From 47e7e56e3e542b6eeb59b941f47f900a6c25d82b Mon Sep 17 00:00:00 2001 From: Bernhard Walser Date: Mon, 29 Mar 2021 19:52:58 +0200 Subject: [PATCH] README update --- README.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/README.md b/README.md index f611df7..c4b9cc9 100644 --- a/README.md +++ b/README.md @@ -58,7 +58,7 @@ What dimension each head should have. What window size to use, make sure that after each downscaling the image dimensions are still divisible by the window size. - `downscaling_factors`: 4-tuple of ints. What downscaling factor to use in each stage. Make sure image dimension is large enough for downscaling factors. -- `relative_position_embedding`: bool. +- `relative_pos_embedding`: bool. Whether to use learnable relative position embedding (2M-1)x(2M-1) or full positional embeddings (M²xM²). ### TODO - Adjust code for and validate on ImageNet-1K and COCO 2017