add pse config
This commit is contained in:
WenmuZhou
parent
a739abab57
commit
2e98890d94
|
|
@ -0,0 +1,135 @@
|
|||
Global:
|
||||
use_gpu: true
|
||||
epoch_num: 600
|
||||
log_smooth_window: 20
|
||||
print_batch_step: 10
|
||||
save_model_dir: ./output/det_mv3_pse/
|
||||
save_epoch_step: 600
|
||||
# evaluation is run every 63 iterations
|
||||
eval_batch_step: [ 0,63 ]
|
||||
cal_metric_during_train: False
|
||||
pretrained_model: ./pretrain_models/MobileNetV3_large_x0_5_pretrained
|
||||
checkpoints: #./output/det_r50_vd_pse_batch8_ColorJitter/best_accuracy
|
||||
save_inference_dir:
|
||||
use_visualdl: False
|
||||
infer_img: doc/imgs_en/img_10.jpg
|
||||
save_res_path: ./output/det_pse/predicts_pse.txt
|
||||
|
||||
Architecture:
|
||||
model_type: det
|
||||
algorithm: PSE
|
||||
Transform: null
|
||||
Backbone:
|
||||
name: MobileNetV3
|
||||
scale: 0.5
|
||||
model_name: large
|
||||
Neck:
|
||||
name: FPN
|
||||
out_channels: 96
|
||||
Head:
|
||||
name: PSEHead
|
||||
hidden_dim: 96
|
||||
out_channels: 7
|
||||
|
||||
Loss:
|
||||
name: PSELoss
|
||||
alpha: 0.7
|
||||
ohem_ratio: 3
|
||||
kernel_sample_mask: pred
|
||||
reduction: none
|
||||
|
||||
Optimizer:
|
||||
name: Adam
|
||||
beta1: 0.9
|
||||
beta2: 0.999
|
||||
lr:
|
||||
name: Step
|
||||
learning_rate: 0.001
|
||||
step_size: 200
|
||||
gamma: 0.1
|
||||
regularizer:
|
||||
name: 'L2'
|
||||
factor: 0.0005
|
||||
|
||||
PostProcess:
|
||||
name: PSEPostProcess
|
||||
thresh: 0
|
||||
box_thresh: 0.85
|
||||
min_area: 16
|
||||
box_type: box # 'box' or 'poly'
|
||||
scale: 1
|
||||
|
||||
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
|
||||
- ColorJitter:
|
||||
brightness: 0.12549019607843137
|
||||
saturation: 0.5
|
||||
- IaaAugment:
|
||||
augmenter_args:
|
||||
- { 'type': Resize, 'args': { 'size': [ 0.5, 3 ] } }
|
||||
- { 'type': Fliplr, 'args': { 'p': 0.5 } }
|
||||
- { 'type': Affine, 'args': { 'rotate': [ -10, 10 ] } }
|
||||
- MakePseGt:
|
||||
kernel_num: 7
|
||||
min_shrink_ratio: 0.4
|
||||
size: 640
|
||||
- RandomCropImgMask:
|
||||
size: [ 640,640 ]
|
||||
main_key: gt_text
|
||||
crop_keys: [ 'image', 'gt_text', 'gt_kernels', 'mask' ]
|
||||
- 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', 'gt_text', 'gt_kernels', 'mask' ] # the order of the dataloader list
|
||||
loader:
|
||||
shuffle: True
|
||||
drop_last: False
|
||||
batch_size_per_card: 16
|
||||
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
|
||||
ratio_list: [ 1.0 ]
|
||||
transforms:
|
||||
- DecodeImage: # load image
|
||||
img_mode: BGR
|
||||
channel_first: False
|
||||
- DetLabelEncode: # Class handling label
