-
File "C:\Users\86157\AppData\Local\Programs\Python\Python36\lib\site-packages\PIL\ImageFont.py", line 190, in __init__
with open(font, "rb") as f:
FileNotFoundError: [Errno 2] No such file or …
-
使用table-detect训练完之后的模型是.h5格式，如何转换为此项目可用的weights格式？
-
gradle sync的时候会提示：
ERROR: Cause: executing external native build for cmake D:\Project\chineseocr_lite-master\android_demo\app\src\main\cpp\CMakeLists.txt
我在win10下配置，环境和readme里面一致，cmake我的版本不对，针对这个项…
-
您好，我把darknet的网络和权重拿出来之后。最后一层的输出是logit层么 也就是未经logistic的，那么预测的时候
对'table/convolutional33/BiasAdd' 需要logistic么，还是类似 函数 dnn_table_predict 里 exp的操作
-
系统： WSL Ubuntu
Onnx Runtime 1.14.0
OpenCV 4.2.0
首先，我提取出来cpp_project为：https://github.com/tx7do/cppocrlite；
然后，我通过cgo，封装成了golang版本：https://github.com/tx7do/go-chineseocr-lite。
然后，我运行demo图片，图1的歌…
-
请问一下您能够提供一下Unet网络的训练地址吗？我试了您的表格横竖线的分割模型，但我想重新训练做一个三线表的分割，感激不尽~ 我的邮箱是 mexingchen.li@gmail.com
-
when use labelme to label image , Is it a straight line or a thin box?
-
* I fork your project and add `Flask` server.
* Project address: https://github.com/sunhailin-Leo/chineseocr_lite
* Here is my code address: https://github.com/sunhailin-Leo/chineseocr_lite/blob/mas…
-
when Execute nvidia-docker attach ef88590217d0 it raise always:
sudo nvidia-docker attach ef88590217d0
You cannot attach to a stopped container, start it first
-
I notice the word:"added the ability for training recurrent models (with layers conv-lstm[conv_lstm]/conv-rnn[crnn]) for accurate detection on video."
So, the lstm/crnn can be used OCR?