From 315495ffe14986cfce90e92203cc317eef5ba5cf Mon Sep 17 00:00:00 2001 From: Jordan Gong Date: Mon, 21 Dec 2020 20:00:51 +0800 Subject: Change image loading technique 1. Use Pillow.Image.open instead of torchvision.io.read_image to read image 2. Transforming PIL images instead of tensors which performs better and device option is removed 3. Images are normalized now --- requirements.txt | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'requirements.txt') diff --git a/requirements.txt b/requirements.txt index a0eaf1a..c58a9c3 100644 --- a/requirements.txt +++ b/requirements.txt @@ -1,4 +1,6 @@ torch~=1.7.1 torchvision~=0.8.0a0+ecf4e9c numpy~=1.19.4 -tqdm~=4.54.1 \ No newline at end of file +tqdm~=4.54.1 +Pillow~=8.0.1 +matplotlib~=3.3.3 \ No newline at end of file -- cgit v1.2.3