|
||||
- DetResizeForTest:
|
||||
limit_side_len: 736
|
||||
limit_type: min
|
||||
- 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: 8
|
||||
|
|
@ -4,16 +4,16 @@ Global:
|
|||
log_smooth_window: 20
|
||||
print_batch_step: 10
|
||||
save_model_dir: ./output/det_r50_vd_pse/
|
||||
save_epoch_step: 1200
|
||||
# evaluation is run every 2000 iterations
|
||||
eval_batch_step: [0,125]
|
||||
save_epoch_step: 600
|
||||
# evaluation is run every 125 iterations
|
||||
eval_batch_step: [ 0,125 ]
|
||||
cal_metric_during_train: False
|
||||
pretrained_model: /ssd1/zhoujun20/fuxian/ResNet50_vd_ssld_pretrained
|
||||
pretrained_model: ./pretrain_models/ResNet50_vd_ssld_pretrained
|
||||
checkpoints: #./output/det_r50_vd_pse_batch8_ColorJitter/best_accuracy
|
||||
save_inference_dir:
|
||||
use_visualdl: False
|
||||
infer_img: doc/imgs_en/img_10.jpg
|
||||
save_res_path: ./output/det_db/predicts_db.txt
|
||||
save_res_path: ./output/det_pse/predicts_pse.txt
|
||||
|
||||
Architecture:
|
||||
model_type: det
|
||||
|
|
@ -68,7 +68,7 @@ Train:
|
|||
data_dir: ./train_data/icdar2015/text_localization/
|
||||
label_file_list:
|
||||
- ./train_data/icdar2015/text_localization/train_icdar2015_label.txt
|
||||
ratio_list: [1.0]
|
||||
ratio_list: [ 1.0 ]
|
||||
transforms:
|
||||
- DecodeImage: # load image
|
||||
img_mode: BGR
|
||||
|
|
@ -81,23 +81,23 @@ Train:
|
|||
augmenter_args:
|
||||
- { 'type': Resize, 'args': { 'size': [ 0.5, 3 ] } }
|
||||
- { 'type': Fliplr, 'args': { 'p': 0.5 } }
|
||||
- { 'type': Affine, 'args': { 'rotate': [-10, 10] } }
|
||||
- { 'type': Affine, 'args': { 'rotate': [ -10, 10 ] } }
|
||||
- MakePseGt:
|
||||
kernel_num: 7
|
||||
min_shrink_ratio: 0.4
|
||||
size: 640
|
||||
- RandomCropImgMask:
|
||||
size: [640,640]
|
||||
size: [ 640,640 ]
|
||||
main_key: gt_text
|
||||
crop_keys: ['image', 'gt_text', 'gt_kernels', 'mask']
|
||||
crop_keys: [ 'image', 'gt_text', 'gt_kernels', 'mask' ]
|
||||
- NormalizeImage:
|
||||
scale: 1./255.
|
||||
mean: [0.485, 0.456, 0.406]
|
||||
std: [0.229, 0.224, 0.225]
|
||||
mean: [ 0.485, 0.456, 0.406 ]
|
||||
std: [ 0.229, 0.224, 0.225 ]
|
||||
order: 'hwc'
|
||||
- ToCHWImage:
|
||||
- KeepKeys:
|
||||
keep_keys: ['image', 'gt_text', 'gt_kernels', 'mask'] # the order of the dataloader list
|
||||
keep_keys: [ 'image', 'gt_text', 'gt_kernels', 'mask' ] # the order of the dataloader list
|
||||
loader:
|
||||
shuffle: True
|
||||
drop_last: False
|
||||
|
|
@ -119,15 +119,14 @@ Eval:
|
|||
- DetResizeForTest:
|
||||
limit_side_len: 736
|
||||
limit_type: min
|
||||
# resize_long: 2240
|
||||
- NormalizeImage:
|
||||
scale: 1./255.
