PyTorch 加载数据集PIL.Image和numpy相互转化出现 TypeError: Cannot handle this data type的问题

PyTorch 加载数据集PIL.Image和numpy相互转化出现 TypeError: Cannot handle this data type的问题

pytorch 加载图片数据集通常会使用 PIL读入图片，进行一些预处理转化为Tensor并有dataloader加载进行训练或测试。有时候我们对图像的预处理要求较高，PIL库无法快捷的完成，常常会用numpy数据辅助完成。但是使用不当也会造成一些问题，例如：

Traceback (most recent call last):
  File "train.py", line 288, in <module>
    main()
  File "train.py", line 231, in main
    for i, (frontRGB, rePro, topRGB) in enumerate(trainDataLoader):
  File "/usr/local/lib/python3.7/dist-packages/torch/utils/data/dataloader.py", line 345, in __next__
    data = self._next_data()
  File "/usr/local/lib/python3.7/dist-packages/torch/utils/data/dataloader.py", line 856, in _next_data
    return self._process_data(data)
  File "/usr/local/lib/python3.7/dist-packages/torch/utils/data/dataloader.py", line 881, in _process_data
    data.reraise()
  File "/usr/local/lib/python3.7/dist-packages/torch/_utils.py", line 394, in reraise
    raise self.exc_type(msg)
TypeError: Caught TypeError in DataLoader worker process 0.
Original Traceback (most recent call last):
  File "/usr/local/lib/python3.7/dist-packages/PIL/Image.py", line 2533, in fromarray
    mode, rawmode = _fromarray_typemap[typekey]
KeyError: ((1, 1, 3), '<f8')

During handling of the above exception, another exception occurred:

Traceback (most recent call last):
  File "/usr/local/lib/python3.7/dist-packages/torch/utils/data/_utils/worker.py", line 178, in _worker_loop
    data = fetcher.fetch(index)
  File "/usr/local/lib/python3.7/dist-packages/torch/utils/data/_utils/fetch.py", line 44, in fetch
    data = [self.dataset[idx] for idx in possibly_batched_index]
  File "/usr/local/lib/python3.7/dist-packages/torch/utils/data/_utils/fetch.py", line 44, in <listcomp>
    data = [self.dataset[idx] for idx in possibly_batched_index]
  File "/home/username/Project/viewSynthesis/crossViewWithDepth/src/datasets.py", line 52, in __getitem__
    img= Image.fromarray(img)
  File "/usr/local/lib/python3.7/dist-packages/PIL/Image.py", line 2535, in fromarray
    raise TypeError("Cannot handle this data type")
TypeError: Cannot handle this data type

这里其实爆出了两个问题，第一是dataloader的报错：

TypeError: Caught TypeError in DataLoader worker process 0.

这是dataloader无法正常加载数据集的错误信息，其原因可能有很多。包括dataset类中__getitem__方法有误等，当然由于numpy与Image相互转化问题导致无法正常返回数据也会报这个错，所以这个信息比较宽泛，如果遇到需要具体分析。
这里又出现了另一个错误信息;

TypeError: Cannot handle this data type

这里的错误产生位置指向了：img= Image.fromarray(img)这一行。我这里通过将img转化为np.ndarray从而进行了更复杂的图像预处理，但是转为图像出了错。这是因为fromarray默认会将图像转为uint8类型（也就是RGB每个通道由8bit表示的图像格式），一旦输入的np数组不是这个格式，就无法正常转化。因此我们需要：

img= Image.fromarray(np.uint8(img))

先将数组转化为uint8再转为图像就没有问题了。
更严格一点可以：

img= Image.fromarray(np.uint8(img)).convert('RGB')

保证图像的格式、通道等。