squeeze¶
- nvtripy.squeeze(input: Tensor, dims: Sequence[int] | int) Tensor [source]¶
Returns a new tensor with the specified singleton dimensions of the input tensor removed.
- Parameters:
input (Tensor) – [dtype=T1] The input tensor.
dims (Sequence[int] | int) – The dimension(s) to remove. These must have a length of 1.
- Returns:
[dtype=T1] A new tensor.
- Return type:
Example: Squeeze All Dimensions
1input = tp.iota((1, 2, 1), dtype=tp.float32) 2output = tp.squeeze(input, dims=(0, 2))
Local Variables¶>>> input tensor( [[[0], [0]]], dtype=float32, loc=gpu:0, shape=(1, 2, 1)) >>> output tensor([0, 0], dtype=float32, loc=gpu:0, shape=(2,))
Example: Squeeze First Dimension
1input = tp.iota((1, 2, 1), dtype=tp.float32) 2output = tp.squeeze(input, 0)
Local Variables¶>>> input tensor( [[[0], [0]]], dtype=float32, loc=gpu:0, shape=(1, 2, 1)) >>> output tensor( [[0], [0]], dtype=float32, loc=gpu:0, shape=(2, 1))
Example: Squeeze First And Third Dimension
1input = tp.iota((1, 2, 1), dtype=tp.float32) 2output = tp.squeeze(input, (0, 2))
Local Variables¶>>> input tensor( [[[0], [0]]], dtype=float32, loc=gpu:0, shape=(1, 2, 1)) >>> output tensor([0, 0], dtype=float32, loc=gpu:0, shape=(2,))