If there is a 2d input, the second dimension represents Channel, it’s nature. But I cannot understand why is the same in 3d input?

```
# size:3*2 , 3 tensors, each have 2 channels
input=[[121,31,14][4,41,41]]
# size:2*3*2 , 2 batches, each batch contains 3 tensors, each have 2 channels
# why BatchNorm1d suggest the second dimension is channel dimension?
input=[[[121,31,14][4,41,41]],[[11,1,14][4,314,1]]]
```