|
||||
mean: [0.485, 0.456, 0.406]
|
||||
std: [0.229, 0.224, 0.225]
|
||||
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']
|
||||
keep_keys: [ 'image', 'shape', 'polys', 'ignore_tags' ]
|
||||
loader:
|
||||
shuffle: False
|
||||
drop_last: False
|
||||
|
|
|
|||
|
|
@ -9,11 +9,13 @@
|
|||
### 1.文本检测算法
|
||||
|
||||
PaddleOCR开源的文本检测算法列表：
|
||||
- [x] DB([paper]( https://arxiv.org/abs/1911.08947)) [2]（ppocr推荐）
|
||||
- [x] EAST([paper](https://arxiv.org/abs/1704.03155))[1]
|
||||
- [x] SAST([paper](https://arxiv.org/abs/1908.05498))[4]
|
||||
- [x] DB([paper]( https://arxiv.org/abs/1911.08947))（ppocr推荐）
|
||||
- [x] EAST([paper](https://arxiv.org/abs/1704.03155))
|
||||
- [x] SAST([paper](https://arxiv.org/abs/1908.05498))
|
||||
- [x] PSENet([paper](https://arxiv.org/abs/1903.12473v2)）
|
||||
|
||||
在ICDAR2015文本检测公开数据集上，算法效果如下：
|
||||
|
||||
|模型|骨干网络|precision|recall|Hmean|下载链接|
|
||||
| --- | --- | --- | --- | --- | --- |
|
||||
|EAST|ResNet50_vd|85.80%|86.71%|86.25%|[下载链接](https://paddleocr.bj.bcebos.com/dygraph_v2.0/en/det_r50_vd_east_v2.0_train.tar)|
|
||||
|
|
@ -21,6 +23,8 @@ PaddleOCR开源的文本检测算法列表：
|
|||
|DB|ResNet50_vd|86.41%|78.72%|82.38%|[下载链接](https://paddleocr.bj.bcebos.com/dygraph_v2.0/en/det_r50_vd_db_v2.0_train.tar)|
|
||||
|DB|MobileNetV3|77.29%|73.08%|75.12%|[下载链接](https://paddleocr.bj.bcebos.com/dygraph_v2.0/en/det_mv3_db_v2.0_train.tar)|
|
||||
|SAST|ResNet50_vd|91.39%|83.77%|87.42%|[下载链接](https://paddleocr.bj.bcebos.com/dygraph_v2.0/en/det_r50_vd_sast_icdar15_v2.0_train.tar)|
|
||||
|PSE|ResNet50_vd|85.81%|79.53%|82.55%|[下载链接](https://paddleocr.bj.bcebos.com/dygraph_v2.1/en_det/det_r50_vd_pse_v2.0_train.tar)|
|
||||
|PSE|MobileNetV3|82.20%|70.47%|75.89%|[下载链接](https://paddleocr.bj.bcebos.com/dygraph_v2.1/en_det/det_mv3_pse_v2.0_train.tar)|
|
||||
|
||||
在Total-text文本检测公开数据集上，算法效果如下：
|
||||
|
||||
|
|
@ -39,13 +43,13 @@ PaddleOCR文本检测算法的训练和使用请参考文档教程中[模型训
|
|||
### 2.文本识别算法
|
||||
|
||||
PaddleOCR基于动态图开源的文本识别算法列表：
|
||||
- [x] CRNN([paper](https://arxiv.org/abs/1507.05717))[7]（ppocr推荐）
|
||||
- [x] Rosetta([paper](https://arxiv.org/abs/1910.05085))[10]
|
||||
- [x] STAR-Net([paper](http://www.bmva.org/bmvc/2016/papers/paper043/index.html))[11]
|
||||
- [x] RARE([paper](https://arxiv.org/abs/1603.03915v1))[12]
|
||||
- [x] SRN([paper](https://arxiv.org/abs/2003.12294))[5]
|
||||
- [x] CRNN([paper](https://arxiv.org/abs/1507.05717))（ppocr推荐）
|
||||
- [x] Rosetta([paper](https://arxiv.org/abs/1910.05085))
|
||||
- [x] STAR-Net([paper](http://www.bmva.org/bmvc/2016/papers/paper043/index.html))
|
||||
- [x] RARE([paper](https://arxiv.org/abs/1603.03915v1))
|
||||
- [x] SRN([paper](https://arxiv.org/abs/2003.12294))
|
||||
|
||||
参考[DTRB][3](https://arxiv.org/abs/1904.01906)文字识别训练和评估流程，使用MJSynth和SynthText两个文字识别数据集训练，在IIIT, SVT, IC03, IC13, IC15, SVTP, CUTE数据集上进行评估，算法效果如下：
|
||||
参考[DTRB](https://arxiv.org/abs/1904.01906) 文字识别训练和评估流程，使用MJSynth和SynthText两个文字识别数据集训练，在IIIT, SVT, IC03, IC13, IC15, SVTP, CUTE数据集上进行评估，算法效果如下：
