LPRNet_Pytorch icon indicating copy to clipboard operation
LPRNet_Pytorch copied to clipboard

Pytorch Implementation For LPRNet, A High Performance And Lightweight License Plate Recognition Framework.

Results 74 LPRNet_Pytorch issues
Sort by recently updated
recently updated
newest added
trafficstars

> 用预训练的模型测试所给的测试集,怎么只有0.9的正确率,再训练了自己的数据集之后就只有0.74了。。。 请教一下大神,你是什么训练出0.74的准确率的?能教我一下你修改了哪儿吗?为啥我训练出来的都是0呢。 这是我训练的过程: Successful to build network! initial net weight successful! [Info] Test Accuracy: 0.0 [0:861:99:960] [Info] Test Speed: 0.015824174165725707s 1/1000] [Info] Test Accuracy: 0.0 [0:866:94:960] [Info] Test Speed:...

车牌识别数据集,,包含多种车牌类型,各省份数量均匀且充足:qq1668486259

请问在转onnx时出现这样的维度问题应该怎么解决呢? 有一些网络改数据格式是可以解决问题的,但是这里好像不行 graph(%input.1 : Float(1, 3, 24, 94), %backbone.0.weight : Float(64, 3, 3, 3), %backbone.0.bias : Float(64), %backbone.1.weight : Float(64), %backbone.1.bias : Float(64), %backbone.1.running_mean : Float(64), %backbone.1.running_var : Float(64), %backbone.4.block.0.weight...

Thanks for the great project! The [LPRNet paper](https://arxiv.org/pdf/1806.10447.pdf) talks about the "basic" and "reduced" model: > To improve runtime performance we also modified LPRNet basic by using 2 × 2...

比如大型挂车的后车牌通常为黄色双层的

When I use `python test_LPRNet.py` the output: ``` Successful to build network! load pretrained model successful! Traceback (most recent call last): File "test_LPRNet.py", line 176, in test() File "test_LPRNet.py", line...

为发现蓝色车牌(CCPD2019)的识别准确率远高于新能源车牌(CCPD2020),并且经过STN空间校正后蓝色车牌的精度提升了,而新能源车牌的精度反而下降,有谁知道是怎么回事吗?