RandomPerspective in PyTorch

Buy Me a Coffee

*Memos:

• My post explains RandomRotation().
• My post explains RandomAffine().
• My post explains RandomHorizontalFlip().
• My post explains RandomVerticalFlip().
• My post explains OxfordIIITPet().

RandomPerspective() can do perspective transformation for zero or more images as shown below:

*Memos:

• The 1st argument for initialization is distortion_scale(Optional-Default:0.5-Type:int or float): *Memos:
  • It can do perspective transformation.
  • It must be 0 <= x <= 1.
• The 2nd argument for initialization is p(Optional-Default:0.5-Type:int or float): *Memos:
  • It’s the probability of whether each image is done with perspective transformation or not.
  • It must be 0 <= x <= 1.
• The 3rd argument for initialization is interpolation(Optional-Default:InterpolationMode.BILINEAR-Type:InterpolationMode).
• The 4th argument for initialization is fill(Optional-Default:0-Type:int, float or tuple/list(int or float)): *Memos:
  • It can change the background of images. *The background can be seen when doing perspective transformation for images.
  • A tuple/list must be the 1D with 1 or 3 elements.
• The 1st argument is img(Required-Type:PIL Image or tensor(int)): *Memos:
  • A tensor must be A 2D or more D.
  • Don’t use img=.
• v2 is recommended to use according to V1 or V2? Which one should I use?.