|
||||
|
||||
|模型|骨干网络|Avg Accuracy|模型存储命名|下载链接|
|
||||
|---|---|---|---|---|
|
||||
|
|
|
|||
|
|
@ -11,9 +11,10 @@ This tutorial lists the text detection algorithms and text recognition algorithm
|
|||
### 1. Text Detection Algorithm
|
||||
|
||||
PaddleOCR open source text detection algorithms list:
|
||||
- [x] EAST([paper](https://arxiv.org/abs/1704.03155))[2]
|
||||
- [x] DB([paper](https://arxiv.org/abs/1911.08947))[1]
|
||||
- [x] SAST([paper](https://arxiv.org/abs/1908.05498))[4]
|
||||
- [x] EAST([paper](https://arxiv.org/abs/1704.03155))
|
||||
- [x] DB([paper](https://arxiv.org/abs/1911.08947))
|
||||
- [x] SAST([paper](https://arxiv.org/abs/1908.05498))
|
||||
- [x] PSE([paper](https://arxiv.org/abs/1903.12473v2))
|
||||
|
||||
On the ICDAR2015 dataset, the text detection result is as follows:
|
||||
|
||||
|
|
@ -24,6 +25,8 @@ On the ICDAR2015 dataset, the text detection result is as follows:
|
|||
|DB|ResNet50_vd|86.41%|78.72%|82.38%|[Download link](https://paddleocr.bj.bcebos.com/dygraph_v2.0/en/det_r50_vd_db_v2.0_train.tar)|
|
||||
|DB|MobileNetV3|77.29%|73.08%|75.12%|[Download link](https://paddleocr.bj.bcebos.com/dygraph_v2.0/en/det_mv3_db_v2.0_train.tar)|
|
||||
|SAST|ResNet50_vd|91.39%|83.77%|87.42%|[Download link](https://paddleocr.bj.bcebos.com/dygraph_v2.0/en/det_r50_vd_sast_icdar15_v2.0_train.tar)|
|
||||
|PSE|ResNet50_vd|85.81%|79.53%|82.55%|[Download link](https://paddleocr.bj.bcebos.com/dygraph_v2.1/en_det/det_r50_vd_pse_v2.0_train.tar)|
|
||||
|PSE|MobileNetV3|82.20%|70.47%|75.89%|[Download link](https://paddleocr.bj.bcebos.com/dygraph_v2.1/en_det/det_mv3_pse_v2.0_train.tar)|
|
||||
|
||||
On Total-Text dataset, the text detection result is as follows:
|
||||
|
||||
|
|
@ -41,11 +44,11 @@ For the training guide and use of PaddleOCR text detection algorithms, please re
|
|||
### 2. Text Recognition Algorithm
|
||||
|
||||
PaddleOCR open-source text recognition algorithms list:
|
||||
- [x] CRNN([paper](https://arxiv.org/abs/1507.05717))[7]
|
||||
- [x] Rosetta([paper](https://arxiv.org/abs/1910.05085))[10]
|
||||
- [x] STAR-Net([paper](http://www.bmva.org/bmvc/2016/papers/paper043/index.html))[11]
|
||||
- [x] RARE([paper](https://arxiv.org/abs/1603.03915v1))[12]
|
||||
- [x] SRN([paper](https://arxiv.org/abs/2003.12294))[5]
|
||||
- [x] CRNN([paper](https://arxiv.org/abs/1507.05717))
|
||||
- [x] Rosetta([paper](https://arxiv.org/abs/1910.05085))
|
||||
- [x] STAR-Net([paper](http://www.bmva.org/bmvc/2016/papers/paper043/index.html))
|
||||
- [x] RARE([paper](https://arxiv.org/abs/1603.03915v1))
|
||||
- [x] SRN([paper](https://arxiv.org/abs/2003.12294))
|
||||
|
||||
Refer to [DTRB](https://arxiv.org/abs/1904.01906), the training and evaluation result of these above text recognition (using MJSynth and SynthText for training, evaluate on IIIT, SVT, IC03, IC13, IC15, SVTP, CUTE) is as follow:
|
||||
|
||||
|
|
|
|||
Loading…
Reference in New Issue