Skip to content

GitLab

"ppstructure/vscode:/vscode.git/clone" did not exist on "63ed5fcab30801626ecf55a89f5dc9faf79a16d2"
Commit 83303bc7 authored by LDOUBLEV's avatar LDOUBLEV
Browse files

fix conflicts

parents 3af943f3 af0bac58
Hide whitespace changes
Inline Side-by-side
Showing with 573 additions and 8 deletions
configs/rec/ch_ppocr_v2.0/rec_chinese_common_train_v2.0.yml
View file @ 83303bc7
......@@ -19,6 +19,7 @@ Global:
max_text_length: 25
infer_mode: False
use_space_char: True
save_res_path: ./output/rec/predicts_chinese_common_v2.0.txt
Optimizer:
......
configs/rec/ch_ppocr_v2.0/rec_chinese_lite_train_v2.0.yml
View file @ 83303bc7
......@@ -19,6 +19,7 @@ Global:
max_text_length: 25
infer_mode: False
use_space_char: True
save_res_path: ./output/rec/predicts_chinese_lite_v2.0.txt
Optimizer:
......
configs/rec/rec_icdar15_train.yml
View file @ 83303bc7
......@@ -10,15 +10,16 @@ Global:
cal_metric_during_train: True
pretrained_model:
checkpoints:
save_inference_dir:
save_inference_dir: ./
use_visualdl: False
infer_img: doc/imgs_words_en/word_10.png
# for data or label process
character_dict_path: ppocr/utils/ic15_dict.txt
character_type: ch
character_dict_path: ppocr/utils/en_dict.txt
character_type: EN
max_text_length: 25
infer_mode: False
use_space_char: False
save_res_path: ./output/rec/predicts_ic15.txt
Optimizer:
name: Adam
......@@ -59,8 +60,8 @@ Metric:
Train:
dataset:
name: SimpleDataSet
data_dir: ./train_data/
label_file_list: ["./train_data/train_list.txt"]
data_dir: ./train_data/ic15_data/
label_file_list: ["./train_data/ic15_data/rec_gt_train.txt"]
transforms:
- DecodeImage: # load image
img_mode: BGR
......@@ -80,8 +81,8 @@ Train:
Eval:
dataset:
name: SimpleDataSet
data_dir: ./train_data/
label_file_list: ["./train_data/train_list.txt"]
data_dir: ./train_data/ic15_data
label_file_list: ["./train_data/ic15_data/rec_gt_test.txt"]
transforms:
- DecodeImage: # load image
img_mode: BGR
......
configs/rec/rec_mtb_nrtr.yml 0 → 100644
View file @ 83303bc7
Global:
use_gpu: True
epoch_num: 21
log_smooth_window: 20
print_batch_step: 10
save_model_dir: ./output/rec/nrtr/
save_epoch_step: 1
# 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:
character_type: EN_symbol
max_text_length: 25
infer_mode: False
use_space_char: True
save_res_path: ./output/rec/predicts_nrtr.txt
Optimizer:
name: Adam
beta1: 0.9
beta2: 0.99
clip_norm: 5.0
lr:
name: Cosine
learning_rate: 0.0005
warmup_epoch: 2
regularizer:
name: 'L2'
factor: 0.
Architecture:
model_type: rec
algorithm: NRTR
in_channels: 1
Transform:
Backbone:
name: MTB
cnn_num: 2
Head:
name: Transformer
d_model: 512
num_encoder_layers: 6
beam_size: -1 # When Beam size is greater than 0, it means to use beam search when evaluation.
Loss:
name: NRTRLoss
smoothing: True
PostProcess:
name: NRTRLabelDecode
Metric:
name: RecMetric
main_indicator: acc
Train:
dataset:
name: LMDBDataSet
data_dir: ./train_data/data_lmdb_release/training/
transforms:
- DecodeImage: # load image
img_mode: BGR
channel_first: False
- NRTRLabelEncode: # Class handling label
- NRTRRecResizeImg:
image_shape: [100, 32]
resize_type: PIL # PIL or OpenCV
- KeepKeys:
keep_keys: ['image', 'label', 'length'] # dataloader will return list in this order
loader:
shuffle: True
batch_size_per_card: 512
drop_last: True
num_workers: 8
Eval:
dataset:
name: LMDBDataSet
data_dir: ./train_data/data_lmdb_release/evaluation/
transforms:
- DecodeImage: # load image
img_mode: BGR
channel_first: False
- NRTRLabelEncode: # Class handling label
- NRTRRecResizeImg:
image_shape: [100, 32]
resize_type: PIL # PIL or OpenCV
- 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: 1
use_shared_memory: False
configs/rec/rec_mv3_none_bilstm_ctc.yml
View file @ 83303bc7
......@@ -19,6 +19,7 @@ Global:
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
......