<span>from</span> <span>torchvision.datasets</span> <span>import</span> <span>OxfordIIITPet</span>
<span>from</span> <span>torchvision.transforms.v2</span> <span>import</span> <span>RandomPerspective</span>
<span>from</span> <span>torchvision.transforms.functional</span> <span>import</span> <span>InterpolationMode</span>
<span>randompers</span> <span>=</span> <span>RandomPerspective</span><span>()</span>
<span>randompers</span> <span>=</span> <span>RandomPerspective</span><span>(</span><span>distortion_scale</span><span>=</span><span>0.5</span><span>,</span>
                               <span>p</span><span>=</span><span>0.5</span><span>,</span>
                               <span>interpolation</span><span>=</span><span>InterpolationMode</span><span>.</span><span>BILINEAR</span><span>,</span>
                               <span>fill</span><span>=</span><span>0</span><span>)</span>
<span>randompers</span>
<span># RandomPerspective(p=0.5, # distortion_scale=0.5, # interpolation=InterpolationMode.BILINEAR, # fill=0) </span>
<span>randompers</span><span>.</span><span>distortion_scale</span>
<span># 0.5 </span>
<span>randompers</span><span>.</span><span>p</span>
<span># 0.5 </span>
<span>randompers</span><span>.</span><span>interpolation</span>
<span># <InterpolationMode.BILINEAR: 'bilinear'> </span>
<span>randompers</span><span>.</span><span>fill</span>
<span># 0 </span>
<span>origin_data</span> <span>=</span> <span>OxfordIIITPet</span><span>(</span>
    <span>root</span><span>=</span><span>"</span><span>data</span><span>"</span><span>,</span>
    <span>transform</span><span>=</span><span>None</span>
    <span># transform=RandomPerspective(distortion_scale=0) </span>    <span># transform=RandomPerspective(p=0) </span><span>)</span>
<span>dis02p1_data</span> <span>=</span> <span>OxfordIIITPet</span><span>(</span>
    <span>root</span><span>=</span><span>"</span><span>data</span><span>"</span><span>,</span>
    <span>transform</span><span>=</span><span>RandomPerspective</span><span>(</span><span>distortion_scale</span><span>=</span><span>0.2</span><span>,</span> <span>p</span><span>=</span><span>1</span><span>)</span>
<span>)</span>
<span>dis06p1_data</span> <span>=</span> <span>OxfordIIITPet</span><span>(</span>
    <span>root</span><span>=</span><span>"</span><span>data</span><span>"</span><span>,</span>
    <span>transform</span><span>=</span><span>RandomPerspective</span><span>(</span><span>distortion_scale</span><span>=</span><span>0.6</span><span>,</span> <span>p</span><span>=</span><span>1</span><span>)</span>
<span>)</span>
<span>dis1p1_data</span> <span>=</span> <span>OxfordIIITPet</span><span>(</span>
    <span>root</span><span>=</span><span>"</span><span>data</span><span>"</span><span>,</span>
    <span>transform</span><span>=</span><span>RandomPerspective</span><span>(</span><span>distortion_scale</span><span>=</span><span>1</span><span>,</span> <span>p</span><span>=</span><span>1</span><span>)</span>
<span>)</span>
<span>p1_data</span> <span>=</span> <span>OxfordIIITPet</span><span>(</span>
    <span>root</span><span>=</span><span>"</span><span>data</span><span>"</span><span>,</span>
    <span>transform</span><span>=</span><span>RandomPerspective</span><span>(</span><span>p</span><span>=</span><span>1</span><span>)</span>
<span>)</span>
<span>p05_data</span> <span>=</span> <span>OxfordIIITPet</span><span>(</span>
    <span>root</span><span>=</span><span>"</span><span>data</span><span>"</span><span>,</span>
    <span>transform</span><span>=</span><span>RandomPerspective</span><span>(</span><span>p</span><span>=</span><span>0.5</span><span>)</span>
<span>)</span>
<span>p1fillgray_data</span> <span>=</span> <span>OxfordIIITPet</span><span>(</span>
    <span>root</span><span>=</span><span>"</span><span>data</span><span>"</span><span>,</span>
    <span>transform</span><span>=</span><span>RandomPerspective</span><span>(</span><span>p</span><span>=</span><span>1</span><span>,</span> <span>fill</span><span>=</span><span>150</span><span>)</span>
<span>)</span>
<span>p1fillpurple_data</span> <span>=</span> <span>OxfordIIITPet</span><span>(</span>
    <span>root</span><span>=</span><span>"</span><span>data</span><span>"</span><span>,</span>
    <span>transform</span><span>=</span><span>RandomPerspective</span><span>(</span><span>p</span><span>=</span><span>1</span><span>,</span> <span>fill</span><span>=</span><span>[</span><span>160</span><span>,</span> <span>32</span><span>,</span> <span>240</span><span>])</span>
<span>)</span>
<span>import</span> <span>matplotlib.pyplot</span> <span>as</span> <span>plt</span>
<span>def</span> <span>show_images1</span><span>(</span><span>data</span><span>,</span> <span>main_title</span><span>=</span><span>None</span><span>):</span>
    <span>plt</span><span>.</span><span>figure</span><span>(</span><span>figsize</span><span>=</span><span>(</span><span>10</span><span>,</span> <span>5</span><span>))</span>
    <span>plt</span><span>.</span><span>suptitle</span><span>(</span><span>t</span><span>=</span><span>main_title</span><span>,</span> <span>y</span><span>=</span><span>0.8</span><span>,</span> <span>fontsize</span><span>=</span><span>14</span><span>)</span>
    <span>for</span> <span>i</span><span>,</span> <span>(</span><span>im</span><span>,</span> <span>_</span><span>)</span> <span>in</span> <span>zip</span><span>(</span><span>range</span><span>(</span><span>1</span><span>,</span> <span>6</span><span>),</span> <span>data</span><span>):</span>
        <span>plt</span><span>.</span><span>subplot</span><span>(</span><span>1</span><span>,</span> <span>5</span><span>,</span> <span>i</span><span>)</span>
        <span>plt</span><span>.</span><span>imshow</span><span>(</span><span>X</span><span>=</span><span>im</span><span>)</span>
        <span>plt</span><span>.</span><span>xticks</span><span>(</span><span>ticks</span><span>=</span><span>[])</span>
        <span>plt</span><span>.</span><span>yticks</span><span>(</span><span>ticks</span><span>=</span><span>[])</span>
    <span>plt</span><span>.</span><span>tight_layout</span><span>()</span>
    <span>plt</span><span>.</span><span>show</span><span>()</span>
<span>show_images1</span><span>(</span><span>data</span><span>=</span><span>origin_data</span><span>,</span> <span>main_title</span><span>=</span><span>"</span><span>origin_data</span><span>"</span><span>)</span>
