End-to-end-for-chinese-plate-recognition
End-to-end-for-chinese-plate-recognition copied to clipboard
基于u-net,cv2以及cnn的中文车牌定位,矫正和端到端识别软件,其中unet和cv2用于车牌定位和矫正,cnn进行车牌识别,unet和cnn都是基于tensorflow的keras实现
请教一个问题,我看代码cnn网络使用的是车牌图片修正后的3通道数据做输入,如果将输入图片做灰度化或二值化后再输入cnn是否训练速度更快,识别效果更好? __________________________________________________________________________________________________ Model: "model" __________________________________________________________________________________________________ Layer (type) Output Shape Param # Connected to ================================================================================================== **input_1 (InputLayer) [(None, 80, 240, 3)] 0** __________________________________________________________________________________________________ conv2d (Conv2D) (None, 80, 240, 16) 448 input_1[0][0]...
您好, 看到您在文件`Unet.py`中对于网络的训练没有设置验证集, 请问这样会对训练结果有影响吗?
您好,请问cnn网络如何使得识别出来的车牌字符是按照顺序排列的?
Dear Maintainers, Firstly, I would like to extend my compliments on the remarkable work being carried out in the realm of Chinese plate recognition with the End-to-end-for-chinese-plate-recognition repository. The integration...
您好,我这边训练80次,大概900张图片。但是最终loss降低至250左右,acc约1%,您可以为我解答一下为什么acc这么低吗?
本人可提供一手车牌检测和车牌识别商用级别数据集,数据简介见链接:https://www.bilibili.com/video/bv1kU4y1e7Sb qq:1041357701