configs/rec/rec_mv3_none_none_ctc.yml
View file @ 83303bc7
......@@ -19,6 +19,7 @@ Global:
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
......
configs/rec/rec_mv3_tps_bilstm_att.yml
View file @ 83303bc7
......@@ -19,6 +19,7 @@ Global:
max_text_length: 25
infer_mode: False
use_space_char: False
save_res_path: ./output/rec/predicts_mv3_tps_bilstm_att.txt
Optimizer:
......
configs/rec/rec_mv3_tps_bilstm_ctc.yml
View file @ 83303bc7
......@@ -19,6 +19,7 @@ Global:
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
......
configs/rec/rec_r31_sar.yml 0 → 100644
View file @ 83303bc7
Global:
use_gpu: true
epoch_num: 5
log_smooth_window: 20
print_batch_step: 20
save_model_dir: ./sar_rec
save_epoch_step: 1
# 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:
# for data or label process
character_dict_path: ppocr/utils/dict90.txt
character_type: EN_symbol
max_text_length: 30
infer_mode: False
use_space_char: False
rm_symbol: True
save_res_path: ./output/rec/predicts_sar.txt
Optimizer:
name: Adam
beta1: 0.9
beta2: 0.999
lr:
name: Piecewise
decay_epochs: [3, 4]
values: [0.001, 0.0001, 0.00001]
regularizer:
name: 'L2'
factor: 0
Architecture:
model_type: rec
algorithm: SAR
Transform:
Backbone:
name: ResNet31
Head:
name: SARHead
Loss:
name: SARLoss
PostProcess:
name: SARLabelDecode
Metric:
name: RecMetric
Train:
dataset:
name: SimpleDataSet
label_file_list: ['./train_data/train_list.txt']
data_dir: ./train_data/
ratio_list: 1.0
transforms:
- DecodeImage: # load image
img_mode: BGR
channel_first: False
- SARLabelEncode: # Class handling label
- SARRecResizeImg:
image_shape: [3, 48, 48, 160] # h:48 w:[48,160]
width_downsample_ratio: 0.25
- KeepKeys:
keep_keys: ['image', 'label', 'valid_ratio'] # dataloader will return list in this order
loader:
shuffle: True
batch_size_per_card: 64
drop_last: True
num_workers: 8
use_shared_memory: False
Eval:
dataset:
name: LMDBDataSet
data_dir: ./train_data/data_lmdb_release/evaluation/
transforms:
- DecodeImage: # load image
img_mode: BGR
channel_first: False
- SARLabelEncode: # Class handling label
- SARRecResizeImg:
image_shape: [3, 48, 48, 160]
width_downsample_ratio: 0.25
- KeepKeys:
keep_keys: ['image', 'label', 'valid_ratio'] # dataloader will return list in this order
loader:
shuffle: False
drop_last: False
batch_size_per_card: 64
num_workers: 4
use_shared_memory: False
configs/rec/rec_r34_vd_none_bilstm_ctc.yml
View file @ 83303bc7
......@@ -19,6 +19,7 @@ Global:
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
......
configs/rec/rec_r34_vd_none_none_ctc.yml
View file @ 83303bc7
......@@ -19,6 +19,7 @@ Global:
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
......
configs/rec/rec_r34_vd_tps_bilstm_att.yml
View file @ 83303bc7
......@@ -19,6 +19,7 @@ Global:
max_text_length: 25
infer_mode: False
use_space_char: False
save_res_path: ./output/rec/predicts_b3_rare_r34_none_gru.txt
Optimizer:
......
configs/rec/rec_r34_vd_tps_bilstm_ctc.yml
View file @ 83303bc7
......@@ -19,6 +19,7 @@ Global:
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
......@@ -37,7 +38,7 @@ Architecture:
name: TPS
num_fiducial: 20
loc_lr: 0.1
model_name: small
model_name: large
Backbone:
name: ResNet
layers: 34
......
configs/rec/rec_r50_fpn_srn.yml
View file @ 83303bc7
......@@ -20,6 +20,7 @@ Global:
num_heads: 8
infer_mode: False
use_space_char: False
save_res_path: ./output/rec/predicts_srn.txt
Optimizer:
......
