forgetest5
/
PaddleOCR
1
0
Fork 0
Code Issues Pull Requests Releases Wiki Activity

Merge pull request #175 from LDOUBLEV/fixocr 

add doc of decommpressing pretrain weight file
This commit is contained in:
Double_V 2020-06-10 20:45:21 +08:00 committed by GitHub
parent 90d2bf0ce4 16572f2790
commit e036c8051b
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
2 changed files with 24 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

12
doc/doc_ch/detection.md
View File

@ -43,6 +43,18 @@ cd PaddleOCR/
wget -P ./pretrain_models/ https://paddle-imagenet-models-name.bj.bcebos.com/MobileNetV3_large_x0_5_pretrained.tar
# 下载ResNet50的预训练模型
wget -P ./pretrain_models/ https://paddle-imagenet-models-name.bj.bcebos.com/ResNet50_vd_ssld_pretrained.tar
# 解压预训练模型文件，以MobileNetV3为例
tar xf ./pretrain_models/MobileNetV3_large_x0_5_pretrained.tar ./pretrain_models/
# 注：正确解压backbone预训练权重文件后，文件夹下包含众多以网络层命名的权重文件，格式如下：
./pretrain_models/MobileNetV3_large_x0_5_pretrained/
└─ conv_last_bn_mean
└─ conv_last_bn_offset
└─ conv_last_bn_scale
└─ conv_last_bn_variance
└─ ......
```
**启动训练**

12
doc/doc_en/detection_en.md
View File

@ -42,6 +42,18 @@ cd PaddleOCR/
wget -P ./pretrain_models/ https://paddle-imagenet-models-name.bj.bcebos.com/MobileNetV3_large_x0_5_pretrained.tar
# Download the pre-trained model of ResNet50
wget -P ./pretrain_models/ https://paddle-imagenet-models-name.bj.bcebos.com/ResNet50_vd_ssld_pretrained.tar
# decompressing the pre-training model file, take MobileNetV3 as an example
tar xf ./pretrain_models/MobileNetV3_large_x0_5_pretrained.tar ./pretrain_models/
# Note: After decompressing the backbone pre-training weight file correctly, the file list in the folder is as follows:
./pretrain_models/MobileNetV3_large_x0_5_pretrained/
└─ conv_last_bn_mean
└─ conv_last_bn_offset
└─ conv_last_bn_scale
└─ conv_last_bn_variance
└─ ......
```
**Start training**