CCPD

CCPD copied to clipboard

论抠图的方法

3

请问向two-stage网络的抠图也是和这个的解决办法一样吗，作者可以参考一下他们的实现方法

YaaYang

train error

1

in forward(self, x) 191 # input = Variable(torch.rand(2, 1, 10, 10), requires_grad=True) 192 # rois = Variable(torch.LongTensor([[0, 1, 2, 7, 8], [0, 3, 3, 8, 8], [1, 3, 3, 8,...

zhijieL387

iname = img_name.rsplit('/', 1)[-1].rsplit('.', 1)[0].split('-') [leftUp, rightDown] = [[int(eel) for eel in el.split('&')] for el in iname[2].split('_')] ori_w, ori_h = float(img.shape[1]), float(img.shape[0]) 这么获取[leftUp, rightDown] 以及ori_w, ori_h ，是正确的吗？ 我怎么觉得这样扣下来的车牌图会不完整啊？！

zhqx511

Run code for VIN number detection

2

Can I test code for Vehicle Identification Number(VIN) number recognition.

harshalcse

A preblem in file rpnet/rpnet.py

2

line376: loss += 0.8 * nn.L1Loss().cuda()(fps_pred[:][:2], y[:][:2]) line377: loss += 0.2 * nn.L1Loss().cuda()(fps_pred[:][2:], y[:][2:]) In the file rpnet.py ,we can know that these two lines refers the L1Loss about the...

SaulZhang

cpu

1

I am about to run the demo.py. If I only use **cpu**, how should I modify the code?

zihaozhang9

能否提供数据集中文件名称解析的代码么？

1

文件名称解析说明，没有详细对应例子，虽然说了包含的内容，但没有给出对应关系，麻烦提供一下解析代码

hengzhangmiivii

the jpeg diatortion

1

i run the demo.py with my own license plate images with different jpeg distortion level .but the accuaracy is extremely low . Is there something wrong ?

liujianzhao6328057

should the image size always be (480,480) in the demo.py?

liujianzhao6328057

poor generalization ability of model

1

I tested on the new data set, the accuracy is very low, but after training, the accuracy is high; I think the generalization ability of the model is very poor......

williu66