mirrors
/
PaddleOCR
mirror of https://github.com/PaddlePaddle/PaddleOCR.git
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity

add benckmark

pull/7049/head
WenmuZhou 2022-07-30 10:00:11 +08:00
parent f6250d61e4
commit dd1e17fd79
28 changed files with 425 additions and 59 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
configs/det/det_mv3_db.yml
View File

@ -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

8
test_tipc/configs/ch_PP-OCRv2_det/train_infer_python.txt
View File

@ -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

4
test_tipc/configs/ch_PP-OCRv2_rec/ch_PP-OCRv2_rec_distillation.yml
View File

@ -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

8
test_tipc/configs/ch_PP-OCRv2_rec/train_infer_python.txt
View File

@ -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

8
test_tipc/configs/ch_PP-OCRv3_det/train_infer_python.txt
View File

@ -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

4
test_tipc/configs/ch_PP-OCRv3_rec/ch_PP-OCRv3_rec_distillation.yml
View File

@ -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

8
test_tipc/configs/ch_PP-OCRv3_rec/train_infer_python.txt
View File

@ -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

10
test_tipc/configs/ch_ppocr_mobile_v2.0_det/train_infer_python.txt
View File

@ -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

8
test_tipc/configs/ch_ppocr_mobile_v2.0_rec/train_infer_python.txt
View File

@ -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

6
test_tipc/configs/ch_ppocr_server_v2.0_det/det_r50_vd_db.yml
View File

@ -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

10
test_tipc/configs/ch_ppocr_server_v2.0_det/train_infer_python.txt
View File

@ -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

8
test_tipc/configs/ch_ppocr_server_v2.0_rec/train_infer_python.txt
View File

@ -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

8
test_tipc/configs/det_mv3_db_v2_0/train_infer_python.txt
View File

@ -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

10
test_tipc/configs/det_r50_db_v2.0/train_infer_python.txt
View File

@ -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

139
test_tipc/configs/det_r50_dcn_fce_ctw_v2.0/det_r50_vd_dcn_fce_ctw.yml 100644
View File

@ -0,0 +1,139 @@
Global:
use_gpu: true
epoch_num: 1500
log_smooth_window: 20
print_batch_step: 20
save_model_dir: ./output/det_r50_dcn_fce_ctw/
save_epoch_step: 100
# evaluation is run every 835 iterations
eval_batch_step: [0, 4000]
cal_metric_during_train: False
pretrained_model: ./pretrain_models/ResNet50_vd_ssld_pretrained
checkpoints:
save_inference_dir:
use_visualdl: False
infer_img: doc/imgs_en/img_10.jpg
save_res_path: ./output/det_fce/predicts_fce.txt
Architecture:
model_type: det
algorithm: FCE
Transform:
Backbone:
name: ResNet_vd
layers: 50
dcn_stage: [False, True, True, True]
out_indices: [1,2,3]
Neck:
name: FCEFPN
out_channels: 256
has_extra_convs: False
extra_stage: 0
Head:
name: FCEHead
fourier_degree: 5
Loss:
name: FCELoss
fourier_degree: 5
num_sample: 50
Optimizer:
name: Adam
beta1: 0.9
beta2: 0.999
lr:
learning_rate: 0.0001
regularizer:
name: 'L2'
factor: 0
PostProcess:
name: FCEPostProcess
scales: [8, 16, 32]
alpha: 1.0
beta: 1.0
fourier_degree: 5
box_type: 'poly'
Metric:
name: DetFCEMetric
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
transforms:
- DecodeImage: # load image
img_mode: BGR
channel_first: False
ignore_orientation: True
- DetLabelEncode: # Class handling label
- ColorJitter:
brightness: 0.142
saturation: 0.5
contrast: 0.5
- RandomScaling:
- RandomCropFlip:
crop_ratio: 0.5
- RandomCropPolyInstances:
crop_ratio: 0.8
min_side_ratio: 0.3
- RandomRotatePolyInstances:
rotate_ratio: 0.5
max_angle: 30
pad_with_fixed_color: False
- SquareResizePad:
target_size: 800
pad_ratio: 0.6
- IaaAugment:
augmenter_args:
- { 'type': Fliplr, 'args': { 'p': 0.5 } }
- FCENetTargets:
fourier_degree: 5
- 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', 'p3_maps', 'p4_maps', 'p5_maps'] # dataloader will return list in this order
loader:
shuffle: True
drop_last: False
batch_size_per_card: 6
num_workers: 8
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
ignore_orientation: True
- DetLabelEncode: # Class handling label
- DetResizeForTest:
limit_type: 'min'
limit_side_len: 736
- NormalizeImage:
scale: 1./255.
mean: [0.485, 0.456, 0.406]
std: [0.229, 0.224, 0.225]
order: 'hwc'
- Pad:
- 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: 2

