Skip to content

GitLab

"vscode:/vscode.git/clone" did not exist on "61ddcb23616333eee8a098331e1837b957a7b874"
Unverified Commit bccba557 authored by Double_V's avatar Double_V Committed by GitHub
Browse files

Merge pull request #4739 from tink2123/add_rec_ctc_model 

add rec ctc model for tipc
parents 731a8406 ce873fa9
Show whitespace changes
Inline Side-by-side
Showing with 999 additions and 9 deletions
test_tipc/configs/ch_ppocr_mobile_v2.0_rec/train_infer_python.txt 0 → 100644
View file @ bccba557
===========================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:null
Global.epoch_num:lite_train_infer=2|whole_train_infer=300
Global.save_model_dir:./output/
Train.loader.batch_size_per_card:lite_train_infer=128|whole_train_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.pretrained_model:
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
##
infer_model:null
infer_export:tools/export_model.py -c configs/rec/rec_icdar15_train.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"
--use_gpu:True|False
--enable_mkldnn:True|False
--cpu_threads:1|6
--rec_batch_num:1|6
--use_tensorrt:True|False
--precision:fp32|fp16|int8
--rec_model_dir:
--image_dir:./inference/rec_inference
--save_log_path:./test/output/
--benchmark:True
null:null
test_tipc/configs/ch_ppocr_server_v2.0_rec/train_infer_python.txt 0 → 100644
View file @ bccba557
===========================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:null
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.pretrained_model:
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
##
infer_model:null
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 --rec_char_dict_path=./ppocr/utils/ic15_dict.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:True|False
--precision:fp32|fp16|int8
--rec_model_dir:
--image_dir:./inference/rec_inference
--save_log_path:./test/output/
--benchmark:True
null:null
test_tipc/configs/rec_mv3_none_bilstm_ctc_v2.0/rec_icdar15_train.yml 0 → 100644
View file @ bccba557
Global:
use_gpu: True
epoch_num: 72
log_smooth_window: 20
print_batch_step: 10
save_model_dir: ./output/rec/mv3_none_bilstm_ctc/
save_epoch_step: 3
# evaluation is run every 2000 iterations
eval_batch_step: [0, 2000]
cal_metric_during_train: True
pretrained_model:
checkpoints:
save_inference_dir:
use_visualdl: False
infer_img: doc/imgs_words_en/word_10.png
# for data or label process
character_dict_path:
max_text_length: 25
infer_mode: False
use_space_char: False
save_res_path: ./output/rec/predicts_mv3_none_bilstm_ctc.txt
Optimizer:
name: Adam
beta1: 0.9
beta2: 0.999
lr:
learning_rate: 0.0005
regularizer:
name: 'L2'
factor: 0
Architecture:
model_type: rec
algorithm: CRNN
Transform:
Backbone:
name: MobileNetV3
scale: 0.5
model_name: large
Neck:
name: SequenceEncoder
encoder_type: rnn
hidden_size: 96
Head:
name: CTCHead
fc_decay: 0
Loss:
name: CTCLoss
PostProcess:
name: CTCLabelDecode
Metric:
name: RecMetric
main_indicator: acc
Train:
dataset:
name: SimpleDataSet
data_dir: ./train_data/ic15_data/
label_file_list: ["./train_data/ic15_data/rec_gt_train.txt"]
transforms:
- DecodeImage: # load image
img_mode: BGR
channel_first: False
- CTCLabelEncode: # Class handling label
- RecResizeImg:
image_shape: [3, 32, 100]
- KeepKeys:
keep_keys: ['image', 'label', 'length'] # dataloader will return list in this order
loader:
shuffle: False
batch_size_per_card: 256
drop_last: True
num_workers: 8
Eval:
dataset:
name: SimpleDataSet
data_dir: ./train_data/ic15_data
label_file_list: ["./train_data/ic15_data/rec_gt_test.txt"]
