chhanxiao / license-plate-recoginition Goto Github PK

File "gen_data.py", line 70, in main
img, lab, color = gen()
File "gen_data.py", line 35, in call
com = aug(image=com)['image']
File "D:\Anaconda3\envs\zx_plate\lib\site-packages\albumentations\core\composition.py", line 210, in call
data = t(force_apply=force_apply, **data)
File "D:\Anaconda3\envs\zx_plate\lib\site-packages\albumentations\core\transforms_interface.py", line 97, in call
return self.apply_with_params(params, **kwargs)
File "D:\Anaconda3\envs\zx_plate\lib\site-packages\albumentations\core\transforms_interface.py", line 112, in apply_with_params
res[key] = target_function(arg, **dict(params, **target_dependencies))
File "D:\Anaconda3\envs\zx_plate\lib\site-packages\albumentations\augmentations\geometric\transforms.py", line 868, in apply
return F.piecewise_affine(img, matrix, self.interpolation, self.mode, self.cval)
File "D:\Anaconda3\envs\zx_plate\lib\site-packages\albumentations\augmentations\functional.py", line 40, in wrapped_function
return clip(func(img, *args, **kwargs), dtype, maxval)
File "D:\Anaconda3\envs\zx_plate\lib\site-packages\albumentations\augmentations\geometric\functional.py", line 614, in piecewise_affine
img, matrix, order=interpolation, mode=mode, cval=cval, preserve_range=True, output_shape=img.shape
File "D:\Anaconda3\envs\zx_plate\lib\site-packages\skimage\transform_warps.py", line 976, in warp
coords = warp_coords(coord_map, output_shape)
File "D:\Anaconda3\envs\zx_plate\lib\site-packages\skimage\transform_warps.py", line 675, in warp_coords
tf_coords = coord_map(tf_coords)
File "D:\Anaconda3\envs\zx_plate\lib\site-packages\skimage\transform_warps.py", line 967, in coord_map
return inverse_map(*args, **map_args)
TypeError: 'NoneType' object is not callable

在运行一段时间后会出现该错误，请问博主该怎么解决呢？

博主您好，想问一下为啥要将LPR的输出序列长度设置为18呢

Traceback (most recent call last):
File "E:/PycharmProjects/Vehicle_Detection/license-plate-recoginition-main/license-plate-recoginition-main/train.py", line 100, in
main(args)
File "E:/PycharmProjects/Vehicle_Detection/license-plate-recoginition-main/license-plate-recoginition-main/train.py", line 57, in main
drop_last=True,
File "C:\Users\wangwy\Anaconda3\lib\site-packages\torch\utils\data\dataloader.py", line 266, in init
sampler = RandomSampler(dataset, generator=generator) # type: ignore
File "C:\Users\wangwy\Anaconda3\lib\site-packages\torch\utils\data\sampler.py", line 104, in init
"value, but got num_samples={}".format(self.num_samples))
ValueError: num_samples should be a positive integer value, but got num_samples=0

Thanks so much for your work, but I have trouble getting this file.(https://github.com/ChHanXiao/license-plate-recoginition/blob/main/datasets/prepare_ccpd.py) It seems this file is not valid anymore. Could your please provide a new link?

代码里的权重是否包含特殊车辆和双行车牌的训练，测试代码在哪里还是自己写一个

车牌放入真实场景是如何操作的

请问网络中torch.split起到了什么作用，试图将双行切割？那么单行得那？请问那部分可以最有效得针对双行识别