59
test_tipc/configs/det_r50_dcn_fce_ctw_v2.0/train_infer_python.txt 100644
View File

@ -0,0 +1,59 @@
===========================train_params===========================
model_name:det_r50_dcn_fce_ctw_v2.0
python:python3.7
gpu_list:0
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
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/det_r50_dcn_fce_ctw_v2.0/det_r50_vd_dcn_fce_ctw.yml -o Global.print_batch_step=1 Train.loader.shuffle=false
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/det_r50_dcn_fce_ctw_v2.0/det_r50_vd_dcn_fce_ctw.yml -o
quant_export:null
fpgm_export:null
distill_export:null
export1:null
export2:null
##
train_model:./inference/det_r50_dcn_fce_ctw_v2.0_train/best_accuracy
infer_export:tools/export_model.py -c test_tipc/configs/det_r50_dcn_fce_ctw_v2.0/det_r50_vd_dcn_fce_ctw.yml -o
infer_quant:False
inference:tools/infer/predict_det.py
--use_gpu:True|False
--enable_mkldnn:False
--cpu_threads:6
--rec_batch_num:1
--use_tensorrt:False
--precision:fp32
--det_model_dir:
--image_dir:./inference/ch_det_data_50/all-sum-510/
--save_log_path:null
--benchmark:True
--det_algorithm:FCE
===========================infer_benchmark_params==========================
random_infer_input:[{float32,[3,640,640]}];[{float32,[3,960,960]}]
===========================train_benchmark_params==========================
batch_size:6
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

2
test_tipc/configs/det_r50_vd_east_v2_0/det_r50_vd_east.yml
View File

@ -20,7 +20,7 @@ Architecture:
algorithm: EAST
Transform:
Backbone:
name: ResNet
name: ResNet_vd
layers: 50
Neck:
name: EASTFPN

5
test_tipc/configs/det_r50_vd_east_v2_0/train_infer_python.txt
View File

@ -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/det_r50_vd_east_v2_0/det_r50_vd_east.yml -o
norm_train:tools/train.py -c test_tipc/configs/det_r50_vd_east_v2_0/det_r50_vd_east.yml -o Global.pretrained_model=pretrain_models/det_r50_vd_east_v2.0_train/best_accuracy.pdparams Global.print_batch_step=1 Train.loader.shuffle=false
pact_train:null
fpgm_train:null
distill_train:null
@ -55,4 +55,5 @@ random_infer_input:[{float32,[3,640,640]}];[{float32,[3,960,960]}]
batch_size:8
fp_items:fp32|fp16
epoch:2
--profiler_options:batch_range=[10,20];state=GPU;tracer_option=Default;profile_path=model.profile
--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

4
test_tipc/configs/det_r50_vd_pse_v2_0/det_r50_vd_pse.yml
View File

@ -8,7 +8,7 @@ Global:
# evaluation is run every 125 iterations
eval_batch_step: [ 0,1000 ]
cal_metric_during_train: False
pretrained_model:
pretrained_model: ./pretrain_models/ResNet50_vd_ssld_pretrained
checkpoints: #./output/det_r50_vd_pse_batch8_ColorJitter/best_accuracy
save_inference_dir:
use_visualdl: False
@ -20,7 +20,7 @@ Architecture:
algorithm: PSE
Transform:
Backbone:
name: ResNet
name: ResNet_vd
layers: 50
Neck:
name: FPN

