Merge branch 'dygraph' of https://github.com/PaddlePaddle/PaddleOCR into dyg_db
LDOUBLEV
4 years ago
commit
2735e9e3c9
File diff suppressed because it is too large
Load Diff
@ -1,130 +0,0 @@
|
||||
Global:
|
||||
use_gpu: true
|
||||
epoch_num: 1200
|
||||
log_smooth_window: 20
|
||||
print_batch_step: 2
|
||||
save_model_dir: ./output/det_r50_vd/
|
||||
save_epoch_step: 1200
|
||||
# evaluation is run every 5000 iterations after the 4000th iteration
|
||||
eval_batch_step: 8
|
||||
# if pretrained_model is saved in static mode, load_static_weights must set to True
|
||||
load_static_weights: True
|
||||
cal_metric_during_train: False
|
||||
pretrained_model: ./pretrain_models/ResNet50_vd_ssld_pretrained/
|
||||
checkpoints:
|
||||
save_inference_dir:
|
||||
use_visualdl: True
|
||||
infer_img: doc/imgs_en/img_10.jpg
|
||||
save_res_path: ./output/det_db/predicts_db.txt
|
||||
|
||||
Optimizer:
|
||||
name: Adam
|
||||
beta1: 0.9
|
||||
beta2: 0.999
|
||||
learning_rate:
|
||||
lr: 0.001
|
||||
regularizer:
|
||||
name: 'L2'
|
||||
factor: 0
|
||||
|
||||
Architecture:
|
||||
type: det
|
||||
algorithm: DB
|
||||
Transform:
|
||||
Backbone:
|
||||
name: ResNet
|
||||
layers: 50
|
||||
Neck:
|
||||
name: FPN
|
||||
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
|
||||
|
||||
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: ./detection/
|
||||
file_list:
|
||||
- ./detection/train_icdar2015_label.txt # dataset1
|
||||
ratio_list: [1.0]
|
||||
transforms:
|
||||
- DecodeImage: # load image
|
||||
img_mode: BGR
|
||||
channel_first: False
|
||||
- DetLabelEncode: # Class handling label
|
||||
- IaaAugment:
|
||||
augmenter_args:
|
||||
- { 'type': Fliplr, 'args': { 'p': 0.5 } }
|
||||
- { 'type': Affine, 'args': { 'rotate': [ -10,10 ] } }
|
||||
- { 'type': Resize,'args': { 'size': [ 0.5,3 ] } }
|
||||
- EastRandomCropData:
|
||||
size: [ 640,640 ]
|
||||
max_tries: 50
|
||||
keep_ratio: true
|
||||
- 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'] # dataloader will return list in this order
|
||||
loader:
|
||||
shuffle: True
|
||||
drop_last: False
|
||||
batch_size: 16
|
||||
num_workers: 8
|
||||
|
||||
EVAL:
|
||||
dataset:
|
||||
name: SimpleDataSet
|
||||
data_dir: ./detection/
|
||||
file_list:
|
||||
- ./detection/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: 1 # must be 1
|
||||
num_workers: 8
|
||||
@ -1,106 +0,0 @@
|
||||
Global:
|
||||
use_gpu: false
|
||||
epoch_num: 500
|
||||
log_smooth_window: 20
|
||||
print_batch_step: 10
|
||||
save_model_dir: ./output/rec/mv3_none_bilstm_ctc/
|
||||
save_epoch_step: 500
|
||||
# evaluation is run every 5000 iterations after the 4000th iteration
|
||||
eval_batch_step: 127
|
||||
# if pretrained_model is saved in static mode, load_static_weights must set to True
|
||||
load_static_weights: True
|
||||
cal_metric_during_train: True
|
||||
pretrained_model:
|
||||
checkpoints:
|
||||
save_inference_dir:
|
||||
use_visualdl: False
|
||||
infer_img: doc/imgs_words/ch/word_1.jpg
|
||||
# for data or label process
|
||||
max_text_length: 80
|
||||
character_dict_path: ppocr/utils/ppocr_keys_v1.txt
|
||||
character_type: 'ch'
|
||||
use_space_char: False
|
||||
infer_mode: False
|
||||
use_tps: False
|
||||
|
||||
|
||||
Optimizer:
|
||||
name: Adam
|
||||
beta1: 0.9
|
||||
beta2: 0.999
|
||||
learning_rate:
|
||||
lr: 0.001
|
||||
regularizer:
|
||||
name: 'L2'
|
||||
factor: 0.00001
|
||||
|
||||
Architecture:
|
||||
type: rec
|
||||
algorithm: CRNN
|
||||
Transform:
|
||||
Backbone:
|
||||
name: MobileNetV3
|
||||
scale: 0.5
|
||||
model_name: small
|
||||
small_stride: [ 1, 2, 2, 2 ]
|
||||
Neck:
|
||||
name: SequenceEncoder
|
||||
encoder_type: fc
|
||||
hidden_size: 96
|
||||
Head:
|
||||
name: CTC
|
||||
fc_decay: 0.00001
|
||||
|
||||
Loss:
|
||||
name: CTCLoss
|
||||
|
||||
PostProcess:
|
||||
name: CTCLabelDecode
|
||||
|
||||
Metric:
|
||||
name: RecMetric
|
||||
main_indicator: acc
|