configs/rec/rec_resnet_stn_bilstm_att.yml 0 → 100644
View file @ 83303bc7
Global:
use_gpu: True
epoch_num: 400
log_smooth_window: 20
print_batch_step: 10
save_model_dir: ./output/rec/seed
save_epoch_step: 3
# evaluation is run every 5000 iterations after the 4000th iteration
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:
character_type: EN_symbol
max_text_length: 100
infer_mode: False
use_space_char: False
save_res_path: ./output/rec/predicts_seed.txt
Optimizer:
name: Adadelta
weight_deacy: 0.0
momentum: 0.9
lr:
name: Piecewise
decay_epochs: [4,5,8]
values: [1.0, 0.1, 0.01]
regularizer:
name: 'L2'
factor: 2.0e-05
Architecture:
model_type: rec
algorithm: SEED
Transform:
name: STN_ON
tps_inputsize: [32, 64]
tps_outputsize: [32, 100]
num_control_points: 20
tps_margins: [0.05,0.05]
stn_activation: none
Backbone:
name: ResNet_ASTER
Head:
name: AsterHead # AttentionHead
sDim: 512
attDim: 512
max_len_labels: 100
Loss:
name: AsterLoss
PostProcess:
name: SEEDLabelDecode
Metric:
name: RecMetric
main_indicator: acc
is_filter: True
Train:
dataset:
name: LMDBDataSet
data_dir: ./train_data/data_lmdb_release/training/
transforms:
- Fasttext:
path: "./cc.en.300.bin"
- DecodeImage: # load image
img_mode: BGR
channel_first: False
- SEEDLabelEncode: # Class handling label
- RecResizeImg:
character_type: en
image_shape: [3, 64, 256]
padding: False
- KeepKeys:
keep_keys: ['image', 'label', 'length', 'fast_label'] # dataloader will return list in this order
loader:
shuffle: True
batch_size_per_card: 256
drop_last: True
num_workers: 6
Eval:
dataset:
name: LMDBDataSet
data_dir: ./train_data/data_lmdb_release/evaluation/
transforms:
- DecodeImage: # load image
img_mode: BGR
channel_first: False
- SEEDLabelEncode: # Class handling label
- RecResizeImg:
character_type: en
image_shape: [3, 64, 256]
padding: False
- KeepKeys:
keep_keys: ['image', 'label', 'length'] # dataloader will return list in this order
loader:
shuffle: False
drop_last: True
batch_size_per_card: 256
num_workers: 4
configs/table/table_mv3.yml 0 → 100755
View file @ 83303bc7
Global:
use_gpu: true
epoch_num: 50
log_smooth_window: 20
print_batch_step: 5
save_model_dir: ./output/table_mv3/
save_epoch_step: 5
# evaluation is run every 400 iterations after the 0th iteration
eval_batch_step: [0, 400]
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
character_dict_path: ppocr/utils/dict/table_structure_dict.txt
character_type: en
max_text_length: 100
max_elem_length: 500
max_cell_num: 500
infer_mode: False
process_total_num: 0
process_cut_num: 0
Optimizer:
name: Adam
beta1: 0.9
beta2: 0.999
clip_norm: 5.0
lr:
learning_rate: 0.001
regularizer:
name: 'L2'
factor: 0.00000
Architecture:
model_type: table
algorithm: TableAttn
Backbone:
name: MobileNetV3
scale: 1.0
model_name: small
disable_se: True
Head:
name: TableAttentionHead
hidden_size: 256
l2_decay: 0.00001
loc_type: 2
Loss:
name: TableAttentionLoss
structure_weight: 100.0
loc_weight: 10000.0
PostProcess:
name: TableLabelDecode
Metric:
name: TableMetric
main_indicator: acc
Train:
dataset:
name: PubTabDataSet
data_dir: train_data/table/pubtabnet/train/
label_file_path: train_data/table/pubtabnet/PubTabNet_2.0.0_train.jsonl
transforms:
- DecodeImage: # load image
img_mode: BGR
channel_first: False
- ResizeTableImage:
max_len: 488
- TableLabelEncode:
- NormalizeImage:
scale: 1./255.
mean: [0.485, 0.456, 0.406]
std: [0.229, 0.224, 0.225]
order: 'hwc'
- PaddingTableImage:
- ToCHWImage:
- KeepKeys:
keep_keys: ['image', 'structure', 'bbox_list', 'sp_tokens', 'bbox_list_mask']
loader:
shuffle: True
batch_size_per_card: 32
drop_last: True
num_workers: 1
Eval:
dataset:
name: PubTabDataSet
data_dir: train_data/table/pubtabnet/val/
label_file_path: train_data/table/pubtabnet/PubTabNet_2.0.0_val.jsonl
transforms:
- DecodeImage: # load image
img_mode: BGR
channel_first: False
- ResizeTableImage:
max_len: 488
- TableLabelEncode:
- NormalizeImage:
scale: 1./255.
