-
-
Hi @Bartzi
I already successfully train my custom data set (loss score below 0.01) with this command until last epoch:
```
python train_text_recognition.py mytrain/curriculum.json log \
--bla…
-
采用官方给出的模型rec_crnn进行转换，三种算子不支持转换：lstm, ctc_align, top_k，请问这些算子后续可以添加吗？或者自己怎么定义这些算子的转换？谢谢~
-
Hi, thanks a lot your efforts. It's a greatwork. I was trying to train your model with CVL dataset on Google Colab Pro. I've transform the image format from .tif to .png and feed to the model. But af…
-
Hi Author,
Great work from you, and thanks for the sharing.
I noted that the accuracy of your best model on IC13 is 93.6% in the paper, while it's 95.98% on the robust reading competition [website](…
-
安装环境后，运行测试时报错：
Loading network VGGnet_test...
Restoring from ./ctpn/checkpoints/VGGnet_fast_rcnn_iter_50000.ckpt...
done
Using TensorFlow backend.
modelPath /home/kunqian/nvidia_dev/chinese_ocr-…
-
https://dmdm101.tistory.com/m/9?category=0
SOREL-20M (Sophos / ReversingLabs-2 천만) 데이터 세트 :
미리 추출 된 기능 및 메타 데이터가있는 거의 2 천만 개의 파일로 구성된 대규모 데이터 세트,
여러 소스에서 파생 된 고품질 레이블, 공급 업체 감지에 대한 정보 에서 악성 코드 샘플…
-
先说明下，最近刚发现百度这个开源项目，乍一看，CV的各种检测算法、分类模型、分割、文字识别、甚至是YOLO v3的支持，都让我心跳加速，恨没有早发现这个开源项目。怀着激动的心情，我开始了这段旅途~
第一步，自然是源码构建，立马就躺了一坑。因为我习惯是在build目录下，再创建debug和release目录用来分开构建。岂料，死活就是构建不成功，报个什么snappy头文件的错误，来这里找答案也…
-
我更改了`rec_chinese_lite_train.yml`配置文件的内容，如下：
```
Global:
algorithm: CRNN
use_gpu: true
epoch_num: 300
log_smooth_window: 20
print_batch_step: 10
save_model_dir: ./output/rec_CRNN
…
-
I have been training CRNN for Vietnamese text recognition for days but my evaluation score always 0.0 in spite of my training score improve
![image](https://github.com/PaddlePaddle/PaddleOCR/assets/…