LPRNet_Pytorch

LPRNet_Pytorch copied to clipboard

修改--test_img_dirs后除了94x24大小的图片都会报错

2

除了94x24大小的所有图片都会报这个错，出什么问题了？ > Traceback (most recent call last):  File "test_LPRNet.py", line 176, in    test()  File "test_LPRNet.py", line 74, in test    Greedy_Decode_Eval(lprnet, test_dataset, args)  File "test_LPRNet.py", line 105, in Greedy_Decode_Eval    prebs =...

IamWilliamWang

synthetic data

1

Hi thank you for your great work . Can I use synthetic data for training and predict on real images ?

centurions

图片名字有中文字的时候会报错no module named shape，可是改了名字之后不就没标签了吗？请问该怎么办

2

littleloverlalala

图片尺寸、字符类别、最大字符数都需要改，应该怎么用？

1

图片尺寸需要改成，256 * 32 共有37种字符，英文+数字+额外一种符号 字符在10~20个，lpr_max_len = 20 想知道该怎么该这个网络才能用

nistarlwc

ncnn推理，已经C++结合ncnn实现lprnet模型推理，有需要可以交流

7

Ayers-github

Accuracy 0.0, when i training custom dataset.

4

Hi, when i training model with custom data set, the accuracy is always 0. I modified the list of CHARS and license plate length, what could be the problem? 

Lightmourne

test_accuracy 0.0

1

test_accuracy是0.0是啥情况？

kankanjiuzou123

https://github.com/pcb9382/PlateRecognition

pcb9382

我在训练集放了3000张，测试集里面放了200张，但是我无论怎样放总会出现[Info] Test Accuracy: 0.0 [0:120:0:120]，也就是tp和tp_2总是为0，我想问一下这是为什么

8

nanlidashi

Is it possible to compute the accuracy output from the LPRNet model?

1

Is there any reference to someone's knowledge which explains how to compute the accuracy of the LPRNet model output? I'm not interested into computing WER or CER, but an overall...

tscu-vid