pice35408784b54431987c4d13c457b9cd
/
videomae-base
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity
VideoMAE 模型在 Kinetics-400 数据集上以自监督方式进行了 1600 轮预训练。该模型由 Tong 等人在论文 VideoMAE: Masked Autoencoders are Data-Efficient Learners for Self-Supervised Video Pre-Training 中提出。
3 Commits 1 Branch 0 Tags 719 MiB
Go to file
yang yingjie 580fedb8f5 first commit 2025-02-17 16:38:05 +08:00
.gitattributes Add .gitattributes 2025-02-17 16:27:15 +08:00
README.md Initial commit 2025-02-17 16:27:14 +08:00
config.json first commit 2025-02-17 16:38:05 +08:00
model.safetensors first commit 2025-02-17 16:38:05 +08:00
preprocessor_config.json first commit 2025-02-17 16:38:05 +08:00
pytorch_model.bin first commit 2025-02-17 16:38:05 +08:00

README.md

videomae-base

VideoMAE 模型在 Kinetics-400 数据集上以自监督方式进行了 1600 轮预训练。该模型由 Tong 等人在论文 VideoMAE: Masked Autoencoders are Data-Efficient Learners for Self-Supervised Video Pre-Training 中提出。