<span>show_images1</span><span>(</span><span>data</span><span>=</span><span>dis02p1_data</span><span>,</span> <span>main_title</span><span>=</span><span>"</span><span>dis02p1_data</span><span>"</span><span>)</span>
<span>show_images1</span><span>(</span><span>data</span><span>=</span><span>dis06p1_data</span><span>,</span> <span>main_title</span><span>=</span><span>"</span><span>dis06p1_data</span><span>"</span><span>)</span>
<span>show_images1</span><span>(</span><span>data</span><span>=</span><span>dis1p1_data</span><span>,</span> <span>main_title</span><span>=</span><span>"</span><span>dis1p1_data</span><span>"</span><span>)</span>
<span>show_images1</span><span>(</span><span>data</span><span>=</span><span>p1_data</span><span>,</span> <span>main_title</span><span>=</span><span>"</span><span>p1_data</span><span>"</span><span>)</span>
<span>show_images1</span><span>(</span><span>data</span><span>=</span><span>p05_data</span><span>,</span> <span>main_title</span><span>=</span><span>"</span><span>p05_data</span><span>"</span><span>)</span>
<span>show_images1</span><span>(</span><span>data</span><span>=</span><span>p1fillgray_data</span><span>,</span> <span>main_title</span><span>=</span><span>"</span><span>p1fillgray_data</span><span>"</span><span>)</span>
<span>show_images1</span><span>(</span><span>data</span><span>=</span><span>p1fillpurple_data</span><span>,</span> <span>main_title</span><span>=</span><span>"</span><span>p1fillpurple_data</span><span>"</span><span>)</span>
<span># ↓ ↓ ↓ ↓ ↓ ↓ The code below is identical to the code above. ↓ ↓ ↓ ↓ ↓ ↓ </span><span>def</span> <span>show_images2</span><span>(</span><span>data</span><span>,</span> <span>main_title</span><span>=</span><span>None</span><span>,</span> <span>d</span><span>=</span><span>0.5</span><span>,</span> <span>prob</span><span>=</span><span>0.5</span><span>,</span> <span>f</span><span>=</span><span>0</span><span>):</span>
    <span>plt</span><span>.</span><span>figure</span><span>(</span><span>figsize</span><span>=</span><span>(</span><span>10</span><span>,</span> <span>5</span><span>))</span>
    <span>plt</span><span>.</span><span>suptitle</span><span>(</span><span>t</span><span>=</span><span>main_title</span><span>,</span> <span>y</span><span>=</span><span>0.8</span><span>,</span> <span>fontsize</span><span>=</span><span>14</span><span>)</span>
    <span>for</span> <span>i</span><span>,</span> <span>(</span><span>im</span><span>,</span> <span>_</span><span>)</span> <span>in</span> <span>zip</span><span>(</span><span>range</span><span>(</span><span>1</span><span>,</span> <span>6</span><span>),</span> <span>data</span><span>):</span>
        <span>plt</span><span>.</span><span>subplot</span><span>(</span><span>1</span><span>,</span> <span>5</span><span>,</span> <span>i</span><span>)</span>
        <span>rp</span> <span>=</span> <span>RandomPerspective</span><span>(</span><span>distortion_scale</span><span>=</span><span>d</span><span>,</span> <span>p</span><span>=</span><span>prob</span><span>,</span> <span>fill</span><span>=</span><span>f</span><span>)</span> <span># Here </span>        <span>plt</span><span>.</span><span>imshow</span><span>(</span><span>X</span><span>=</span><span>rp</span><span>(</span><span>im</span><span>))</span> <span># Here </span>        <span>plt</span><span>.</span><span>xticks</span><span>(</span><span>ticks</span><span>=</span><span>[])</span>
        <span>plt</span><span>.</span><span>yticks</span><span>(</span><span>ticks</span><span>=</span><span>[])</span>
    <span>plt</span><span>.</span><span>tight_layout</span><span>()</span>
    <span>plt</span><span>.</span><span>show</span><span>()</span>
<span>show_images2</span><span>(</span><span>data</span><span>=</span><span>origin_data</span><span>,</span> <span>main_title</span><span>=</span><span>"</span><span>origin_data</span><span>"</span><span>,</span> <span>d</span><span>=</span><span>0</span><span>)</span>
<span>show_images2</span><span>(</span><span>data</span><span>=</span><span>origin_data</span><span>,</span> <span>main_title</span><span>=</span><span>"</span><span>dis02p1_data</span><span>"</span><span>,</span> <span>d</span><span>=</span><span>0.2</span><span>,</span> <span>prob</span><span>=</span><span>1</span><span>)</span>
<span>show_images2</span><span>(</span><span>data</span><span>=</span><span>origin_data</span><span>,</span> <span>main_title</span><span>=</span><span>"</span><span>dis06p1_data</span><span>"</span><span>,</span> <span>d</span><span>=</span><span>0.6</span><span>,</span> <span>prob</span><span>=</span><span>1</span><span>)</span>
<span>show_images2</span><span>(</span><span>data</span><span>=</span><span>origin_data</span><span>,</span> <span>main_title</span><span>=</span><span>"</span><span>dis1p1_data</span><span>"</span><span>,</span> <span>d</span><span>=</span><span>1</span><span>,</span> <span>prob</span><span>=</span><span>1</span><span>)</span>
<span>show_images2</span><span>(</span><span>data</span><span>=</span><span>origin_data</span><span>,</span> <span>main_title</span><span>=</span><span>"</span><span>p1_data</span><span>"</span><span>,</span> <span>prob</span><span>=</span><span>1</span><span>)</span>
<span>show_images2</span><span>(</span><span>data</span><span>=</span><span>origin_data</span><span>,</span> <span>main_title</span><span>=</span><span>"</span><span>p05_data</span><span>"</span><span>,</span> <span>prob</span><span>=</span><span>0.5</span><span>)</span>
<span>show_images2</span><span>(</span><span>data</span><span>=</span><span>origin_data</span><span>,</span> <span>main_title</span><span>=</span><span>"</span><span>p1fillgray_data</span><span>"</span><span>,</span> <span>prob</span><span>=</span><span>1</span><span>,</span> <span>f</span><span>=</span><span>150</span><span>)</span>
<span>show_images2</span><span>(</span><span>data</span><span>=</span><span>origin_data</span><span>,</span> <span>main_title</span><span>=</span><span>"</span><span>p1fillpurple_data</span><span>"</span><span>,</span> <span>prob</span><span>=</span><span>1</span><span>,</span>
             <span>f</span><span>=</span><span>[</span><span>160</span><span>,</span> <span>32</span><span>,</span> <span>240</span><span>])</span>
<span>from</span> <span>torchvision.datasets</span> <span>import</span> <span>OxfordIIITPet</span>
<span>from</span> <span>torchvision.transforms.v2</span> <span>import</span> <span>RandomPerspective</span>
<span>from</span> <span>torchvision.transforms.functional</span> <span>import</span> <span>InterpolationMode</span>

