@@ -13,7 +13,7 @@ train_infer_img_dir:./inference/rec_inference
 null:null
 ##
 trainer:norm_train
-norm_train:tools/train.py -c test_tipc/configs/ch_PP-OCRv3_rec/ch_PP-OCRv3_rec_distillation.yml -o 
+norm_train:tools/train.py -c test_tipc/configs/ch_PP-OCRv3_rec/ch_PP-OCRv3_rec_distillation.yml -o Global.print_batch_step=1 Train.loader.shuffle=false
 pact_train:null
 fpgm_train:null
 distill_train:null
@@ -51,3 +51,9 @@ null:null
 null:null
 ===========================infer_benchmark_params==========================
 random_infer_input:[{float32,[3,48,320]}]
+===========================train_benchmark_params==========================
+batch_size:128
+fp_items:fp32|fp16
+epoch:1
+--profiler_options:batch_range=[10,20];state=GPU;tracer_option=Default;profile_path=model.profile
+flags:FLAGS_eager_delete_tensor_gb=0.0;FLAGS_fraction_of_gpu_memory_to_use=0.98;FLAGS_conv_workspace_size_limit=4096
diff --git a/test_tipc/configs/ch_ppocr_mobile_v2.0_det/train_infer_python.txt b/test_tipc/configs/ch_ppocr_mobile_v2.0_det/train_infer_python.txt
@@ -13,7 +13,7 @@ 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_ppocr_v2.0/ch_det_mv3_db_v2.0.yml -o Global.pretrained_model=./pretrain_models/MobileNetV3_large_x0_5_pretrained
+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 Global.print_batch_step=1 Train.loader.shuffle=false
 pact_train:null
 fpgm_train:null
 distill_train:null
@@ -50,4 +50,10 @@ null:null
 --benchmark:True
 null:null
 ===========================infer_benchmark_params==========================
-random_infer_input:[{float32,[3,640,640]}];[{float32,[3,960,960]}]
+random_infer_input:[{float32,[3,640,640]}];[{float32,[3,960,960]}]
+===========================train_benchmark_params==========================
+batch_size:8
+fp_items:fp32|fp16
+epoch:2
+--profiler_options:batch_range=[10,20];state=GPU;tracer_option=Default;profile_path=model.profile
+flags:FLAGS_eager_delete_tensor_gb=0.0;FLAGS_fraction_of_gpu_memory_to_use=0.98;FLAGS_conv_workspace_size_limit=4096
diff --git a/test_tipc/configs/ch_ppocr_mobile_v2.0_rec/train_infer_python.txt b/test_tipc/configs/ch_ppocr_mobile_v2.0_rec/train_infer_python.txt
@@ -13,7 +13,7 @@ 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
+norm_train:tools/train.py -c configs/rec/rec_icdar15_train.yml -o Global.print_batch_step=4 Train.loader.shuffle=false
 pact_train:null
 fpgm_train:null
 distill_train:null
@@ -51,3 +51,9 @@ inference:tools/infer/predict_rec.py
 null:null
 ===========================infer_benchmark_params==========================
 random_infer_input:[{float32,[3,32,100]}]
+===========================train_benchmark_params==========================
+batch_size:256
+fp_items:fp32|fp16
+epoch:3
+--profiler_options:batch_range=[10,20];state=GPU;tracer_option=Default;profile_path=model.profile
+flags:FLAGS_eager_delete_tensor_gb=0.0;FLAGS_fraction_of_gpu_memory_to_use=0.98;FLAGS_conv_workspace_size_limit=4096
diff --git a/test_tipc/configs/ch_ppocr_server_v2.0_det/det_r50_vd_db.yml b/test_tipc/configs/ch_ppocr_server_v2.0_det/det_r50_vd_db.yml
@@ -2,13 +2,13 @@ Global:
  use_gpu: false
  epoch_num: 5
  log_smooth_window: 20
- print_batch_step: 1
+ print_batch_step: 2
  save_model_dir: ./output/db_mv3/
  save_epoch_step: 1200
  # evaluation is run every 2000 iterations
- eval_batch_step: [0, 400]
+ eval_batch_step: [0, 30000]
  cal_metric_during_train: False
- pretrained_model: ./pretrain_models/MobileNetV3_large_x0_5_pretrained
+ pretrained_model:
  checkpoints:
  save_inference_dir:
  use_visualdl: False

diff --git a/test_tipc/configs/ch_ppocr_server_v2.0_det/train_infer_python.txt b/test_tipc/configs/ch_ppocr_server_v2.0_det/train_infer_python.txt
@@ -13,7 +13,7 @@ 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 
+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