transforms:
- DecodeImage: # load image
img_mode: BGR
channel_first: False
- CTCLabelEncode: # Class handling label
- RecResizeImg:
image_shape: [3, 32, 100]
- KeepKeys:
keep_keys: ['image', 'label', 'length'] # dataloader will return list in this order
loader:
shuffle: False
drop_last: False
batch_size_per_card: 256
num_workers: 4
test_tipc/configs/rec_mv3_none_bilstm_ctc_v2.0/train_infer_python.txt 0 → 100644
View file @ bccba557
===========================train_params===========================
model_name:rec_mv3_none_bilstm_ctc_v2.0
python:python3.7
gpu_list:0|0,1
Global.use_gpu:True|True
Global.auto_cast:null
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/rec_mv3_none_bilstm_ctc_v2.0/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/rec_mv3_none_bilstm_ctc_v2.0/rec_icdar15_train.yml -o
null:null
##
===========================infer_params===========================
Global.save_inference_dir:./output/
Global.pretrained_model:
norm_export:tools/export_model.py -c test_tipc/configs/rec_mv3_none_bilstm_ctc_v2.0/rec_icdar15_train.yml -o
quant_export:null
fpgm_export:null
distill_export:null
export1:null
export2:null
##
infer_model:null
infer_export:tools/export_model.py -c test_tipc/configs/rec_mv3_none_bilstm_ctc_v2.0/rec_icdar15_train.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"
--use_gpu:True|False
--enable_mkldnn:True|False
--cpu_threads:1|6
--rec_batch_num:1|6
--use_tensorrt:True|False
--precision:fp32|fp16|int8
--rec_model_dir:
--image_dir:./inference/rec_inference
--save_log_path:./test/output/
--benchmark:True
null:null
test_tipc/configs/rec_mv3_none_none_ctc_v2.0/rec_icdar15_train.yml 0 → 100644
View file @ bccba557
Global:
use_gpu: True
epoch_num: 72
log_smooth_window: 20
print_batch_step: 10
save_model_dir: ./output/rec/mv3_none_none_ctc/
save_epoch_step: 3
# evaluation is run every 2000 iterations
eval_batch_step: [0, 2000]
cal_metric_during_train: True
pretrained_model:
checkpoints:
save_inference_dir:
use_visualdl: False
infer_img: doc/imgs_words_en/word_10.png
# for data or label process
character_dict_path:
max_text_length: 25
infer_mode: False
use_space_char: False
save_res_path: ./output/rec/predicts_mv3_none_none_ctc.txt
Optimizer:
name: Adam
beta1: 0.9
beta2: 0.999
lr:
learning_rate: 0.0005
regularizer:
name: 'L2'
factor: 0
Architecture:
model_type: rec
algorithm: Rosetta
Transform:
Backbone:
name: MobileNetV3
scale: 0.5
model_name: large
Neck:
name: SequenceEncoder
encoder_type: reshape
Head:
name: CTCHead
fc_decay: 0.0004
Loss:
name: CTCLoss
PostProcess:
name: CTCLabelDecode
Metric:
name: RecMetric
main_indicator: acc
Train:
dataset:
name: SimpleDataSet
data_dir: ./train_data/ic15_data/
label_file_list: ["./train_data/ic15_data/rec_gt_train.txt"]
transforms:
- DecodeImage: # load image
img_mode: BGR
channel_first: False
- CTCLabelEncode: # Class handling label
- RecResizeImg:
image_shape: [3, 32, 100]
- KeepKeys:
keep_keys: ['image', 'label', 'length'] # dataloader will return list in this order
loader:
shuffle: False
batch_size_per_card: 256
drop_last: True
num_workers: 8
Eval:
dataset:
name: SimpleDataSet
data_dir: ./train_data/ic15_data
label_file_list: ["./train_data/ic15_data/rec_gt_test.txt"]
transforms:
- DecodeImage: # load image
img_mode: BGR
channel_first: False
- CTCLabelEncode: # Class handling label
- RecResizeImg:
image_shape: [3, 32, 100]
- KeepKeys:
keep_keys: ['image', 'label', 'length'] # dataloader will return list in this order
loader:
shuffle: False
drop_last: False