5
test_tipc/configs/det_r50_vd_pse_v2_0/train_infer_python.txt
View File

@ -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/det_r50_vd_pse_v2_0/det_r50_vd_pse.yml -o
norm_train:tools/train.py -c test_tipc/configs/det_r50_vd_pse_v2_0/det_r50_vd_pse.yml -o Global.print_batch_step=1 Train.loader.shuffle=false
pact_train:null
fpgm_train:null
distill_train:null
@ -54,5 +54,6 @@ random_infer_input:[{float32,[3,640,640]}];[{float32,[3,960,960]}]
===========================train_benchmark_params==========================
batch_size:8
fp_items:fp32|fp16
epoch:10
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

2
test_tipc/configs/en_table_structure/table_mv3.yml
View File

@ -6,7 +6,7 @@ Global:
save_model_dir: ./output/table_mv3/
save_epoch_step: 3
# evaluation is run every 400 iterations after the 0th iteration
eval_batch_step: [0, 400]
eval_batch_step: [0, 40000]
cal_metric_during_train: True
pretrained_model:
checkpoints:

10
test_tipc/configs/en_table_structure/train_infer_python.txt
View File

@ -13,7 +13,7 @@ train_infer_img_dir:./ppstructure/docs/table/table.jpg
null:null
##
trainer:norm_train
norm_train:tools/train.py -c test_tipc/configs/en_table_structure/table_mv3.yml -o
norm_train:tools/train.py -c test_tipc/configs/en_table_structure/table_mv3.yml -o Global.print_batch_step=1 Train.loader.shuffle=false
pact_train:null
fpgm_train:null
distill_train:null
@ -27,7 +27,7 @@ null:null
===========================infer_params===========================
Global.save_inference_dir:./output/
Global.checkpoints:
norm_export:tools/export_model.py -c test_tipc/configs/en_table_structure/table_mv3.yml -o
norm_export:tools/export_model.py -c test_tipc/configs/en_table_structure/table_mv3.yml -o
quant_export:
fpgm_export:
distill_export:null
@ -51,3 +51,9 @@ null:null
null:null
===========================infer_benchmark_params==========================
random_infer_input:[{float32,[3,488,488]}]
===========================train_benchmark_params==========================
batch_size:32
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

2
test_tipc/configs/rec_mv3_none_bilstm_ctc_v2.0/rec_icdar15_train.yml
View File

@ -6,7 +6,7 @@ Global:
save_model_dir: ./output/rec/mv3_none_bilstm_ctc/
save_epoch_step: 3
# evaluation is run every 2000 iterations
eval_batch_step: [0, 2000]
eval_batch_step: [0, 20000]
cal_metric_during_train: True
pretrained_model:
checkpoints:

10
test_tipc/configs/rec_mv3_none_bilstm_ctc_v2.0/train_infer_python.txt
View File

@ -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/rec_mv3_none_bilstm_ctc_v2.0/rec_icdar15_train.yml -o
norm_train:tools/train.py -c test_tipc/configs/rec_mv3_none_bilstm_ctc_v2.0/rec_icdar15_train.yml -o Global.print_batch_step=4 Train.loader.shuffle=false
pact_train:null
fpgm_train:null
distill_train:null
@ -50,4 +50,10 @@ inference:tools/infer/predict_rec.py --rec_char_dict_path=./ppocr/utils/ic15_dic
--benchmark:True
null:null
===========================infer_benchmark_params==========================
random_infer_input:[{float32,[3,32,100]}]
random_infer_input:[{float32,[3,32,100]}]
===========================train_benchmark_params==========================
batch_size:256
fp_items:fp32|fp16
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