@@ -50,4 +50,10 @@ inference:tools/infer/predict_det.py
 --benchmark:True
 null:null
 ===========================infer_benchmark_params==========================
-random_infer_input:[{float32,[3,640,640]}];[{float32,[3,960,960]}]
+random_infer_input:[{float32,[3,640,640]}];[{float32,[3,960,960]}]
+===========================train_benchmark_params==========================
+batch_size:8
+fp_items:fp32|fp16
+epoch:2
+--profiler_options:batch_range=[10,20];state=GPU;tracer_option=Default;profile_path=model.profile
+flags:FLAGS_eager_delete_tensor_gb=0.0;FLAGS_fraction_of_gpu_memory_to_use=0.98;FLAGS_conv_workspace_size_limit=4096
diff --git a/test_tipc/configs/ch_ppocr_server_v2.0_rec/train_infer_python.txt b/test_tipc/configs/ch_ppocr_server_v2.0_rec/train_infer_python.txt
@@ -13,7 +13,7 @@ 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
+norm_train:tools/train.py -c test_tipc/configs/ch_ppocr_server_v2.0_rec/rec_icdar15_train.yml -o Global.print_batch_step=4 Train.loader.shuffle=false
 pact_train:null
 fpgm_train:null
 distill_train:null
@@ -51,3 +51,9 @@ inference:tools/infer/predict_rec.py
 null:null
 ===========================infer_benchmark_params==========================
 random_infer_input:[{float32,[3,32,100]}]
+===========================train_benchmark_params==========================
+batch_size:256
+fp_items:fp32|fp16
+epoch:2
+--profiler_options:batch_range=[10,20];state=GPU;tracer_option=Default;profile_path=model.profile
+flags:FLAGS_eager_delete_tensor_gb=0.0;FLAGS_fraction_of_gpu_memory_to_use=0.98;FLAGS_conv_workspace_size_limit=4096
diff --git a/test_tipc/configs/det_mv3_db_v2_0/train_infer_python.txt b/test_tipc/configs/det_mv3_db_v2_0/train_infer_python.txt
@@ -13,7 +13,7 @@ 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/det_mv3_db.yml -o Global.pretrained_model=./pretrain_models/MobileNetV3_large_x0_5_pretrained
+norm_train:tools/train.py -c configs/det/det_mv3_db.yml -o Global.pretrained_model=./pretrain_models/MobileNetV3_large_x0_5_pretrained Global.print_batch_step=1 Train.loader.shuffle=false
 pact_train:null
 fpgm_train:null
 distill_train:null
@@ -52,8 +52,8 @@ null:null
 ===========================infer_benchmark_params==========================
 random_infer_input:[{float32,[3,640,640]}];[{float32,[3,960,960]}]
 ===========================train_benchmark_params==========================
-batch_size:8|16
+batch_size:16
 fp_items:fp32|fp16
-epoch:15
+epoch:4
 --profiler_options:batch_range=[10,20];state=GPU;tracer_option=Default;profile_path=model.profile
-flags:FLAGS_eager_delete_tensor_gb=0.0;FLAGS_fraction_of_gpu_memory_to_use=0.98;FLAGS_conv_workspace_size_limit=4096
+flags:FLAGS_eager_delete_tensor_gb=0.0;FLAGS_fraction_of_gpu_memory_to_use=0.98;FLAGS_conv_workspace_size_limit=4096
diff --git a/test_tipc/configs/det_r50_db_v2.0/train_infer_python.txt b/test_tipc/configs/det_r50_db_v2.0/train_infer_python.txt
@@ -13,7 +13,7 @@ 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/det_r50_vd_db.yml -o 
+norm_train:tools/train.py -c configs/det/det_r50_vd_db.yml -o Global.print_batch_step=1 Train.loader.shuffle=false
 quant_export:null
 fpgm_export:null
 distill_train:null
@@ -50,4 +50,10 @@ inference:tools/infer/predict_det.py
 --benchmark:True
 null:null
 ===========================infer_benchmark_params==========================
-random_infer_input:[{float32,[3,640,640]}];[{float32,[3,960,960]}]
+random_infer_input:[{float32,[3,640,640]}];[{float32,[3,960,960]}]
+===========================train_benchmark_params==========================
+batch_size:8
+fp_items:fp32|fp16
+epoch:2
+--profiler_options:batch_range=[10,20];state=GPU;tracer_option=Default;profile_path=model.profile
+flags:FLAGS_eager_delete_tensor_gb=0.0;FLAGS_fraction_of_gpu_memory_to_use=0.98;FLAGS_conv_workspace_size_limit=4096