<span>randompers</span> <span>=</span> <span>RandomPerspective</span><span>()</span>
<span>randompers</span> <span>=</span> <span>RandomPerspective</span><span>(</span><span>distortion_scale</span><span>=</span><span>0.5</span><span>,</span>
                               <span>p</span><span>=</span><span>0.5</span><span>,</span>
                               <span>interpolation</span><span>=</span><span>InterpolationMode</span><span>.</span><span>BILINEAR</span><span>,</span>
                               <span>fill</span><span>=</span><span>0</span><span>)</span>
<span>randompers</span>
<span># RandomPerspective(p=0.5, # distortion_scale=0.5, # interpolation=InterpolationMode.BILINEAR, # fill=0) </span>
<span>randompers</span><span>.</span><span>distortion_scale</span>
<span># 0.5 </span>
<span>randompers</span><span>.</span><span>p</span>
<span># 0.5 </span>
<span>randompers</span><span>.</span><span>interpolation</span>
<span># <InterpolationMode.BILINEAR: 'bilinear'> </span>
<span>randompers</span><span>.</span><span>fill</span>
<span># 0 </span>
<span>origin_data</span> <span>=</span> <span>OxfordIIITPet</span><span>(</span>
    <span>root</span><span>=</span><span>"</span><span>data</span><span>"</span><span>,</span>
    <span>transform</span><span>=</span><span>None</span>
    <span># transform=RandomPerspective(distortion_scale=0) </span>    <span># transform=RandomPerspective(p=0) </span><span>)</span>