||||
|
||||
TRAIN:
|
||||
dataset:
|
||||
name: SimpleDataSet
|
||||
data_dir: ./rec
|
||||
file_list:
|
||||
- ./rec/train.txt # dataset1
|
||||
ratio_list: [ 0.4,0.6 ]
|
||||
transforms:
|
||||
- DecodeImage: # load image
|
||||
img_mode: BGR
|
||||
channel_first: False
|
||||
- CTCLabelEncode: # Class handling label
|
||||
- RecAug:
|
||||
- RecResizeImg:
|
||||
image_shape: [ 3,32,320 ]
|
||||
- keepKeys:
|
||||
keep_keys: [ 'image','label','length' ] # dataloader will return list in this order
|
||||
loader:
|
||||
batch_size: 256
|
||||
shuffle: True
|
||||
drop_last: True
|
||||
num_workers: 8
|
||||
|
||||
EVAL:
|
||||
dataset:
|
||||
name: SimpleDataSet
|
||||
data_dir: ./rec
|
||||
file_list:
|
||||
- ./rec/val.txt
|
||||
transforms:
|
||||
- DecodeImage: # load image
|
||||
img_mode: BGR
|
||||
channel_first: False
|
||||
- CTCLabelEncode: # Class handling label
|
||||
- RecResizeImg:
|
||||
image_shape: [ 3,32,320 ]
|
||||
- keepKeys:
|
||||
keep_keys: [ 'image','label','length' ] # dataloader will return list in this order
|
||||
loader:
|
||||
shuffle: False
|
||||
drop_last: False
|
||||
batch_size: 256
|
||||
num_workers: 8
|
||||
@ -1,104 +0,0 @@
|
||||
Global:
|
||||
use_gpu: false
|
||||
epoch_num: 500
|
||||
log_smooth_window: 20
|
||||
print_batch_step: 10
|
||||
save_model_dir: ./output/rec/res34_none_bilstm_ctc/
|
||||
save_epoch_step: 500
|
||||
# evaluation is run every 5000 iterations after the 4000th iteration
|
||||
eval_batch_step: 127
|
||||
# if pretrained_model is saved in static mode, load_static_weights must set to True
|
||||
load_static_weights: True
|
||||
cal_metric_during_train: True
|
||||
pretrained_model:
|
||||
checkpoints:
|
||||
save_inference_dir:
|
||||
use_visualdl: False
|
||||
infer_img: doc/imgs_words/ch/word_1.jpg
|
||||
# for data or label process
|
||||
max_text_length: 80
|
||||
character_dict_path: ppocr/utils/ppocr_keys_v1.txt
|
||||
character_type: 'ch'
|
||||
use_space_char: False
|
||||
infer_mode: False
|
||||
use_tps: False
|
||||
|
||||
|
||||
Optimizer:
|
||||
name: Adam
|
||||
beta1: 0.9
|
||||
beta2: 0.999
|
||||
learning_rate:
|
||||
lr: 0.001
|
||||
regularizer:
|
||||
name: 'L2'
|
||||
factor: 0.00001
|
||||
|
||||
Architecture:
|
||||
type: rec
|
||||
algorithm: CRNN
|
||||
Transform:
|
||||
Backbone:
|
||||
name: ResNet
|
||||
layers: 34
|
||||
Neck:
|
||||
name: SequenceEncoder
|
||||
encoder_type: fc
|
||||
hidden_size: 96
|
||||
Head:
|
||||
name: CTC
|
||||
fc_decay: 0.00001
|
||||
|
||||
Loss:
|
||||
name: CTCLoss
|
||||
|
||||
PostProcess:
|
||||
name: CTCLabelDecode
|
||||
|
||||
Metric:
|
||||
name: RecMetric
|
||||
main_indicator: acc
|
||||
|
||||
TRAIN:
|
||||
dataset:
|
||||
name: SimpleDataSet
|
||||
data_dir: ./rec
|
||||
file_list:
|
||||
- ./rec/train.txt # dataset1
|
||||
ratio_list: [ 0.4,0.6 ]
|
||||
transforms:
|
||||
- DecodeImage: # load image
|
||||
img_mode: BGR
|
||||
channel_first: False
|
||||
- CTCLabelEncode: # Class handling label
|
||||
- RecAug:
|
||||
- RecResizeImg:
|
||||
image_shape: [ 3,32,320 ]
|
||||
- keepKeys:
|
||||
keep_keys: [ 'image','label','length' ] # dataloader will return list in this order
|
||||
loader:
|
||||
batch_size: 256
|
||||
shuffle: True
|
||||
drop_last: True
|
||||
num_workers: 8
|
||||
|
||||
EVAL:
|
||||
dataset:
|
||||
name: SimpleDataSet
|
||||
data_dir: ./rec
|
||||
file_list:
|
||||
- ./rec/val.txt
|
||||
transforms:
|
||||
- DecodeImage: # load image
|
||||
img_mode: BGR
|
||||
channel_first: False
|
||||
- CTCLabelEncode: # Class handling label
|
||||
- RecResizeImg:
|
||||
image_shape: [ 3,32,320 ]
|
||||
- keepKeys:
|
||||
keep_keys: [ 'image','label','length' ] # dataloader will return list in this order
|
||||
loader:
|
||||
shuffle: False
|
||||
drop_last: False
|
||||
batch_size: 256
|
||||
num_workers: 8
|
||||
Some files were not shown because too many files have changed in this diff Show More
Loading…
Reference in new issue