【解决错误】ValueError: axes don't match array

最新推荐文章于 2024-10-17 11:01:30 发布

不会飞的鹰08

最新推荐文章于 2024-10-17 11:01:30 发布

阅读量3w

点赞数 2

本文链接：https://blog.csdn.net/weixin_41449637/article/details/103578188

版权

本文详细解析了在使用PyTorch进行面部特征点检测训练时遇到的数据加载错误，指出图片通道不一致导致的问题，并提供了解决方案，即统一图片读取模式为RGB，确保数据预处理的一致性。

摘要生成于 C知道，由 DeepSeek-R1 满血版支持，前往体验 >

Original Traceback (most recent call last):
  File "/home/cody/anaconda3/envs/pytorch/lib/python3.6/site-packages/torch/utils/data/_utils/worker.py", line 178, in _worker_loop
    data = fetcher.fetch(index)
  File "/home/cody/anaconda3/envs/pytorch/lib/python3.6/site-packages/torch/utils/data/_utils/fetch.py", line 44, in fetch
    data = [self.dataset[idx] for idx in possibly_batched_index]
  File "/home/cody/anaconda3/envs/pytorch/lib/python3.6/site-packages/torch/utils/data/_utils/fetch.py", line 44, in <listcomp>
    data = [self.dataset[idx] for idx in possibly_batched_index]
  File "/home/cody/anaconda3/envs/pytorch/lib/python3.6/site-packages/torch/utils/data/dataset.py", line 256, in __getitem__
    return self.dataset[self.indices[idx]]
  File "/home/cody/anaconda3/envs/pytorch/lib/python3.6/site-packages/torch/utils/data/dataset.py", line 206, in __getitem__
    return self.datasets[dataset_idx][sample_idx]
  File "/home/cody/PycharmProjects/ONET/Facial_Landmark_Detection/train_test/datasets.py", line 314, in __getitem__
    image_t = np.transpose(image_t, (2, 0, 1))
  File "<__array_function__ internals>", line 6, in transpose
  File "/home/cody/anaconda3/envs/pytorch/lib/python3.6/site-packages/numpy/core/fromnumeric.py", line 650, in transpose
    return _wrapfunc(a, 'transpose', axes)
  File "/home/cody/anaconda3/envs/pytorch/lib/python3.6/site-packages/numpy/core/fromnumeric.py", line 61, in _wrapfunc
    return bound(*args, **kwds)
ValueError: axes don't match array

解决办法：

image = np.array(Image.open(img_name))

更改为：

image = np.array(Image.open(img_name).convert("RGB"))

图片文件下的图，有的是单通道，有的是三通道，转化下读图模式即可