<span>dis02p1_data</span> <span>=</span> <span>OxfordIIITPet</span><span>(</span>
    <span>root</span><span>=</span><span>"</span><span>data</span><span>"</span><span>,</span>
    <span>transform</span><span>=</span><span>RandomPerspective</span><span>(</span><span>distortion_scale</span><span>=</span><span>0.2</span><span>,</span> <span>p</span><span>=</span><span>1</span><span>)</span>
<span>)</span>

<span>dis06p1_data</span> <span>=</span> <span>OxfordIIITPet</span><span>(</span>
    <span>root</span><span>=</span><span>"</span><span>data</span><span>"</span><span>,</span>
    <span>transform</span><span>=</span><span>RandomPerspective</span><span>(</span><span>distortion_scale</span><span>=</span><span>0.6</span><span>,</span> <span>p</span><span>=</span><span>1</span><span>)</span>
<span>)</span>

<span>dis1p1_data</span> <span>=</span> <span>OxfordIIITPet</span><span>(</span>
    <span>root</span><span>=</span><span>"</span><span>data</span><span>"</span><span>,</span>
    <span>transform</span><span>=</span><span>RandomPerspective</span><span>(</span><span>distortion_scale</span><span>=</span><span>1</span><span>,</span> <span>p</span><span>=</span><span>1</span><span>)</span>
<span>)</span>

<span>p1_data</span> <span>=</span> <span>OxfordIIITPet</span><span>(</span>
    <span>root</span><span>=</span><span>"</span><span>data</span><span>"</span><span>,</span>
    <span>transform</span><span>=</span><span>RandomPerspective</span><span>(</span><span>p</span><span>=</span><span>1</span><span>)</span>
<span>)</span>

<span>p05_data</span> <span>=</span> <span>OxfordIIITPet</span><span>(</span>
    <span>root</span><span>=</span><span>"</span><span>data</span><span>"</span><span>,</span>
    <span>transform</span><span>=</span><span>RandomPerspective</span><span>(</span><span>p</span><span>=</span><span>0.5</span><span>)</span>
<span>)</span>

<span>p1fillgray_data</span> <span>=</span> <span>OxfordIIITPet</span><span>(</span>
    <span>root</span><span>=</span><span>"</span><span>data</span><span>"</span><span>,</span>
    <span>transform</span><span>=</span><span>RandomPerspective</span><span>(</span><span>p</span><span>=</span><span>1</span><span>,</span> <span>fill</span><span>=</span><span>150</span><span>)</span>
<span>)</span>

<span>p1fillpurple_data</span> <span>=</span> <span>OxfordIIITPet</span><span>(</span>
    <span>root</span><span>=</span><span>"</span><span>data</span><span>"</span><span>,</span>
    <span>transform</span><span>=</span><span>RandomPerspective</span><span>(</span><span>p</span><span>=</span><span>1</span><span>,</span> <span>fill</span><span>=</span><span>[</span><span>160</span><span>,</span> <span>32</span><span>,</span> <span>240</span><span>])</span>
<span>)</span>

<span>import</span> <span>matplotlib.pyplot</span> <span>as</span> <span>plt</span>

