From b8a7a4f8a6d2f28a5c16e950ed1e4b95eede20be Mon Sep 17 00:00:00 2001 From: Niels Rogge Date: Thu, 8 Sep 2022 11:00:17 +0000 Subject: [PATCH] Upload README.md with huggingface_hub --- README.md | 4 +--- 1 file changed, 1 insertion(+), 3 deletions(-) diff --git a/README.md b/README.md index 5452b22..1dd6b17 100644 --- a/README.md +++ b/README.md @@ -48,15 +48,13 @@ For code examples, we refer to the [documentation](https://huggingface.co/transf This model was trained on [Kinetics-400](https://www.deepmind.com/open-source/kinetics). -## Training procedure - ### Preprocessing The exact details of preprocessing during training can be found [here](https://github.com/microsoft/VideoX/blob/40f6d177e0a057a50ac69ac1de6b5938fd268601/X-CLIP/datasets/build.py#L247). The exact details of preprocessing during validation can be found [here](https://github.com/microsoft/VideoX/blob/40f6d177e0a057a50ac69ac1de6b5938fd268601/X-CLIP/datasets/build.py#L285). -One resizes the shorter edge of each frame, after which center cropping is performed to a fixed-size resolution (like 224x224). Next, frames are normalized across the RGB channels with the ImageNet mean and standard deviation. +During validation, one resizes the shorter edge of each frame, after which center cropping is performed to a fixed-size resolution (like 224x224). Next, frames are normalized across the RGB channels with the ImageNet mean and standard deviation. ## Evaluation results