mean: [0.485, 0.456, 0.406]
std: [0.229, 0.224, 0.225]
order: 'hwc'
- PaddingTableImage:
- ToCHWImage:
- KeepKeys:
keep_keys: ['image', 'structure', 'bbox_list', 'sp_tokens', 'bbox_list_mask']
loader:
shuffle: False
drop_last: False
batch_size_per_card: 16
num_workers: 1
deploy/android_demo/.gitignore 0 → 100644
View file @ 83303bc7
*.iml
.gradle
/local.properties
/.idea/*
.DS_Store
/build
/captures
.externalNativeBuild
deploy/android_demo/README.md 0 → 100644
View file @ 83303bc7
# 如何快速测试
### 1. 安装最新版本的Android Studio
可以从 https://developer.android.com/studio 下载。本Demo使用是4.0版本Android Studio编写。
### 2. 按照NDK 20 以上版本
Demo测试的时候使用的是NDK 20b版本，20版本以上均可以支持编译成功。
如果您是初学者，可以用以下方式安装和测试NDK编译环境。
点击 File -> New ->New Project， 新建 "Native C++" project
### 3. 导入项目
点击 File->New->Import Project...， 然后跟着Android Studio的引导导入
# 获得更多支持
前往[端计算模型生成平台EasyEdge](https://ai.baidu.com/easyedge/app/open_source_demo?referrerUrl=paddlelite)，获得更多开发支持：
- Demo APP：可使用手机扫码安装，方便手机端快速体验文字识别
- SDK：模型被封装为适配不同芯片硬件和操作系统SDK，包括完善的接口，方便进行二次开发
deploy/android_demo/app/build.gradle 0 → 100644
View file @ 83303bc7
import java.security.MessageDigest
apply plugin: 'com.android.application'
android {
compileSdkVersion 29
defaultConfig {
applicationId "com.baidu.paddle.lite.demo.ocr"
minSdkVersion 23
targetSdkVersion 29
versionCode 1
versionName "1.0"
testInstrumentationRunner "android.support.test.runner.AndroidJUnitRunner"
externalNativeBuild {
cmake {
cppFlags "-std=c++11 -frtti -fexceptions -Wno-format"
arguments '-DANDROID_PLATFORM=android-23', '-DANDROID_STL=c++_shared' ,"-DANDROID_ARM_NEON=TRUE"
}
}
ndk {
// abiFilters "arm64-v8a", "armeabi-v7a"
abiFilters "arm64-v8a", "armeabi-v7a"
ldLibs "jnigraphics"
}
}
buildTypes {
release {
minifyEnabled false
proguardFiles getDefaultProguardFile('proguard-android-optimize.txt'), 'proguard-rules.pro'
}
}
externalNativeBuild {
cmake {
path "src/main/cpp/CMakeLists.txt"
version "3.10.2"
}
}
}
dependencies {
implementation fileTree(include: ['*.jar'], dir: 'libs')
implementation 'androidx.appcompat:appcompat:1.1.0'
implementation 'androidx.constraintlayout:constraintlayout:1.1.3'
testImplementation 'junit:junit:4.12'
androidTestImplementation 'com.android.support.test:runner:1.0.2'
androidTestImplementation 'com.android.support.test.espresso:espresso-core:3.0.2'
}
def archives = [
[
'src' : 'https://paddleocr.bj.bcebos.com/dygraph_v2.0/lite/paddle_lite_libs_v2_9_0.tar.gz',
'dest': 'PaddleLite'
],
[
'src' : 'https://paddlelite-demo.bj.bcebos.com/libs/android/opencv-4.2.0-android-sdk.tar.gz',
'dest': 'OpenCV'
],
[
'src' : 'https://paddleocr.bj.bcebos.com/dygraph_v2.0/lite/ocr_v2_for_cpu.tar.gz',
'dest' : 'src/main/assets/models'
],
[
'src' : 'https://paddleocr.bj.bcebos.com/dygraph_v2.0/lite/ch_dict.tar.gz',
'dest' : 'src/main/assets/labels'
]
]
task downloadAndExtractArchives(type: DefaultTask) {
doFirst {
println "Downloading and extracting archives including libs and models"
}
doLast {
// Prepare cache folder for archives
String cachePath = "cache"
if (!file("${cachePath}").exists()) {
mkdir "${cachePath}"
}
archives.eachWithIndex { archive, index ->
MessageDigest messageDigest = MessageDigest.getInstance('MD5')
messageDigest.update(archive.src.bytes)
String cacheName = new BigInteger(1, messageDigest.digest()).toString(32)
// Download the target archive if not exists
boolean copyFiles = !file("${archive.dest}").exists()
if (!file("${cachePath}/${cacheName}.tar.gz").exists()) {
ant.get(src: archive.src, dest: file("${cachePath}/${cacheName}.tar.gz"))
copyFiles = true; // force to copy files from the latest archive files
}
// Extract the target archive if its dest path does not exists
if (copyFiles) {
copy {
from tarTree("${cachePath}/${cacheName}.tar.gz")
into "${archive.dest}"
}
}
}
}
}
preBuild.dependsOn downloadAndExtractArchives
\ No newline at end of file
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