YangShuai

Can someone tell me which GAN is the best?

3

I am a freshman for GAN and want to learn it. Can someone tell me which GAN is the best at present? Thank you. O(∩_∩)O~~

想请教下yolov3针对车牌识别具体做了哪些优化

1

小姐姐你好，我是paddle tech day过来的~~看到你在readme中说对YOLOv3进行针对性优化，能否指点下在哪些方面做了优化呢？ 另外方便提供下YOLOv3的模型吗？谢谢小姐姐^ ^

How do you draw the picture of [ Object Pairs with High Relation Weights] and [Class Co-Occurrence Information is Learnt] in your slides?

1

How do you draw the picture of [ Object Pairs with High Relation Weights] and [ Class Co-Occurrence Information is Learnt ] in your slides of CVPR2018

关于最后使用7个softmax进行序列识别的问题

4

google的门牌号识别的论文里说，第一个softmax用于预测序列长度，其余的softmax用于预测位置和字符。照这样来说，最后不应该用8个softmax吗？车牌号长度一般为7，第一个softmax用于预测车牌号序列长度，剩下7个预测位置和字符。

如何训练？

2

https://github.com/zuoqing1988/train-mtcnn 链接失效，求一个训练步骤 感谢大佬

Hi, I just want to test my image with model without training it, so can you share your trained model such as "model.ckpt-858"? thanks

when I run `python demo.py -model=e2e-mlt.h5` on my image using pretrained model, I get error chars like: `Using cuda ... 炯 豚树糊Ｖ 鐫혁 労潔菉 瘙늠캄视胎興瘙菁綜헤誉숯덧顾 瞑주诈밟赌漓誉 瘙룹覆払멸戈 捉貯Ω汽 逢茉帛ш²터勇 炯...

我目前了解的车牌识别方法就是两种：分割然后识别单个字符；或者使用CTC进行序列识别。我没看懂你这个code用的是什么方法，多标签分类是什么意思呀？

你好。我运行mainTest.cpp后，终端的打印信息为： ---------- 检测到的特征点：0 0 透视变换矩阵求解错误！ 请问这个问题该怎么解决，谢谢 使用的就是repo中自带的两张图