22
test_tipc/docs/benchmark_train.md
View File

@ -51,3 +51,25 @@ train_log/
├── PaddleOCR_det_mv3_db_v2_0_bs8_fp32_SingleP_DP_N1C1_log
└── PaddleOCR_det_mv3_db_v2_0_bs8_fp32_SingleP_DP_N1C4_log
```
## 3. 各模型单卡性能数据一览
*注：本节中的速度指标均使用单卡（1块Nvidia V100 16G GPU）测得。通常情况下。
|模型名称|配置文件|大数据集 float32 fps |小数据集 float32 fps |diff |大数据集 float16 fps|小数据集 float16 fps| diff | 大数据集大小 | 小数据集大小 |
|:-:|:-:|:-:|:-:|:-:|:-:|:-:|:-:|:-:|:-:|
| ch_ppocr_mobile_v2.0_det |[config](../configs/ch_ppocr_mobile_v2.0_det/train_infer_python.txt) | 53.836 | 53.343 / 53.914 / 52.785 |0.020940758 | 45.574 | 45.57 / 46.292 / 46.213 | 0.015596647 | 10,000| 2,000|
| ch_ppocr_mobile_v2.0_rec |[config](../configs/ch_ppocr_mobile_v2.0_rec/train_infer_python.txt) | 2083.311 | 2043.194 / 2066.372 / 2093.317 |0.023944295 | 2153.261 | 2167.561 / 2165.726 / 2155.614| 0.005511725 | 600,000| 160,000|
| ch_ppocr_server_v2.0_det |[config](../configs/ch_ppocr_server_v2.0_det/train_infer_python.txt) | 20.716 | 20.739 / 20.807 / 20.755 |0.003268131 | 20.592 | 20.498 / 20.993 / 20.75| 0.023579288 | 10,000| 2,000|
| ch_ppocr_server_v2.0_rec |[config](../configs/ch_ppocr_server_v2.0_rec/train_infer_python.txt) | 528.56 | 528.386 / 528.991 / 528.391 |0.001143687 | 1189.788 | 1190.007 / 1176.332 / 1192.084| 0.013213834 | 600,000| 160,000|
| ch_PP-OCRv2_det |[config](../configs/ch_PP-OCRv2_det/train_infer_python.txt) | 13.87 | 13.386 / 13.529 / 13.428 |0.010569887 | 17.847 | 17.746 / 17.908 / 17.96| 0.011915367 | 10,000| 2,000|
| ch_PP-OCRv2_rec |[config](../configs/ch_PP-OCRv2_rec/train_infer_python.txt) | 109.248 | 106.32 / 106.318 / 108.587 |0.020895687 | 117.491 | 117.62 / 117.757 / 117.726| 0.001163413 | 140,000| 40,000|
| det_mv3_db_v2.0 |[config](../configs/det_mv3_db_v2_0/train_infer_python.txt) | 61.802 | 62.078 / 61.802 / 62.008 |0.00444602 | 82.947 | 84.294 / 84.457 / 84.005| 0.005351836 | 10,000| 2,000|
| det_r50_vd_db_v2.0 |[config](../configs/det_r50_vd_db_v2.0/train_infer_python.txt) | 29.955 | 29.092 / 29.31 / 28.844 |0.015899011 | 51.097 |50.367 / 50.879 / 50.227| 0.012814717 | 10,000| 2,000|
| det_r50_vd_east_v2.0 |[config](../configs/det_r50_vd_east_v2.0/train_infer_python.txt) | 42.485 | 42.624 / 42.663 / 42.561 |0.00239083 | 67.61 |67.825/ 68.299/ 68.51| 0.00999854 | 10,000| 2,000|
| det_r50_vd_pse_v2.0 |[config](../configs/det_r50_vd_pse_v2.0/train_infer_python.txt) | 16.455 | 16.517 / 16.555 / 16.353 |0.012201752 | 27.02 |27.288 / 27.152 / 27.408| 0.009340339 | 10,000| 2,000|
| rec_mv3_none_bilstm_ctc_v2.0 |[config](../configs/rec_mv3_none_bilstm_ctc_v2.0/train_infer_python.txt) | 2288.358 | 2291.906 / 2293.725 / 2290.05 |0.001602197 | 2336.17 |2327.042 / 2328.093 / 2344.915| 0.007622025 | 600,000| 160,000|
| PP-Structure-table |[config](../configs/en_table_structure/train_infer_python.txt) | 14.151 | 14.077 / 14.23 / 14.25 |0.012140351 | 16.285 | 16.595 / 16.878 / 16.531 | 0.020559308 | 20,000| 5,000|
| det_r50_dcn_fce_ctw_v2.0 |[config](../configs/det_r50_dcn_fce_ctw_v2.0/train_infer_python.txt) | 14.057 | 14.029 / 14.02 / 14.014 |0.001069214 | 18.298 |18.411 / 18.376 / 18.331| 0.004345228 | 10,000| 2,000|
