parser.add_argument('--quad', action='store_true', help='quad dataloader')
the quad dataloader is an experimental feature we thought of that may allow some benefits of higher –img size training at lower –img sizes.This quad-collate function will reshapes a batch from 16x3x640x640 to 4x3x1280x1280, which does not have much effect by itself as it is only rearranging the mosaics in the batch, but which interestingly allows for 2x upscaling of some images within the batch (one of the 4 mosaics in each quad is upscaled by 2x, the other 3 mosaics are deleted).
四元数据加载器是我们认为的一个实验性功能,它可能允许在较低 –img 尺寸下进行更高 –img 尺寸训练的一些好处。此四元整理功能会将批次从 16x3x640x640 重塑为 4x3x1280x1280,这不会产生太大影响 本身,因为它只是重新排列批次中的马赛克,但有趣的是允许批次中的某些图像放大 2 倍(每个四边形中的 4 个马赛克中的一个放大 2 倍,其他 3 个马赛克被删除)
就是将通道上的信息转移到图像尺度信息
可以看做该方法是 –img 640 和 –img 1280 的折中方案,在特殊项目场景下兼顾速度和精度。
原文地址:http://www.cnblogs.com/chentiao/p/16788530.html