Faster-Rcnn-TF 输入图像尺寸变换

Faster-Rcnn本身对于采集的原图像没有要求,但是作为输入放入网络训练的话就必须限制图片的大小,一般Faster-Rcnn对于输入图像的大小限制规则是:限制最小边为600,最大边为1000,对于输入图像优先考虑最大边的限制

代码:./lib/utils/blob.py

def prep_im_for_blob(im, pixel_means, target_size, max_size):
    """Mean subtract and scale an image for use in a blob."""
    im = im.astype(np.float32, copy=False)
    im -= pixel_means
    im_shape = im.shape
    im_size_min = np.min(im_shape[0:2])
    im_size_max = np.max(im_shape[0:2])
    print('im_shape', im_shape)
    # print('im_size_min', im_size_min)
    # print('im_size_max', im_size_max)
    im_scale = float(target_size) / float(im_size_min)
    # Prevent the biggest axis from being more than MAX_SIZE
    if np.round(im_scale * im_size_max) > max_size:
        im_scale = float(max_size) / float(im_size_max)
    im = cv2.resize(im, None, None, fx=im_scale, fy=im_scale,
                    interpolation=cv2.INTER_LINEAR)
    print('im.shape', im.shape)
    return im, im_scale

例如

输入图像的大小是:375*500*3,则resize后的图像大小为:600*800*3

输入图像的大小是:375*800*3,则resize后的图像大小为:469*1000*3

猜你喜欢

转载自blog.csdn.net/oMoDao1/article/details/82427934