| ch_PP-OCRv3_det |[config](../configs/ch_PP-OCRv3_det/train_infer_python.txt) | 8.622 | 8.431 / 8.423 / 8.479|0.006604552 | 14.203 |14.346 14.468 14.23| 0.016450097 | 10,000| 2,000|
| ch_PP-OCRv3_rec |[config](../configs/ch_PP-OCRv3_rec/train_infer_python.txt) | 73.627 | 72.46 / 73.575 / 73.704|0.016878324 | | | | 160,000| 40,000|

82
test_tipc/prepare.sh
View File

@ -22,27 +22,79 @@ trainer_list=$(func_parser_value "${lines[14]}")
if [ ${MODE} = "benchmark_train" ];then
pip install -r requirements.txt
if [[ ${model_name} =~ "det_mv3_db_v2_0" || ${model_name} =~ "det_r50_vd_pse_v2_0" || ${model_name} =~ "det_r18_db_v2_0" ]];then
rm -rf ./train_data/icdar2015
if [[ ${model_name} =~ "ch_ppocr_mobile_v2.0_det" || ${model_name} =~ "det_mv3_db_v2_0" ]];then
wget -nc -P ./pretrain_models/ https://paddleocr.bj.bcebos.com/pretrained/MobileNetV3_large_x0_5_pretrained.pdparams --no-check-certificate
wget -nc -P ./train_data/ https://paddleocr.bj.bcebos.com/dygraph_v2.0/test/icdar2015.tar --no-check-certificate
cd ./train_data/ && tar xf icdar2015.tar && cd ../
rm -rf ./train_data/icdar2015
wget -nc -P ./train_data/ https://paddleocr.bj.bcebos.com/dataset/icdar2015_benckmark.tar --no-check-certificate
cd ./train_data/ && tar xf icdar2015_benckmark.tar
ln -s ./icdar2015_benckmark ./icdar2015
cd ../
fi
if [[ ${model_name} =~ "ch_ppocr_server_v2.0_det" || ${model_name} =~ "ch_PP-OCRv3_det" ]];then
rm -rf ./train_data/icdar2015
wget -nc -P ./train_data/ https://paddleocr.bj.bcebos.com/dataset/icdar2015_benckmark.tar --no-check-certificate
cd ./train_data/ && tar xf icdar2015_benckmark.tar
ln -s ./icdar2015_benckmark ./icdar2015
cd ../
fi
if [[ ${model_name} =~ "ch_PP-OCRv2_det" ]];then
wget -nc -P ./pretrain_models/ https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_server_v2.0_det_train.tar --no-check-certificate
cd ./pretrain_models/ && tar xf ch_ppocr_server_v2.0_det_train.tar && cd ../
rm -rf ./train_data/icdar2015
wget -nc -P ./train_data/ https://paddleocr.bj.bcebos.com/dataset/icdar2015_benckmark.tar --no-check-certificate
cd ./train_data/ && tar xf icdar2015_benckmark.tar
ln -s ./icdar2015_benckmark ./icdar2015
cd ../
fi
if [[ ${model_name} =~ "det_r50_vd_east_v2_0" ]]; then
wget -nc -P ./pretrain_models/ https://paddleocr.bj.bcebos.com/dygraph_v2.0/en/det_r50_vd_east_v2.0_train.tar --no-check-certificate
cd ./pretrain_models/ && tar xf det_r50_vd_east_v2.0_train.tar && cd ../
wget -nc -P ./train_data/ https://paddleocr.bj.bcebos.com/dygraph_v2.0/test/icdar2015.tar --no-check-certificate
cd ./train_data/ && tar xf icdar2015.tar && cd ../
rm -rf ./train_data/icdar2015
wget -nc -P ./train_data/ https://paddleocr.bj.bcebos.com/dataset/icdar2015_benckmark.tar --no-check-certificate
cd ./train_data/ && tar xf icdar2015_benckmark.tar
ln -s ./icdar2015_benckmark ./icdar2015
cd ../
fi
if [[ ${model_name} =~ "det_r50_vd_pse_v2_0" ]];then
if [[ ${model_name} =~ "det_r50_db_v2.0" || ${model_name} =~ "det_r50_vd_pse_v2_0" ]];then
