Skip to content
GitLab
Menu
Projects
Groups
Snippets
Loading...
Help
Help
Support
Community forum
Keyboard shortcuts
?
Submit feedback
Contribute to GitLab
Sign in / Register
Toggle navigation
Menu
Open sidebar
wangsen
paddle_dbnet
Commits
24e42556
"...composable_kernel_onnx.git" did not exist on "db0eb1ea9cbc789d8f17b6d101794d966d2f3088"
Unverified
Commit
24e42556
authored
May 18, 2020
by
xiaoting
Committed by
GitHub
May 18, 2020
Browse files
Merge pull request #55 from LDOUBLEV/fixocr
Fixocr
parents
078a823f
516139e4
Changes
1
Hide whitespace changes
Inline
Side-by-side
Showing
1 changed file
with
10 additions
and
3 deletions
+10
-3
doc/detection.md
doc/detection.md
+10
-3
No files found.
doc/detection.md
View file @
24e42556
...
@@ -65,17 +65,24 @@ PaddleOCR计算三个OCR检测相关的指标,分别是:Precision、Recall
...
@@ -65,17 +65,24 @@ PaddleOCR计算三个OCR检测相关的指标,分别是:Precision、Recall
运行如下代码,根据配置文件det_db_mv3.yml中save_res_path指定的测试集检测结果文件,计算评估指标。
运行如下代码,根据配置文件det_db_mv3.yml中save_res_path指定的测试集检测结果文件,计算评估指标。
```
```
python3 tools/eval.py -c configs/det/det_mv3_db.yml -o Glo
a
bl.checkpoints="
./output
/best_accuracy"
python3 tools/eval.py -c configs/det/det_mv3_db.yml -o Glob
a
l.checkpoints="
{path/to/weights}
/best_accuracy"
```
```
训练中模型参数默认保存在Global.save_model_dir目录下。在评估指标时,需要设置Global.checkpoints指向保存的参数文件。
比如:
```
python3 tools/eval.py -c configs/det/det_mv3_db.yml -o Global.checkpoints="./output/det_db/best_accuracy"
```
## 测试检测效果
## 测试检测效果
测试单张图像的检测效果
测试单张图像的检测效果
```
```
python3 tools/infer_det.py -c config/det/det_mv3_db.yml -o TestReader.single_img_path="./d
emo
.jpg"
python3 tools/infer_det.py -c config/det/det_mv3_db.yml -o TestReader.single_img_path="./d
oc/imgs_en/img_10
.jpg"
```
```
测试文件夹下所有图像的检测效果
测试文件夹下所有图像的检测效果
```
```
python3 tools/infer_det.py -c config/det/det_mv3_db.yml -o TestReader.single_img_path="./d
emo_img
/"
python3 tools/infer_det.py -c config/det/det_mv3_db.yml -o TestReader.single_img_path="./d
oc/imgs_en
/"
```
```
Write
Preview
Markdown
is supported
0%
Try again
or
attach a new file
.
Attach a file
Cancel
You are about to add
0
people
to the discussion. Proceed with caution.
Finish editing this message first!
Cancel
Please
register
or
sign in
to comment