用填充提取矩形框

作者: 日耀九洲
发布时间: 2025-03-01 07:35:17 (4天前)
转自：

3 条回复

0#
回复此人
布偶的表弟派大星丶 | 2019-08-31 10-32

<div class =“post-text”itemprop =“text”> <P> 可以使用创建蒙版 <code> tf.pad </code> 。 </p> <pre> <code> crop = tf.ones([3, 3]) # "before_axis_x" how many padding will be added before cropping zone over the axis x # "after_axis_x" how many padding will be added after cropping zone over the axis x mask = tf.pad(crop, [[before_axis_0, after_axis_0], [before_axis_1, after_axis_1]] tf.mask(image, mask) # creates the extracted image </code> </pre> <P> 为了与tf.image.crop_and_resize具有相同的行为，这里有一个函数，它将获取一个框数组，并将返回带有填充的提取图像数组。 </p> <pre> <code> def extract_with_padding(image, boxes): """ boxes: tensor of shape [num_boxes, 4]. boxes are the coordinates of the extracted part box is an array [y1, x1, y2, x2] where [y1, x1] (respectively [y2, x2]) are the coordinates of the top left (respectively bottom right ) part of the image image: tensor containing the initial image """ extracted = [] shape = tf.shape(image) for b in boxes: crop = tf.ones([3, 3]) mask = tf.pad(crop, [[b[0], shape[0] - b[2]], [b[1] , shape[1] - b[3]]]) extracted.append(tf.boolean_mask(image, mask)) return extracted </code> </pre> </DIV>

编辑
1#
回复此人
甲基蓝 | 2019-08-31 10-32

<div class =“post-text”itemprop =“text”> <P> 谢谢你非常好的功能@edkevekeh。我不得不稍微修改它以使它做我想要的。一，我无法迭代作为Tensor对象的盒子。此外，裁剪尺寸由方框决定，并不总是3x3。此外，tf.boolean_mask返回裁剪，但我想保留裁剪，但在裁剪外部替换为0.所以我用乘法替换了tf.boolean_mask。 </p> <P> 对于我的用例，num_boxes可能很大，所以我想知道是否有比for循环更有效的方法，猜测不是。我修改过的@ edkevekeh解决方案，如果有人需要的话。 </p> <pre> <code> def extract_with_padding(image, boxes): """ boxes: tensor of shape [num_boxes, 4]. boxes are the coordinates of the extracted part box is an array [y1, x1, y2, x2] where [y1, x1] (respectively [y2, x2]) are the coordinates of the top left (respectively bottom right ) part of the image image: tensor containing the initial image """ extracted = [] shape = tf.shape(image) for i in range(boxes.shape[0]): b = boxes[i] crop = tf.ones([b[2] - b[0], b[3] - b[1]]) mask = tf.pad(crop, [[b[0], shape[0] - b[2]], [b[1] , shape[1] - b[3]]]) extracted.append(image*mask) return extracted </code> </pre> </DIV>

编辑

登录后才能参与评论