wget -nc -P ./pretrain_models/ https://paddleocr.bj.bcebos.com/pretrained/ResNet50_vd_ssld_pretrained.pdparams --no-check-certificate
wget -nc -P ./train_data/ https://paddleocr.bj.bcebos.com/dygraph_v2.0/test/icdar2015.tar --no-check-certificate
cd ./train_data/ && tar xf icdar2015.tar && cd ../
rm -rf ./train_data/icdar2015
wget -nc -P ./train_data/ https://paddleocr.bj.bcebos.com/dataset/icdar2015_benckmark.tar --no-check-certificate
cd ./train_data/ && tar xf icdar2015_benckmark.tar
ln -s ./icdar2015_benckmark ./icdar2015
cd ../
fi
if [[ ${model_name} =~ "det_r18_db_v2_0" ]];then
wget -nc -P ./pretrain_models/ https://paddleocr.bj.bcebos.com/pretrained/ResNet18_vd_pretrained.pdparams --no-check-certificate
wget -nc -P ./train_data/ https://paddleocr.bj.bcebos.com/dygraph_v2.0/test/icdar2015.tar --no-check-certificate
cd ./train_data/ && tar xf icdar2015.tar && cd ../
rm -rf ./train_data/icdar2015
wget -nc -P ./train_data/ https://paddleocr.bj.bcebos.com/dataset/icdar2015_benckmark.tar --no-check-certificate
cd ./train_data/ && tar xf icdar2015_benckmark.tar
ln -s ./icdar2015_benckmark ./icdar2015
cd ../
fi
if [[ ${model_name} =~ "ch_ppocr_mobile_v2.0_rec" || ${model_name} =~ "ch_ppocr_server_v2.0_rec" || ${model_name} =~ "ch_PP-OCRv2_rec" || ${model_name} =~ "rec_mv3_none_bilstm_ctc_v2.0" || ${model_name} =~ "ch_PP-OCRv3_rec" ]];then
rm -rf ./train_data/ic15_data_benckmark
wget -nc -P ./train_data/ https://paddleocr.bj.bcebos.com/dataset/ic15_data_benckmark.tar --no-check-certificate
cd ./train_data/ && tar xf ic15_data_benckmark.tar
ln -s ./ic15_data_benckmark ./ic15_data
cd ../
fi
if [[ ${model_name} == "en_table_structure" ]];then
wget -nc -P ./pretrain_models/ https://paddleocr.bj.bcebos.com/dygraph_v2.1/table/en_ppocr_mobile_v2.0_table_structure_train.tar --no-check-certificate
cd ./pretrain_models/ && tar xf en_ppocr_mobile_v2.0_table_structure_train.tar && cd ../
rm -rf ./train_data/pubtabnet
wget -nc -P ./train_data/ https://paddleocr.bj.bcebos.com/dataset/pubtabnet_benckmark.tar --no-check-certificate
cd ./train_data/ && tar xf pubtabnet_benckmark.tar
ln -s ./pubtabnet_benckmark ./pubtabnet
cd ../
fi
if [[ ${model_name} == "det_r50_dcn_fce_ctw_v2.0" ]]; then
wget -nc -P ./pretrain_models/ https://paddleocr.bj.bcebos.com/contribution/det_r50_dcn_fce_ctw_v2.0_train.tar --no-check-certificate
cd ./pretrain_models/ && tar xf det_r50_dcn_fce_ctw_v2.0_train.tar && cd ../
rm -rf ./train_data/icdar2015
wget -nc -P ./train_data/ https://paddleocr.bj.bcebos.com/dataset/icdar2015_benckmark.tar --no-check-certificate
cd ./train_data/ && tar xf icdar2015_benckmark.tar
ln -s ./icdar2015_benckmark ./icdar2015
cd ../
fi
fi
@ -137,6 +189,10 @@ if [ ${MODE} = "lite_train_lite_infer" ];then
wget -nc -P ./pretrain_models/ https://paddleocr.bj.bcebos.com/dygraph_v2.0/en/det_r50_vd_east_v2.0_train.tar --no-check-certificate
cd ./pretrain_models/ && tar xf det_r50_vd_east_v2.0_train.tar && cd ../
fi
if [ ${model_name} == "det_r50_dcn_fce_ctw_v2.0" ]; then
wget -nc -P ./pretrain_models/ https://paddleocr.bj.bcebos.com/contribution/det_r50_dcn_fce_ctw_v2.0_train.tar --no-check-certificate