batch_size_per_card: 256
num_workers: 8
test_tipc/configs/rec_mv3_none_none_ctc_v2.0/train_infer_python.txt 0 → 100644
View file @ bccba557
===========================train_params===========================
model_name:rec_mv3_none_none_ctc_v2.0
python:python3.7
gpu_list:0|0,1
Global.use_gpu:True|True
Global.auto_cast:null
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/rec_mv3_none_none_ctc_v2.0/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/rec_mv3_none_none_ctc_v2.0/rec_icdar15_train.yml -o
null:null
##
===========================infer_params===========================
Global.save_inference_dir:./output/
Global.pretrained_model:
norm_export:tools/export_model.py -c test_tipc/configs/rec_mv3_none_none_ctc_v2.0/rec_icdar15_train.yml -o
quant_export:null
fpgm_export:null
distill_export:null
export1:null
export2:null
##
infer_model:null
infer_export:tools/export_model.py -c test_tipc/configs/rec_mv3_none_none_ctc_v2.0/rec_icdar15_train.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"
--use_gpu:True|False
--enable_mkldnn:True|False
--cpu_threads:1|6
--rec_batch_num:1|6
--use_tensorrt:True|False
--precision:fp32|fp16|int8
--rec_model_dir:
--image_dir:./inference/rec_inference
--save_log_path:./test/output/
--benchmark:True
null:null
test_tipc/configs/rec_mv3_tps_bilstm_ctc_v2.0/rec_icdar15_train.yml 0 → 100644
View file @ bccba557
Global:
use_gpu: True
epoch_num: 72
log_smooth_window: 20
print_batch_step: 10
save_model_dir: ./output/rec/mv3_tps_bilstm_ctc/
save_epoch_step: 3
# evaluation is run every 2000 iterations
eval_batch_step: [0, 2000]
cal_metric_during_train: True
pretrained_model:
checkpoints:
save_inference_dir:
use_visualdl: False
infer_img: doc/imgs_words_en/word_10.png
# for data or label process
character_dict_path:
max_text_length: 25
infer_mode: False
use_space_char: False
save_res_path: ./output/rec/predicts_mv3_tps_bilstm_ctc.txt
Optimizer:
name: Adam
beta1: 0.9
beta2: 0.999
lr:
learning_rate: 0.0005
regularizer:
name: 'L2'
factor: 0
Architecture:
model_type: rec
algorithm: STARNet
Transform:
name: TPS
num_fiducial: 20
loc_lr: 0.1
model_name: small
Backbone:
name: MobileNetV3
scale: 0.5
model_name: large
Neck:
name: SequenceEncoder
encoder_type: rnn
hidden_size: 96
Head:
name: CTCHead
fc_decay: 0.0004
Loss:
name: CTCLoss
PostProcess:
name: CTCLabelDecode
Metric:
name: RecMetric
main_indicator: acc
Train:
dataset:
name: SimpleDataSet
data_dir: ./train_data/ic15_data/
label_file_list: ["./train_data/ic15_data/rec_gt_train.txt"]
transforms:
- DecodeImage: # load image
img_mode: BGR
channel_first: False
- CTCLabelEncode: # Class handling label
- RecResizeImg:
image_shape: [3, 32, 100]
- KeepKeys:
keep_keys: ['image', 'label', 'length'] # dataloader will return list in this order
loader:
shuffle: False
batch_size_per_card: 256
drop_last: True
num_workers: 8
Eval:
dataset:
name: SimpleDataSet
data_dir: ./train_data/ic15_data
label_file_list: ["./train_data/ic15_data/rec_gt_test.txt"]
transforms:
- DecodeImage: # load image
img_mode: BGR
channel_first: False
- CTCLabelEncode: # Class handling label
- RecResizeImg:
image_shape: [3, 32, 100]
- KeepKeys:
keep_keys: ['image', 'label', 'length'] # dataloader will return list in this order
loader:
shuffle: False
drop_last: False
batch_size_per_card: 256
num_workers: 4
test_tipc/configs/rec_mv3_tps_bilstm_ctc_v2.0/train_infer_python.txt 0 → 100644
View file @ bccba557
===========================train_params===========================
model_name:rec_mv3_tps_bilstm_ctc_v2.0
python:python3.7
gpu_list:0|0,1
