报错： ValueError: axes don't match array
ValueError:轴与数组不匹配 问题，下面是报错：
报错行代码经常为：image = np.transpose(image, (2, 0, 1))
这行代码的作用是调换整图像的shape顺序
[width, height, channels]
（2， 0， 1）即为结果的顺序
[channels, height, width]
0%| | 0/1 [00:00<?, ?it/s]Epoch: 0
0%| | 0/1 [00:00<?, ?it/s]
Traceback (most recent call last):
File "D:/cver/Others/Auto_Classification/Auto_Classification/train.py", line 174, in <module>
run(images_list, val_list)
File "D:/cver/Others/Auto_Classification/Auto_Classification/train.py", line 147, in run
train_one(train_dataloader, model, optimizer, loss_fn, None)
File "D:/cver/Others/Auto_Classification/Auto_Classification/train.py", line 76, in train_one
for bi, data in enumerate(tk):
File "D:\Users\11145999\AppData\Roaming\Python\Python37\site-packages\tqdm\std.py", line 1180, in __iter__
for obj in iterable:
File "D:\Users\11145999\AppData\Roaming\Python\Python37\site-packages\torch\utils\data\dataloader.py", line 521, in __next__
data = self._next_data()
File "D:\Users\11145999\AppData\Roaming\Python\Python37\site-packages\torch\utils\data\dataloader.py", line 561, in _next_data
data = self._dataset_fetcher.fetch(index) # may raise StopIteration
File "D:\Users\11145999\AppData\Roaming\Python\Python37\site-packages\torch\utils\data\_utils\fetch.py", line 49, in fetch
data = [self.dataset[idx] for idx in possibly_batched_index]
File "D:\Users\11145999\AppData\Roaming\Python\Python37\site-packages\torch\utils\data\_utils\fetch.py", line 49, in <listcomp>
data = [self.dataset[idx] for idx in possibly_batched_index]
File "D:/cver/Others/Auto_Classification/Auto_Classification/train.py", line 46, in __getitem__
"image": self.normalize(image),
File "D:/cver/Others/Auto_Classification/Auto_Classification/train.py", line 26, in normalize
image = np.transpose(image, (2, 0, 1)) # [3,224,224]
File "<__array_function__ internals>", line 6, in transpose
File "D:\Users\11145999\AppData\Roaming\Python\Python37\site-packages\numpy\core\fromnumeric.py", line 660, in transpose
return _wrapfunc(a, 'transpose', axes)
File "D:\Users\11145999\AppData\Roaming\Python\Python37\site-packages\numpy\core\fromnumeric.py", line 57, in _wrapfunc
return bound(*args, **kwds)
ValueError: axes don't match array但此时发生了一些问题，如果图像混杂进了灰度图等图片，那么这行代码就会报错（如上）
解决方法
from skimage.color import gray2rgb
image = Image.open(image_name)
if image.mode == 'L': # 判断是否为灰度图
image = gray2rgb(image) # 如果是，就转称彩色 （通道数变成三）
仔细看可以发发现，opencv 的坑，所以大家在一步步排查问题的时候，比如 当一个训练任务你原本能跑，换了数据后不能跑了，有可能就是混入了灰度图，你第一次看到ValueError: axes don't match array ，百度会说是维度问题，然后大家根据正常debug，用opencv读的图片，发现所有图片都是三通道，没问题，不过实际是opencv 的一个玩笑，大家看我上面的图片就知道了。本期opencv 坑 就到这，下期再见。