cd ./pretrain_models/ && tar xf det_r50_dcn_fce_ctw_v2.0_train.tar & cd ../
fi
elif [ ${MODE} = "whole_train_whole_infer" ];then
wget -nc -P ./pretrain_models/ https://paddle-imagenet-models-name.bj.bcebos.com/dygraph/MobileNetV3_large_x0_5_pretrained.pdparams --no-check-certificate
@ -363,6 +419,10 @@ elif [ ${MODE} = "whole_infer" ];then
wget -nc -P ./inference/ https://paddleocr.bj.bcebos.com/dygraph_v2.0/en/det_r50_vd_east_v2.0_train.tar --no-check-certificate
cd ./inference/ && tar xf det_r50_vd_east_v2.0_train.tar & cd ../
fi
if [ ${model_name} == "det_r50_dcn_fce_ctw_v2.0" ]; then
wget -nc -P ./inference/ https://paddleocr.bj.bcebos.com/contribution/det_r50_dcn_fce_ctw_v2.0_train.tar --no-check-certificate
cd ./inference/ && tar xf det_r50_dcn_fce_ctw_v2.0_train.tar & cd ../
fi
if [[ ${model_name} =~ "en_table_structure" ]];then
wget -nc -P ./inference/ https://paddleocr.bj.bcebos.com/dygraph_v2.0/table/en_ppocr_mobile_v2.0_table_structure_infer.tar --no-check-certificate
wget -nc -P ./inference/ https://paddleocr.bj.bcebos.com/dygraph_v2.0/table/en_ppocr_mobile_v2.0_table_det_infer.tar --no-check-certificate

37
tools/program.py
View File

@ -154,6 +154,24 @@ def check_xpu(use_xpu):
except Exception as e:
pass
def to_float32(preds):
if isinstance(preds, dict):
for k in preds:
if isinstance(preds[k], dict) or isinstance(preds[k], list):
preds[k] = to_float32(preds[k])
else:
preds[k] = preds[k].astype(paddle.float32)
elif isinstance(preds, list):
for k in range(len(preds)):
if isinstance(preds[k], dict):
preds[k] = to_float32(preds[k])
elif isinstance(preds[k], list):
preds[k] = to_float32(preds[k])
else:
preds[k] = preds[k].astype(paddle.float32)
else:
preds = preds.astype(paddle.float32)
return preds
def train(config,
train_dataloader,
@ -252,13 +270,19 @@ def train(config,
# use amp
if scaler:
with paddle.amp.auto_cast():
with paddle.amp.auto_cast(level='O2'):
if model_type == 'table' or extra_input:
preds = model(images, data=batch[1:])
elif model_type in ["kie", 'vqa']:
preds = model(batch)
else:
preds = model(images)
preds = to_float32(preds)
loss = loss_class(preds, batch)
avg_loss = loss['loss']
scaled_avg_loss = scaler.scale(avg_loss)
scaled_avg_loss.backward()
scaler.minimize(optimizer, scaled_avg_loss)
else:
if model_type == 'table' or extra_input:
preds = model(images, data=batch[1:])
@ -266,15 +290,8 @@ def train(config,
preds = model(batch)
else:
preds = model(images)
loss = loss_class(preds, batch)
avg_loss = loss['loss']
if scaler:
scaled_avg_loss = scaler.scale(avg_loss)
scaled_avg_loss.backward()
scaler.minimize(optimizer, scaled_avg_loss)
else:
loss = loss_class(preds, batch)
avg_loss = loss['loss']
avg_loss.backward()
optimizer.step()
optimizer.clear_grad()

1
tools/train.py
View File

@ -157,6 +157,7 @@ def main(config, device, logger, vdl_writer):
scaler = paddle.amp.GradScaler(
init_loss_scaling=scale_loss,
use_dynamic_loss_scaling=use_dynamic_loss_scaling)
model, optimizer = paddle.amp.decorate(models=model, optimizers=optimizer, level='O2', master_weight=True)
else:
scaler = None