te')); return $arr; } /* 遍历用户所有主题 * @param $uid 用户ID * @param int $page 页数 * @param int $pagesize 每页记录条数 * @param bool $desc 排序方式 TRUE降序 FALSE升序 * @param string $key 返回的数组用那一列的值作为 key * @param array $col 查询哪些列 */ function thread_tid_find_by_uid($uid, $page = 1, $pagesize = 1000, $desc = TRUE, $key = 'tid', $col = array()) { if (empty($uid)) return array(); $orderby = TRUE == $desc ? -1 : 1; $arr = thread_tid__find($cond = array('uid' => $uid), array('tid' => $orderby), $page, $pagesize, $key, $col); return $arr; } // 遍历栏目下tid 支持数组 $fid = array(1,2,3) function thread_tid_find_by_fid($fid, $page = 1, $pagesize = 1000, $desc = TRUE) { if (empty($fid)) return array(); $orderby = TRUE == $desc ? -1 : 1; $arr = thread_tid__find($cond = array('fid' => $fid), array('tid' => $orderby), $page, $pagesize, 'tid', array('tid', 'verify_date')); return $arr; } function thread_tid_delete($tid) { if (empty($tid)) return FALSE; $r = thread_tid__delete(array('tid' => $tid)); return $r; } function thread_tid_count() { $n = thread_tid__count(); return $n; } // 统计用户主题数 大数量下严谨使用非主键统计 function thread_uid_count($uid) { $n = thread_tid__count(array('uid' => $uid)); return $n; } // 统计栏目主题数 大数量下严谨使用非主键统计 function thread_fid_count($fid) { $n = thread_tid__count(array('fid' => $fid)); return $n; } ?>machine learning - Vision mamba implementation - Stack Overflow

科技改变生活-雨落星辰 - 所有的伟大,都源于一个勇敢的开始

    最新消息：雨落星辰是一个专注网站SEO优化、网站SEO诊断、搜索引擎研究、网络营销推广、网站策划运营及站长类的自媒体原创博客
    你的位置： 首页>programmer>machine learning - Vision mamba implementation - Stack Overflow

    machine learning - Vision mamba implementation - Stack Overflow

    programmeradmin3浏览0评论

    I am a new user of the Mamba model, I read a few papers saying it has a robust performance on image segmentation tasks. If someone has implemented it before, is there any guidance on the correct setup for the mamba block or input image patches and dimensions that could lead to the best results?

    My implementation so far has not shown any advantage of adding the Mamba block into my code, here is a small snippet of my implementation:

    x = torch.rand(1, 16, 256, 256)
norm = RMSNorm(16**2)
mamba = Mamba(16**2)
_, c, h, _ = x.shape
x = rearrange(x, 'b c (p1 ph) (p2 pw) -> b (c p1 p2) (ph pw)', ph=16, pw=16)
x = mamba(norm(x)) + x
x = rearrange(x, 'b (c p) d -> b c p d', c=c)
x = rearrange(x, 'b c (p1 p2) (ph pw) -> b c (p1 ph) (p2 pw)', p1=h//16, ph=16)

    与本文相关的文章

    发布评论

    评论列表(0)

    1. 暂无评论