From 505dafff4ef7a7de6b8e601f1af0010850b5e938 Mon Sep 17 00:00:00 2001 From: Tim Gates Date: Thu, 31 Dec 2020 12:44:06 +1100 Subject: [PATCH] docs: fix simple typo, offcial -> official There is a small typo in README.md. Should read `official` rather than `offcial`. --- README.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/README.md b/README.md index a7b2e39..ddbbdb1 100644 --- a/README.md +++ b/README.md @@ -10,7 +10,7 @@ R-FCN: Object Detection via Region-based Fully Convolutional Networks The official R-FCN code (written in MATLAB) is available [here](https://github.com/daijifeng001/R-FCN). -py-R-FCN is modified from [the offcial R-FCN implementation](https://github.com/daijifeng001/R-FCN) and [py-faster-rcnn code](https://github.com/rbgirshick/py-faster-rcnn ), and the usage is quite similar to [py-faster-rcnn](https://github.com/rbgirshick/py-faster-rcnn ). +py-R-FCN is modified from [the official R-FCN implementation](https://github.com/daijifeng001/R-FCN) and [py-faster-rcnn code](https://github.com/rbgirshick/py-faster-rcnn ), and the usage is quite similar to [py-faster-rcnn](https://github.com/rbgirshick/py-faster-rcnn ). There are slight differences between py-R-FCN and the official R-FCN implementation. - py-R-FCN is ~10% slower at test-time, because some operations execute on the CPU in Python layers (e.g., 90ms / image vs. 99ms / image for ResNet-50)