# tensorplay.functional.unflatten

Source: https://www.tensorplay.cn/docs/generated/tensorplay.functional.unflatten.html

```python
tensorplay.functional.unflatten(input, dim, sizes) → Tensor
```

Expands a dimension of the input tensor over multiple dimensions.

> **See also**
>
> tensorplay.flatten() the inverse of this function. It coalesces several dimensions into one.

Parameters:

- input ([Tensor](/docs/generated/tensorplay.Tensor.html#tensorplay.Tensor)) – the input tensor.

- dim ([int](https://docs.python.org/3/builtins/functions.html#int)) – Dimension to be unflattened, specified as an index into input.shape.

- sizes (Tuple[[int](https://docs.python.org/3/builtins/functions.html#int)]) – New shape of the unflattened dimension. One of its elements can be -1 in which case the corresponding output dimension is inferred. Otherwise, the product of sizes must equal input.shape[dim].

Returns:

A View of input with the specified dimension unflattened.

Examples::

```
>>> tensorplay.unflatten(tensorplay.randn(3, 4, 1), 1, (2, 2)).shape
tensorplay.Size([3, 2, 2, 1])
>>> tensorplay.unflatten(tensorplay.randn(3, 4, 1), 1, (-1, 2)).shape
tensorplay.Size([3, 2, 2, 1])
>>> tensorplay.unflatten(tensorplay.randn(5, 12, 3), -2, (2, 2, 3, 1, 1)).shape
tensorplay.Size([5, 2, 2, 3, 1, 1, 3])
```