From 8c615f07638e55003dcacd0808b711d62241b20b Mon Sep 17 00:00:00 2001 From: Xintao Date: Fri, 6 Sep 2019 21:32:28 +0800 Subject: [PATCH] Update README.md --- README.md | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/README.md b/README.md index 17d42a16..39d94ce2 100644 --- a/README.md +++ b/README.md @@ -14,7 +14,7 @@ MMSR is an open source image and video super-resolution toolbox based on PyTorch ## Dependencies and Installation - Python 3 (Recommend to use [Anaconda](https://www.anaconda.com/download/#linux)) -- [PyTorch >= 1.0](https://pytorch.org/) +- [PyTorch >= 1.1](https://pytorch.org/) - NVIDIA GPU + [CUDA](https://developer.nvidia.com/cuda-downloads) - [Deformable Convolution](https://arxiv.org/abs/1703.06211). We use [mmdetection](https://github.com/open-mmlab/mmdetection)'s dcn implementation. Please first compile it. ``` @@ -24,7 +24,7 @@ MMSR is an open source image and video super-resolution toolbox based on PyTorch - Python packages: `pip install numpy opencv-python lmdb pyyaml` - TensorBoard: - PyTorch >= 1.1: `pip install tb-nightly future` - - PyTorch == 1.0: `pip install tensorboardX` + ## Dataset Preparation We use datasets in LDMB format for faster IO speed. Please refer to [DATASETS.md](datasets/DATASETS.md) for more details.