.. _l-onnx-doc-Crop:

====
Crop
====

.. contents::
    :local:


.. _l-onnx-op-crop-1:

Crop - 1
========

**Version**

* **name**: `Crop (GitHub) <https://github.com/onnx/onnx/blob/main/docs/Operators.md#Crop>`_
* **domain**: **main**
* **since_version**: **1**
* **function**:
* **support_level**:
* **shape inference**:

This version of the operator has been available
**since version 1**.

**Summary**

Crop and image to the specified spatial dimensions. If scale is given,
then optionally start the crop offset by the left/top border amounts.
If scale is not provided, crop the borders as provided.

**Attributes**

* **border**:
  A 1-D values of (leftBorder, topBorder, rightBorder, bottomBorder). Default value is ``?``.
* **scale**:
  A 1-D values of (height, width). Default value is ``?``.

**Inputs**

* **input** (heterogeneous) - **T**:
  Input tensor of shape [N,C,H,W]

**Outputs**

* **output** (heterogeneous) - **T**:
  Result, has same type as input, with H and W dimensions reduced.

**Examples**