Global.use_gpu:True|True
Global.auto_cast:null
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/rec_mv3_tps_bilstm_ctc_v2.0/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/rec_mv3_tps_bilstm_ctc_v2.0/rec_icdar15_train.yml -o
null:null
##
===========================infer_params===========================
Global.save_inference_dir:./output/
Global.pretrained_model:
norm_export:tools/export_model.py -c test_tipc/configs/rec_mv3_tps_bilstm_ctc_v2.0/rec_icdar15_train.yml -o
quant_export:null
fpgm_export:null
distill_export:null
export1:null
export2:null
##
infer_model:null
infer_export:tools/export_model.py -c test_tipc/configs/rec_mv3_tps_bilstm_ctc_v2.0/rec_icdar15_train.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"
--use_gpu:True|False
--enable_mkldnn:True|False
--cpu_threads:1|6
--rec_batch_num:1|6
--use_tensorrt:True|False
--precision:fp32|fp16|int8
--rec_model_dir:
--image_dir:./inference/rec_inference
--save_log_path:./test/output/
--benchmark:True
null:null
test_tipc/configs/rec_r34_vd_none_bilstm_ctc_v2.0/rec_icdar15_train.yml 0 → 100644
View file @ bccba557
Global:
use_gpu: true
epoch_num: 72
log_smooth_window: 20
print_batch_step: 10
save_model_dir: ./output/rec/r34_vd_none_bilstm_ctc/
save_epoch_step: 3
# evaluation is run every 2000 iterations
eval_batch_step: [0, 2000]
cal_metric_during_train: True
pretrained_model:
checkpoints:
save_inference_dir:
use_visualdl: False
infer_img: doc/imgs_words_en/word_10.png
# for data or label process
character_dict_path:
max_text_length: 25
infer_mode: False
use_space_char: False
save_res_path: ./output/rec/predicts_r34_vd_none_bilstm_ctc.txt
Optimizer:
name: Adam
beta1: 0.9
beta2: 0.999
lr:
learning_rate: 0.0005
regularizer:
name: 'L2'
factor: 0
Architecture:
model_type: rec
algorithm: CRNN
Transform:
Backbone:
name: ResNet
layers: 34
Neck:
name: SequenceEncoder
encoder_type: rnn
hidden_size: 256
Head:
name: CTCHead
fc_decay: 0
Loss:
name: CTCLoss
PostProcess:
name: CTCLabelDecode
Metric:
name: RecMetric
main_indicator: acc
Train:
dataset:
name: SimpleDataSet
data_dir: ./train_data/ic15_data/
label_file_list: ["./train_data/ic15_data/rec_gt_train.txt"]
transforms:
- DecodeImage: # load image
img_mode: BGR
channel_first: False
- CTCLabelEncode: # Class handling label
- RecResizeImg:
image_shape: [3, 32, 100]
- KeepKeys:
keep_keys: ['image', 'label', 'length'] # dataloader will return list in this order
loader:
shuffle: True
batch_size_per_card: 256
drop_last: True
num_workers: 8
Eval:
dataset:
name: SimpleDataSet
data_dir: ./train_data/ic15_data
label_file_list: ["./train_data/ic15_data/rec_gt_test.txt"]
transforms:
- DecodeImage: # load image
img_mode: BGR
channel_first: False
- CTCLabelEncode: # Class handling label
- RecResizeImg:
image_shape: [3, 32, 100]
- KeepKeys:
keep_keys: ['image', 'label', 'length'] # dataloader will return list in this order
loader:
shuffle: False
drop_last: False
batch_size_per_card: 256
num_workers: 4
test_tipc/configs/rec_r34_vd_none_bilstm_ctc_v2.0/train_infer_python.txt 0 → 100644
View file @ bccba557
===========================train_params===========================
model_name:rec_r34_vd_none_bilstm_ctc_v2.0
python:python3.7
gpu_list:0|0,1
Global.use_gpu:True|True
Global.auto_cast:null
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/rec_r34_vd_none_bilstm_ctc_v2.0/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/rec_r34_vd_none_bilstm_ctc_v2.0/rec_icdar15_train.yml -o
null:null
##
===========================infer_params===========================
