CCPD
CCPD copied to clipboard
[ECCV 2018] CCPD: a diverse and well-annotated dataset for license plate detection and recognition
I downloaded the files from Google Drive, but the compression level seems too high. The paper mentions that the average file size is 200kb, but I got the following statistics...
您好,我想请问一下如果训练自己的数据集,图片大小必须是720*1160吗?我的数据图片大小都是不一样的。 我修改了数据集的读取部分,因为我的数据集标注和您论文的方式不太一样,但是训练时报错 ``` File "rpnet.py", line 359, in YI = [[int(ee) for ee in el.split('_')[:7]] for el in labels] ValueError: invalid literal for int() with base 10: 'A2' ``` 以及在rpnet.py文件的379行也就是...
模型文件
你们有没有wR2.pth模型文件,我用你们的wR2.pth文件训练出来的fh02.pth模型发现对车牌位置都没框对
Hey, could please describe the implementation details, such as the training set and test set partitioning and training process of other subset(excluding the CCPD-Base). These question are not described in...
训练中把解析的车牌标注打印了一下,发现绝大部分车牌都是皖牌的,而且是皖A。
说好的publicly available呢???
例如 ``` 0727777777778-90_84-91&434_564&598-559&583_105&579_95&452_550&457-0_0_15_29_15_33_32-120-426.jpg ``` https://imgur.com/HXXPdTE 这里第一项0727777777778,根据readme的说法是牌照面积和图片面积的比值 请问该怎么理解呢,理解成 (牌照像素数 / 图片总像素数)=0.72也显然不正确 以及亮度和模糊度采用的是什么样的度量标准? 谢谢
使用命令 : python wR2.py -i /root/mt/cimg/home/booy/booy/ccpd_dataset/ccpd_db/ -b 4 报错内容 /usr/local/lib/python3.6/dist-packages/torch/optim/lr_scheduler.py:100: UserWarning: Detected call of `lr_scheduler.step()` before `optimizer.step()`. In PyTorch 1.1.0 and later, you should call them in the opposite order:...