From c9504a942572b99119d02af814e57083f6113f8c Mon Sep 17 00:00:00 2001
From: andyjpaddle <jiangkaitao@baidu.com>
Date: Mon, 15 Aug 2022 09:38:56 +0000
Subject: [PATCH] fix vl predict format

---
 doc/doc_ch/algorithm_rec_visionlan.md    | 4 ++--
 doc/doc_en/algorithm_rec_visionlan_en.md | 4 ++--
 ppocr/postprocess/rec_postprocess.py     | 2 +-
 3 files changed, 5 insertions(+), 5 deletions(-)

diff --git a/doc/doc_ch/algorithm_rec_visionlan.md b/doc/doc_ch/algorithm_rec_visionlan.md
index 0c4fe86e..df039491 100644
--- a/doc/doc_ch/algorithm_rec_visionlan.md
+++ b/doc/doc_ch/algorithm_rec_visionlan.md
@@ -101,7 +101,7 @@ python3 tools/export_model.py -c configs/rec/rec_r45_visionlan.yml -o Global.pre
 执行如下命令进行模型推理：
 
 ```shell
-python3 tools/infer/predict_rec.py --image_dir='./doc/imgs_words/en/word_2.png' --rec_model_dir='./inference/rec_r45_visionlan/' --rec_algorithm='VisionLAN' --rec_image_shape='3,64,256' --rec_char_dict_path='./ppocr/utils/dict36.txt'
+python3 tools/infer/predict_rec.py --image_dir='./doc/imgs_words/en/word_2.png' --rec_model_dir='./inference/rec_r45_visionlan/' --rec_algorithm='VisionLAN' --rec_image_shape='3,64,256' --rec_char_dict_path='./ppocr/utils/ic15_dict.txt' --use_space_char=False
 # 预测文件夹下所有图像时，可修改image_dir为文件夹，如 --image_dir='./doc/imgs_words_en/'。
 ```
 
@@ -110,7 +110,7 @@ python3 tools/infer/predict_rec.py --image_dir='./doc/imgs_words/en/word_2.png'
 执行命令后，上面图像的预测结果（识别的文本和得分）会打印到屏幕上，示例如下：
 结果如下：
 ```shell
-Predicts of ./doc/imgs_words/en/word_2.png:('yourself', 0.97076982)
+Predicts of ./doc/imgs_words/en/word_2.png:('yourself', 0.9999493)
 ```
 
 **注意**：
diff --git a/doc/doc_en/algorithm_rec_visionlan_en.md b/doc/doc_en/algorithm_rec_visionlan_en.md
index ebd02d52..70c2ccc4 100644
--- a/doc/doc_en/algorithm_rec_visionlan_en.md
+++ b/doc/doc_en/algorithm_rec_visionlan_en.md
@@ -90,7 +90,7 @@ After the conversion is successful, there are three files in the directory:
 For VisionLAN text recognition model inference, the following commands can be executed:
 
 ```
-python3 tools/infer/predict_rec.py --image_dir='./doc/imgs_words/en/word_2.png' --rec_model_dir='./inference/rec_r45_visionlan/' --rec_algorithm='VisionLAN' --rec_image_shape='3,64,256' --rec_char_dict_path='./ppocr/utils/dict36.txt'
+python3 tools/infer/predict_rec.py --image_dir='./doc/imgs_words/en/word_2.png' --rec_model_dir='./inference/rec_r45_visionlan/' --rec_algorithm='VisionLAN' --rec_image_shape='3,64,256' --rec_char_dict_path='./ppocr/utils/ic15_dict.txt' --use_space_char=False
 ```
 
 ![](../imgs_words/en/word_2.png)
@@ -98,7 +98,7 @@ python3 tools/infer/predict_rec.py --image_dir='./doc/imgs_words/en/word_2.png'
 After executing the command, the prediction result (recognized text and score) of the image above is printed to the screen, an example is as follows:
 The result is as follows:
 ```shell
-Predicts of ./doc/imgs_words/en/word_2.png:('yourself', 0.97076982)
+Predicts of ./doc/imgs_words/en/word_2.png:('yourself', 0.9999493)
 ```
 
 <a name="4-2"></a>
diff --git a/ppocr/postprocess/rec_postprocess.py b/ppocr/postprocess/rec_postprocess.py
index 1b4ab73e..fc9fccfb 100644
--- a/ppocr/postprocess/rec_postprocess.py
+++ b/ppocr/postprocess/rec_postprocess.py
@@ -780,7 +780,7 @@ class VLLabelDecode(BaseRecLabelDecode):
             ) + length[i])].topk(1)[0][:, 0]
             preds_prob = paddle.exp(
                 paddle.log(preds_prob).sum() / (preds_prob.shape[0] + 1e-6))
-            text.append((preds_text, preds_prob.numpy()))
+            text.append((preds_text, preds_prob.numpy()[0]))
         if label is None:
             return text
         label = self.decode(label)
-- 
GitLab