From 647803e76d66f6e6fbdc1fca46c0b4b782063b13 Mon Sep 17 00:00:00 2001 From: ZHKKKe Date: Tue, 22 Dec 2020 00:41:22 +0800 Subject: [PATCH] update the requirements.txt for the webcam demo --- demo/video_matting/webcam/README.md | 4 ++-- demo/video_matting/webcam/requirements.txt | 2 +- 2 files changed, 3 insertions(+), 3 deletions(-) diff --git a/demo/video_matting/webcam/README.md b/demo/video_matting/webcam/README.md index 151d96b..9b47ddf 100644 --- a/demo/video_matting/webcam/README.md +++ b/demo/video_matting/webcam/README.md @@ -32,13 +32,13 @@ We recommend creating a new conda virtual environment to run this demo, as follo 2. Download the pre-trained model from this [link](https://drive.google.com/file/d/1Nf1ZxeJZJL8Qx9KadcYYyEmmlKhTADxX/view?usp=sharing) and put it into the folder `MODNet/pretrained/`. -3. Create a conda virtual environment named `modnet` (if it doesn't exist) and activate it: +3. Create a conda virtual environment named `modnet` (if it doesn't exist) and activate it. Here we use `python=3.6` as an example: ``` conda create -n modnet python=3.6 source activate modnet ``` -4. Install the required python dependencies (here we use PyTorch==1.0.0): +4. Install the required python dependencies (please make sure your CUDA version is supported by the PyTorch version installed): ``` pip install -r demo/video_matting/webcam/requirements.txt ``` diff --git a/demo/video_matting/webcam/requirements.txt b/demo/video_matting/webcam/requirements.txt index eb0d67b..fd6cb97 100644 --- a/demo/video_matting/webcam/requirements.txt +++ b/demo/video_matting/webcam/requirements.txt @@ -1,5 +1,5 @@ numpy Pillow opencv-python -torch == 1.0.0 +torch >= 1.0.0 torchvision \ No newline at end of file