Skip to content

GitLab

"graphbolt/src/cuda/index_select_csc_impl.hip" did not exist on "1547bd931d17cd1da144a6d38bb687c0f2c3b364"
Commit a0bfa304 authored by Yin Cui's avatar Yin Cui Committed by A. Unique TensorFlower
Browse files

Update readme. 

PiperOrigin-RevId: 463012965
parent 700d29e9
Show whitespace changes
Inline Side-by-side
Showing with 2 additions and 5 deletions
official/projects/video_ssl/README.md
View file @ a0bfa304
......@@ -17,10 +17,7 @@ from the same short video are pulled together in the embedding space, while
clips from different videos are pushed away. CVRL significantly closes the gap
between unsupervised and supervised video representation learning.
We release the code and pre-trained models.
More pre-trained model checkpoints and a detailed instruction about the code
will be updated.
Here we release the code and pre-trained models.
## Experimental Results
......@@ -35,7 +32,7 @@ will be updated.
## Pre-trained Model Checkpoints
We provide model checkpoints pre-trained on unlabeled RGB videos from
Kinetics-400 and Kinetics-600. All models are trained scratch with random
Kinetics-400 and Kinetics-600. All models are trained from scratch with random
initialization.
We also provide a baseline model checkpoint of "ImageNet inflated" we used in
......
Markdown is supported
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment