Giter Site home page Giter Site logo

crnn_plate_recognition's Issues

模型输入tensor的尺寸不对

做好数据处理等前置工作后,执行训练脚本 python train.py --cfg OWN_config.yaml 提示模型尺寸不正确,示例代码train.py 中构建的三种模型都不正确,如何约束这个尺寸问题?

下面展示各个模型的错误:
1 -- build_lprnet
model = build_lprnet(num_classes=len(plate_chr))
错误为:RuntimeError: Given groups=1, weight of size [64, 3, 3, 3], expected input[32, 1, 32, 160] to have 3 channels, but got 1 channels instead
2 -- myNet_ocr
model = myNet_ocr(num_classes=len(plate_chr),cfg=cfg)
错误为:RuntimeError: Given groups=1, weight of size [32, 3, 5, 5], expected input[32, 1, 32, 160] to have 3 channels, but got 1 channels instead
3 -- crnn
model = crnn.get_crnn(config,cfg=cfg)
错误为:RuntimeError: Given groups=1, weight of size [32, 3, 5, 5], expected input[32, 1, 32, 160] to have 3 channels, but got 1 channels instead

ImportError: No module named lib.models.crnn

大家是否遇到同样的问题,有解决方案吗?

 ~/Documents/GitHub/crnn_plate_recognition/ [master] python train.py --cfg lib/config/360CC_config.yaml
Traceback (most recent call last):
  File "train.py", line 8, in <module>
    import lib.models.crnn as crnn
ImportError: No module named lib.models.crnn

训练模型选择问题

您好,请问训练过程中使用的myNet_ocr模型与CRNN模型有联系吗?怎么替换为CRNN模型呢?感谢大佬。

训练tricks咨询

请问博主,是否还有别的训练方法啊,我这边按照您提供的readme训练,虽然模型精度也能达到98%,但是模型的泛化性还是比您训练的模型差一点点,特别是双层车牌效果没您的好,请问您也是用的您所提供的dataset训练的吗?还是说加过其它额外数据?或者是在调参上面有一些技巧呢?谢谢。

训练图片的宽度为啥是固定的?

我很想用此代码来训练文本识别,文本的长度是不固定的。但是 我们训练和 ncnn中的识别代码,都是宽度是固定的168,对于车牌这种还可以。要是 文本变长的,我们应该怎么办啊,求教。

train.py parser.add_argument('--img_w',type=int,default=168,help='width')

脚本
OW: 280 # origial width: 280
H: 32
W: 100 # resized width: 160

Can't use Weechat or QQ Group

Hi @we0091234,

I'm Arunkumar from India. I can't connect with you on both WeChat and QQ group. Are there any other ways to connect with you? I have some doubts I need to discuss.

Thanks!

LPRnet Accuracy

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 accuracy value for the LPRNet output

kpt-label

kpt-label 为2 报错,这个是kpt写死了只能为4么

Recommend Projects

  • React photo React

    A declarative, efficient, and flexible JavaScript library for building user interfaces.

  • Vue.js photo Vue.js

    🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.

  • Typescript photo Typescript

    TypeScript is a superset of JavaScript that compiles to clean JavaScript output.

  • TensorFlow photo TensorFlow

    An Open Source Machine Learning Framework for Everyone

  • Django photo Django

    The Web framework for perfectionists with deadlines.

  • D3 photo D3

    Bring data to life with SVG, Canvas and HTML. 📊📈🎉

Recommend Topics

  • javascript

    JavaScript (JS) is a lightweight interpreted programming language with first-class functions.

  • web

    Some thing interesting about web. New door for the world.

  • server

    A server is a program made to process requests and deliver data to clients.

  • Machine learning

    Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.

  • Game

    Some thing interesting about game, make everyone happy.

Recommend Org

  • Facebook photo Facebook

    We are working to build community through open source technology. NB: members must have two-factor auth.

  • Microsoft photo Microsoft

    Open source projects and samples from Microsoft.

  • Google photo Google

    Google ❤️ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.