<span>def</span> <span>show_images1</span><span>(</span><span>data</span><span>,</span> <span>main_title</span><span>=</span><span>None</span><span>):</span>
    <span>plt</span><span>.</span><span>figure</span><span>(</span><span>figsize</span><span>=</span><span>(</span><span>10</span><span>,</span> <span>5</span><span>))</span>
    <span>plt</span><span>.</span><span>suptitle</span><span>(</span><span>t</span><span>=</span><span>main_title</span><span>,</span> <span>y</span><span>=</span><span>0.8</span><span>,</span> <span>fontsize</span><span>=</span><span>14</span><span>)</span>
    <span>for</span> <span>i</span><span>,</span> <span>(</span><span>im</span><span>,</span> <span>_</span><span>)</span> <span>in</span> <span>zip</span><span>(</span><span>range</span><span>(</span><span>1</span><span>,</span> <span>6</span><span>),</span> <span>data</span><span>):</span>
        <span>plt</span><span>.</span><span>subplot</span><span>(</span><span>1</span><span>,</span> <span>5</span><span>,</span> <span>i</span><span>)</span>
        <span>plt</span><span>.</span><span>imshow</span><span>(</span><span>X</span><span>=</span><span>im</span><span>)</span>
        <span>plt</span><span>.</span><span>xticks</span><span>(</span><span>ticks</span><span>=</span><span>[])</span>
        <span>plt</span><span>.</span><span>yticks</span><span>(</span><span>ticks</span><span>=</span><span>[])</span>
    <span>plt</span><span>.</span><span>tight_layout</span><span>()</span>
    <span>plt</span><span>.</span><span>show</span><span>()</span>

<span>show_images1</span><span>(</span><span>data</span><span>=</span><span>origin_data</span><span>,</span> <span>main_title</span><span>=</span><span>"</span><span>origin_data</span><span>"</span><span>)</span>
<span>show_images1</span><span>(</span><span>data</span><span>=</span><span>dis02p1_data</span><span>,</span> <span>main_title</span><span>=</span><span>"</span><span>dis02p1_data</span><span>"</span><span>)</span>
<span>show_images1</span><span>(</span><span>data</span><span>=</span><span>dis06p1_data</span><span>,</span> <span>main_title</span><span>=</span><span>"</span><span>dis06p1_data</span><span>"</span><span>)</span>
<span>show_images1</span><span>(</span><span>data</span><span>=</span><span>dis1p1_data</span><span>,</span> <span>main_title</span><span>=</span><span>"</span><span>dis1p1_data</span><span>"</span><span>)</span>
<span>show_images1</span><span>(</span><span>data</span><span>=</span><span>p1_data</span><span>,</span> <span>main_title</span><span>=</span><span>"</span><span>p1_data</span><span>"</span><span>)</span>
<span>show_images1</span><span>(</span><span>data</span><span>=</span><span>p05_data</span><span>,</span> <span>main_title</span><span>=</span><span>"</span><span>p05_data</span><span>"</span><span>)</span>
<span>show_images1</span><span>(</span><span>data</span><span>=</span><span>p1fillgray_data</span><span>,</span> <span>main_title</span><span>=</span><span>"</span><span>p1fillgray_data</span><span>"</span><span>)</span>
<span>show_images1</span><span>(</span><span>data</span><span>=</span><span>p1fillpurple_data</span><span>,</span> <span>main_title</span><span>=</span><span>"</span><span>p1fillpurple_data</span><span>"</span><span>)</span>

