clip_boxes_to_image

Clip boxes so that they lie inside an image of size <code>size</code>.

Provides access to datasets, models and preprocessing
facilities for deep learning with images. Integrates seamlessly
with the 'torch' package and it's 'API' borrows heavily from
'PyTorch' vision package.

Daniel Falbel

torchvision

Models, Datasets and Transformations for Images

Christophe Regouby

Akanksha Koshti

Derrick Richard

 RStudio

clip_boxes_to_image function

<dl><dt>boxes</dt>
<dd>(Tensor[N, 4]): boxes in \((x_{min}, y_{min}, x_{max}, y_{max})\) format
with<ul>
<li>\(0 \leq x_{min} &lt; x_{max}\) and</li>
<li>\(0 \leq y_{min} &lt; y_{max}\).</li>
</ul></dd>
<dt>size</dt>
<dd>(Tuple[height, width]): size of the image</dd></dl>

Arguments

Clip Boxes to Image — clip_boxes_to_image

<dl>

<dt>boxes</dt>
<dd>(Tensor[N, 4]): boxes in \((x_{min}, y_{min}, x_{max}, y_{max})\) format
with<ul>
<li>\(0 \leq x_{min} &lt; x_{max}\) and</li>
<li>\(0 \leq y_{min} &lt; y_{max}\).</li>
</ul></dd>


<dt>size</dt>
<dd>(Tuple[height, width]): size of the image</dd>

</dl>

clip_boxes_to_image: Clip Boxes to Image

Description

Usage

Value

Arguments