diffusion_policy icon indicating copy to clipboard operation
diffusion_policy copied to clipboard

Is EMA used to update the training weights?

Open StarCycle opened this issue 10 months ago • 0 comments

Hello @cheng-chi ,

In your colab notebook I find that you mention the EMA model can "accelerate training and improves stability": b632a5a0185bbd8b7dde82955fef541

However, in the training loop, you may only update the EMA model with the training model: 659b2caf46c1603a22cfdbdefd5c275

The ema.step function will not update/smooth the training weights. Why can it accelerate training?

If my understanding is wrong, please let me know

Best, StarCycle

StarCycle avatar Apr 19 '24 14:04 StarCycle