PROSAGA码农传奇-Caffe-从PIF图像的Caffe分割中整形输出数组

从PIF图像的Caffe分割中整形输出数组

作者: IP地址
发布时间: 2025-07-13 06:43:57 (4月前)
转自：

<div class =“post-text”itemprop =“text”>
  <P>
    看起来我能够弄清楚这一点。这不是数组顺序的问题，而是值和数据类型。这是我放在一起从输出中获取正确图像的代码。
  </p>
   <pre>
    <code>
      predictions = model.predict({'data_55': image} , useCPUOnly = True) # Run the prediction

map_final = predictions['fc8_seg'][0,0,:,:] # fc8_seg is the output of the neural network
map_final = map_final.reshape((50,50)) # Reshape the output from shape (2500) to (50, 50)
map_final = numpy.flip(map_final, 1) # Flip axis 1 to unmirror the image

# Scale the values in the array to a range between 0 and 255
map_final -= map_final.min() 
map_final /= map_final.max()
map_final = numpy.ceil(map_final*255)

map_final_unint8 = map_final.astype(numpy.uint8) # Convert the data type to an uint8
pil_image = Image.fromarray(map_final_unint8, mode = 'L') # Create the PIL image

</code>
  </pre>
  <P>
    并输出：
  </p>
  <P>
    <a href="https://i.stack.imgur.com/SyZ6L.jpg" rel="nofollow noreferrer">
      <img src =“https://i.stack.imgur.com/SyZ6L.jpg”alt =“输出”/>
    </A>
  </p>
  <P>
    一切看起来都应该如此！
  </p>
</DIV>