Global.save_inference_dir:./output/
Global.pretrained_model:
norm_export:tools/export_model.py -c test_tipc/configs/rec_r34_vd_none_bilstm_ctc_v2.0/rec_icdar15_train.yml -o
quant_export:null
fpgm_export:null
distill_export:null
export1:null
export2:null
##
infer_model:null
infer_export:tools/export_model.py -c test_tipc/configs/rec_r34_vd_none_bilstm_ctc_v2.0/rec_icdar15_train.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"
--use_gpu:True|False
--enable_mkldnn:True|False
--cpu_threads:1|6
--rec_batch_num:1|6
--use_tensorrt:True|False
--precision:fp32|fp16|int8
--rec_model_dir:
--image_dir:./inference/rec_inference
--save_log_path:./test/output/
--benchmark:True
null:null
test_tipc/configs/rec_r34_vd_none_none_ctc_v2.0/rec_icdar15_train.yml 0 → 100644
View file @ bccba557
Global:
use_gpu: true
epoch_num: 72
log_smooth_window: 20
print_batch_step: 10
save_model_dir: ./output/rec/r34_vd_none_none_ctc/
save_epoch_step: 3
# evaluation is run every 2000 iterations
eval_batch_step: [0, 2000]
cal_metric_during_train: True
pretrained_model:
checkpoints:
save_inference_dir:
use_visualdl: False
infer_img: doc/imgs_words_en/word_10.png
# for data or label process
character_dict_path:
max_text_length: 25
infer_mode: False
use_space_char: False
save_res_path: ./output/rec/predicts_r34_vd_none_none_ctc.txt
Optimizer:
name: Adam
beta1: 0.9
beta2: 0.999
lr:
learning_rate: 0.0005
regularizer:
name: 'L2'
factor: 0
Architecture:
model_type: rec
algorithm: Rosetta
Backbone:
name: ResNet
layers: 34
Neck:
name: SequenceEncoder
encoder_type: reshape
Head:
name: CTCHead
fc_decay: 0.0004
Loss:
name: CTCLoss
PostProcess:
name: CTCLabelDecode
Metric:
name: RecMetric
main_indicator: acc
Train:
dataset:
name: SimpleDataSet
data_dir: ./train_data/ic15_data/
label_file_list: ["./train_data/ic15_data/rec_gt_train.txt"]
transforms:
- DecodeImage: # load image
img_mode: BGR
channel_first: False
- CTCLabelEncode: # Class handling label
- RecResizeImg:
image_shape: [3, 32, 100]
- KeepKeys:
keep_keys: ['image', 'label', 'length'] # dataloader will return list in this order
loader:
shuffle: True
batch_size_per_card: 256
drop_last: True
num_workers: 8
Eval:
dataset:
name: SimpleDataSet
data_dir: ./train_data/ic15_data
label_file_list: ["./train_data/ic15_data/rec_gt_test.txt"]
transforms:
- DecodeImage: # load image
img_mode: BGR
channel_first: False
- CTCLabelEncode: # Class handling label
- RecResizeImg:
image_shape: [3, 32, 100]
- KeepKeys:
keep_keys: ['image', 'label', 'length'] # dataloader will return list in this order
loader:
shuffle: False
drop_last: False
batch_size_per_card: 256
num_workers: 4
test_tipc/configs/rec_r34_vd_none_none_ctc_v2.0/train_infer_python.txt 0 → 100644
View file @ bccba557
===========================train_params===========================
model_name:rec_r34_vd_none_none_ctc_v2.0
python:python3.7
gpu_list:0|0,1
Global.use_gpu:True|True
Global.auto_cast:null
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/rec_r34_vd_none_none_ctc_v2.0/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/rec_r34_vd_none_none_ctc_v2.0/rec_icdar15_train.yml -o
null:null
##
===========================infer_params===========================
Global.save_inference_dir:./output/
Global.pretrained_model:
norm_export:tools/export_model.py -c test_tipc/configs/rec_r34_vd_none_none_ctc_v2.0/rec_icdar15_train.yml -o
quant_export:null
fpgm_export:null
distill_export:null
export1:null
export2:null
##
infer_model:null