<span># ↓ ↓ ↓ ↓ ↓ ↓ The code below is identical to the code above. ↓ ↓ ↓ ↓ ↓ ↓ </span><span>def</span> <span>show_images2</span><span>(</span><span>data</span><span>,</span> <span>main_title</span><span>=</span><span>None</span><span>,</span> <span>d</span><span>=</span><span>0.5</span><span>,</span> <span>prob</span><span>=</span><span>0.5</span><span>,</span> <span>f</span><span>=</span><span>0</span><span>):</span>
    <span>plt</span><span>.</span><span>figure</span><span>(</span><span>figsize</span><span>=</span><span>(</span><span>10</span><span>,</span> <span>5</span><span>))</span>
    <span>plt</span><span>.</span><span>suptitle</span><span>(</span><span>t</span><span>=</span><span>main_title</span><span>,</span> <span>y</span><span>=</span><span>0.8</span><span>,</span> <span>fontsize</span><span>=</span><span>14</span><span>)</span>
    <span>for</span> <span>i</span><span>,</span> <span>(</span><span>im</span><span>,</span> <span>_</span><span>)</span> <span>in</span> <span>zip</span><span>(</span><span>range</span><span>(</span><span>1</span><span>,</span> <span>6</span><span>),</span> <span>data</span><span>):</span>
        <span>plt</span><span>.</span><span>subplot</span><span>(</span><span>1</span><span>,</span> <span>5</span><span>,</span> <span>i</span><span>)</span>
        <span>rp</span> <span>=</span> <span>RandomPerspective</span><span>(</span><span>distortion_scale</span><span>=</span><span>d</span><span>,</span> <span>p</span><span>=</span><span>prob</span><span>,</span> <span>fill</span><span>=</span><span>f</span><span>)</span> <span># Here </span>        <span>plt</span><span>.</span><span>imshow</span><span>(</span><span>X</span><span>=</span><span>rp</span><span>(</span><span>im</span><span>))</span> <span># Here </span>        <span>plt</span><span>.</span><span>xticks</span><span>(</span><span>ticks</span><span>=</span><span>[])</span>
        <span>plt</span><span>.</span><span>yticks</span><span>(</span><span>ticks</span><span>=</span><span>[])</span>
    <span>plt</span><span>.</span><span>tight_layout</span><span>()</span>
    <span>plt</span><span>.</span><span>show</span><span>()</span>

<span>show_images2</span><span>(</span><span>data</span><span>=</span><span>origin_data</span><span>,</span> <span>main_title</span><span>=</span><span>"</span><span>origin_data</span><span>"</span><span>,</span> <span>d</span><span>=</span><span>0</span><span>)</span>
<span>show_images2</span><span>(</span><span>data</span><span>=</span><span>origin_data</span><span>,</span> <span>main_title</span><span>=</span><span>"</span><span>dis02p1_data</span><span>"</span><span>,</span> <span>d</span><span>=</span><span>0.2</span><span>,</span> <span>prob</span><span>=</span><span>1</span><span>)</span>
<span>show_images2</span><span>(</span><span>data</span><span>=</span><span>origin_data</span><span>,</span> <span>main_title</span><span>=</span><span>"</span><span>dis06p1_data</span><span>"</span><span>,</span> <span>d</span><span>=</span><span>0.6</span><span>,</span> <span>prob</span><span>=</span><span>1</span><span>)</span>
<span>show_images2</span><span>(</span><span>data</span><span>=</span><span>origin_data</span><span>,</span> <span>main_title</span><span>=</span><span>"</span><span>dis1p1_data</span><span>"</span><span>,</span> <span>d</span><span>=</span><span>1</span><span>,</span> <span>prob</span><span>=</span><span>1</span><span>)</span>
<span>show_images2</span><span>(</span><span>data</span><span>=</span><span>origin_data</span><span>,</span> <span>main_title</span><span>=</span><span>"</span><span>p1_data</span><span>"</span><span>,</span> <span>prob</span><span>=</span><span>1</span><span>)</span>
<span>show_images2</span><span>(</span><span>data</span><span>=</span><span>origin_data</span><span>,</span> <span>main_title</span><span>=</span><span>"</span><span>p05_data</span><span>"</span><span>,</span> <span>prob</span><span>=</span><span>0.5</span><span>)</span>
<span>show_images2</span><span>(</span><span>data</span><span>=</span><span>origin_data</span><span>,</span> <span>main_title</span><span>=</span><span>"</span><span>p1fillgray_data</span><span>"</span><span>,</span> <span>prob</span><span>=</span><span>1</span><span>,</span> <span>f</span><span>=</span><span>150</span><span>)</span>
<span>show_images2</span><span>(</span><span>data</span><span>=</span><span>origin_data</span><span>,</span> <span>main_title</span><span>=</span><span>"</span><span>p1fillpurple_data</span><span>"</span><span>,</span> <span>prob</span><span>=</span><span>1</span><span>,</span>
             <span>f</span><span>=</span><span>[</span><span>160</span><span>,</span> <span>32</span><span>,</span> <span>240</span><span>])</span>
from torchvision.datasets import OxfordIIITPet
from torchvision.transforms.v2 import RandomPerspective
from torchvision.transforms.functional import InterpolationMode

