search

taeinkwon / h2odataset

https://taeinkwon.com/projects/h2o/
48 stars 3 forks source link

Details about the rgb-based action recognization models. #14

Closed sqiangcao99 closed 2 years ago

sqiangcao99 commented 2 years ago

Hi, thanks for the great work. I try to reproduce the recognization results of SlowFast using pyslowfast. Concretely, I build the dataset with the trimed action clips (i.e. 569 training samples) from the cam4(rgb256) and modify the dataset based on charades.py. The model(SLOWFAST_4x16_R50) is trained from scratch. However, I get about 42% top1 acc on val set for about 100 epochs. Did I miss any details?

taeinkwon commented 2 years ago

Hi,

As far as I remember, I used SLOWFAST_32x2_R50 for the baseline meaning that 32 frames with the 2 sampling rate. I hope this helps you. Please let me know if you need any further information.

Best, Taein Kwon