报错信息:TypeError: can't convert np.ndarray of type numpy.int32. The only supported types are: float64, float32, float16, int64, int32, int16, int8, uint8, and bool.
众所周知,在torch中,与numpy数组互相转换的API是torch.from_numpy() 或者.numpy()
但有时候,二者直接转换会遇到报错(下图第87行)
解决方法很简单,想到很难。 既先转为list,然后在转tensor:
labels = list(labels)
myLabel = torch.LongTensor(labels)
myLabel
Out[98]: tensor([0, 0, 0, ..., 7, 7, 7])