randompers = RandomPerspective()
randompers = RandomPerspective(distortion_scale=0.5,
                               p=0.5,
                               interpolation=InterpolationMode.BILINEAR,
                               fill=0)
randompers
# RandomPerspective(p=0.5, # distortion_scale=0.5, # interpolation=InterpolationMode.BILINEAR, # fill=0) 
randompers.distortion_scale
# 0.5 
randompers.p
# 0.5 
randompers.interpolation
# <InterpolationMode.BILINEAR: 'bilinear'> 
randompers.fill
# 0 
origin_data = OxfordIIITPet(
    root="data",
    transform=None
    # transform=RandomPerspective(distortion_scale=0)     # transform=RandomPerspective(p=0) )

dis02p1_data = OxfordIIITPet(
    root="data",
    transform=RandomPerspective(distortion_scale=0.2, p=1)
)

dis06p1_data = OxfordIIITPet(
    root="data",
    transform=RandomPerspective(distortion_scale=0.6, p=1)
)

dis1p1_data = OxfordIIITPet(
    root="data",
    transform=RandomPerspective(distortion_scale=1, p=1)
)

p1_data = OxfordIIITPet(
    root="data",
    transform=RandomPerspective(p=1)
)

p05_data = OxfordIIITPet(
    root="data",
    transform=RandomPerspective(p=0.5)
)

p1fillgray_data = OxfordIIITPet(
    root="data",
    transform=RandomPerspective(p=1, fill=150)
)

p1fillpurple_data = OxfordIIITPet(
    root="data",
    transform=RandomPerspective(p=1, fill=[160, 32, 240])
)

import matplotlib.pyplot as plt

def show_images1(data, main_title=None):
    plt.figure(figsize=(10, 5))
    plt.suptitle(t=main_title, y=0.8, fontsize=14)
    for i, (im, _) in zip(range(1, 6), data):
        plt.subplot(1, 5, i)
        plt.imshow(X=im)
        plt.xticks(ticks=[])
        plt.yticks(ticks=[])
    plt.tight_layout()
    plt.show()

show_images1(data=origin_data, main_title="origin_data")
show_images1(data=dis02p1_data, main_title="dis02p1_data")
show_images1(data=dis06p1_data, main_title="dis06p1_data")
show_images1(data=dis1p1_data, main_title="dis1p1_data")
show_images1(data=p1_data, main_title="p1_data")
show_images1(data=p05_data, main_title="p05_data")
show_images1(data=p1fillgray_data, main_title="p1fillgray_data")
show_images1(data=p1fillpurple_data, main_title="p1fillpurple_data")

# ↓ ↓ ↓ ↓ ↓ ↓ The code below is identical to the code above. ↓ ↓ ↓ ↓ ↓ ↓ def show_images2(data, main_title=None, d=0.5, prob=0.5, f=0):
    plt.figure(figsize=(10, 5))
    plt.suptitle(t=main_title, y=0.8, fontsize=14)
    for i, (im, _) in zip(range(1, 6), data):
        plt.subplot(1, 5, i)
        rp = RandomPerspective(distortion_scale=d, p=prob, fill=f) # Here         plt.imshow(X=rp(im)) # Here         plt.xticks(ticks=[])
        plt.yticks(ticks=[])
    plt.tight_layout()
    plt.show()

show_images2(data=origin_data, main_title="origin_data", d=0)
show_images2(data=origin_data, main_title="dis02p1_data", d=0.2, prob=1)
show_images2(data=origin_data, main_title="dis06p1_data", d=0.6, prob=1)
show_images2(data=origin_data, main_title="dis1p1_data", d=1, prob=1)
show_images2(data=origin_data, main_title="p1_data", prob=1)
show_images2(data=origin_data, main_title="p05_data", prob=0.5)
show_images2(data=origin_data, main_title="p1fillgray_data", prob=1, f=150)
show_images2(data=origin_data, main_title="p1fillpurple_data", prob=1,
             f=[160, 32, 240])

Enter fullscreen mode Exit fullscreen mode

原文链接：RandomPerspective in PyTorch