infer_export:tools/export_model.py -c test_tipc/configs/rec_r34_vd_none_none_ctc_v2.0/rec_icdar15_train.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"
--use_gpu:True|False
--enable_mkldnn:True|False
--cpu_threads:1|6
--rec_batch_num:1|6
--use_tensorrt:True|False
--precision:fp32|fp16|int8
--rec_model_dir:
--image_dir:./inference/rec_inference
--save_log_path:./test/output/
--benchmark:True
null:null
test_tipc/configs/rec_r34_vd_tps_bilstm_ctc_v2.0/rec_icdar15_train.yml 0 → 100644
View file @ bccba557
Global:
use_gpu: true
epoch_num: 72
log_smooth_window: 20
print_batch_step: 10
save_model_dir: ./output/rec/r34_vd_tps_bilstm_ctc/
save_epoch_step: 3
# evaluation is run every 2000 iterations
eval_batch_step: [0, 2000]
cal_metric_during_train: True
pretrained_model:
checkpoints:
save_inference_dir:
use_visualdl: False
infer_img: doc/imgs_words_en/word_10.png
# for data or label process
character_dict_path:
max_text_length: 25
infer_mode: False
use_space_char: False
save_res_path: ./output/rec/predicts_r34_vd_tps_bilstm_ctc.txt
Optimizer:
name: Adam
beta1: 0.9
beta2: 0.999
lr:
learning_rate: 0.0005
regularizer:
name: 'L2'
factor: 0
Architecture:
model_type: rec
algorithm: STARNet
Transform:
name: TPS
num_fiducial: 20
loc_lr: 0.1
model_name: large
Backbone:
name: ResNet
layers: 34
Neck:
name: SequenceEncoder
encoder_type: rnn
hidden_size: 256
Head:
name: CTCHead
fc_decay: 0
Loss:
name: CTCLoss
PostProcess:
name: CTCLabelDecode
Metric:
name: RecMetric
main_indicator: acc
Train:
dataset:
name: SimpleDataSet
data_dir: ./train_data/ic15_data/
label_file_list: ["./train_data/ic15_data/rec_gt_train.txt"]
transforms:
- DecodeImage: # load image
img_mode: BGR
channel_first: False
- CTCLabelEncode: # Class handling label
- RecResizeImg:
image_shape: [3, 32, 100]
- KeepKeys:
keep_keys: ['image', 'label', 'length'] # dataloader will return list in this order
loader:
shuffle: True
batch_size_per_card: 256
drop_last: True
num_workers: 8
Eval:
dataset:
name: SimpleDataSet
data_dir: ./train_data/ic15_data
label_file_list: ["./train_data/ic15_data/rec_gt_test.txt"]
transforms:
- DecodeImage: # load image
img_mode: BGR
channel_first: False
- CTCLabelEncode: # Class handling label
- RecResizeImg:
image_shape: [3, 32, 100]
- KeepKeys:
keep_keys: ['image', 'label', 'length'] # dataloader will return list in this order
loader:
shuffle: False
drop_last: False
batch_size_per_card: 256
num_workers: 4
test_tipc/configs/rec_r34_vd_tps_bilstm_ctc_v2.0/train_infer_python.txt 0 → 100644
View file @ bccba557
===========================train_params===========================
model_name:rec_r34_vd_tps_bilstm_ctc_v2.0
python:python3.7
gpu_list:0|0,1
Global.use_gpu:True|True
Global.auto_cast:null
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/rec_r34_vd_tps_bilstm_ctc_v2.0/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/rec_r34_vd_tps_bilstm_ctc_v2.0/rec_icdar15_train.yml -o
null:null
##
===========================infer_params===========================
Global.save_inference_dir:./output/
Global.pretrained_model:
norm_export:tools/export_model.py -c test_tipc/configs/rec_r34_vd_tps_bilstm_ctc_v2.0/rec_icdar15_train.yml -o
quant_export:null
fpgm_export:null
distill_export:null
export1:null
export2:null
##
infer_model:null
infer_export:tools/export_model.py -c test_tipc/configs/rec_r34_vd_tps_bilstm_ctc_v2.0/rec_icdar15_train.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"
--use_gpu:True|False
--enable_mkldnn:True|False
--cpu_threads:1|6
--rec_batch_num:1|6
--use_tensorrt:True|False
--precision:fp32|fp16|int8
--rec_model_dir:
