最近在运行论文的开源代码时报错：could not broadcast input array from shape (7,7,16) into shape (7，7)
参考了这篇博客得以解决：https://blog.csdn.net/z704630835/article/details/86525973

def make_mosaic(images, num_rows, num_cols, border=1, class_names=None):
    num_images = len(images)
    image_shape = images.shape[1:]   #(7,7,16,1)
    mosaic = ma.masked_all(
            (num_rows * image_shape[0] + (num_rows - 1) * border,
             num_cols * image_shape[1] + (num_cols - 1) * border),
            dtype=np.float32)
    paddedh = image_shape[0] + border
    paddedw = image_shape[1] + border

    for image_arg in range(num_images):
        row = int(np.floor(image_arg / num_cols))
        col = image_arg % num_cols
        image = np.squeeze(images[image_arg])   #(7,7,16)
        image_shape = image.shape  #(7,7,16)
        mosaic[row * paddedh:row * paddedh + image_shape[0],
         col * paddedw:col * paddedw + image_shape[1]] = image

    return mosaic

原因：图片质量参差不齐，甚至有的图片是4维的，运行该程序后直接报错

解决方法：在对image进行如下操作：

      try:
          if img.shape[2] == 3:
                img = cv2.transform.resize(img, (image.shape[0], image.shape[1])
      except:
            continue