--image_dir:./inference/rec_inference
--save_log_path:./test/output/
--benchmark:True
null:null
test_tipc/prepare.sh
View file @ bccba557
......@@ -111,14 +111,12 @@ elif [ ${MODE} = "whole_infer" ];then
wget -nc -P ./inference https://paddleocr.bj.bcebos.com/dygraph_v2.0/test/ch_det_data_50.tar --no-check-certificate
wget -nc -P ./inference https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_server_v2.0_rec_infer.tar --no-check-certificate
cd ./inference && tar xf ch_ppocr_server_v2.0_det_infer.tar && tar xf ch_ppocr_server_v2.0_rec_infer.tar && tar xf ch_det_data_50.tar && cd ../
elif [ ${model_name} = "ocr_rec" ]; then
rm -rf ./train_data/ic15_data
elif [ ${model_name} = "ch_ppocr_mobile_v2.0_rec" ]; then
eval_model_name="ch_ppocr_mobile_v2.0_rec_infer"
wget -nc -P ./inference/ https://paddleocr.bj.bcebos.com/dygraph_v2.0/test/rec_inference.tar --no-check-certificate
wget -nc -P ./inference https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_mobile_v2.0_rec_infer.tar --no-check-certificate
cd ./inference && tar xf ${eval_model_name}.tar && tar xf rec_inference.tar && cd ../
elif [ ${model_name} = "ocr_server_rec" ]; then
rm -rf ./train_data/ic15_data
elif [ ${model_name} = "ch_ppocr_server_v2.0_rec" ]; then
eval_model_name="ch_ppocr_server_v2.0_rec_infer"
wget -nc -P ./inference/ https://paddleocr.bj.bcebos.com/dygraph_v2.0/test/rec_inference.tar --no-check-certificate
wget -nc -P ./inference https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_server_v2.0_rec_infer.tar --no-check-certificate
......@@ -163,7 +161,7 @@ if [ ${MODE} = "cpp_infer" ];then
wget -nc -P ./inference https://paddleocr.bj.bcebos.com/dygraph_v2.0/test/ch_det_data_50.tar --no-check-certificate
wget -nc -P ./inference https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_mobile_v2.0_det_infer.tar --no-check-certificate
cd ./inference && tar xf ch_ppocr_mobile_v2.0_det_infer.tar && tar xf ch_det_data_50.tar && cd ../
elif [ ${model_name} = "ocr_rec" ]; then
elif [ ${model_name} = "ch_ppocr_mobile_v2.0_rec" ]; then
wget -nc -P ./inference/ https://paddleocr.bj.bcebos.com/dygraph_v2.0/test/rec_inference.tar --no-check-certificate
wget -nc -P ./inference https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_mobile_v2.0_rec_infer.tar --no-check-certificate
cd ./inference && tar xf ch_ppocr_mobile_v2.0_rec_infer.tar && tar xf rec_inference.tar && cd ../
......
test_tipc/test_train_inference_python.sh
View file @ bccba557
......@@ -336,7 +336,7 @@ else
set_eval_pretrain=$(func_set_params "${pretrain_model_key}" "${save_log}/${train_model_name}")
# save norm trained models to set pretrain for pact training and fpgm training
if [ ${trainer} = ${trainer_norm} ] && [ ${nodes} -le 1]; then
if [ ${trainer} = ${trainer_norm} ] && [ ${nodes} -le 1 ]; then
load_norm_train_model=${set_eval_pretrain}
fi
# run eval
......@@ -359,7 +359,7 @@ else
#run inference
eval $env
save_infer_path="${save_log}"
if [ ${inference_dir} != "null" ] && [ ${inference_dir} != '##' ]; then
if [[ ${inference_dir} != "null" ]] && [[ ${inference_dir} != '##' ]]; then
infer_model_dir="${save_infer_path}/${inference_dir}"
else
infer_model_dir=${save_infer_path}
......
tools/infer/predict_rec.py
View file @ bccba557
......@@ -91,7 +91,7 @@ class TextRecognizer(object):
time_keys=[
'preprocess_time', 'inference_time', 'postprocess_time'
],
warmup=2,
warmup=0,
logger=logger)
def resize_norm_img(self, img, max_wh_ratio):
......
Markdown is supported
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment