-
Notifications
You must be signed in to change notification settings - Fork 7.9k
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
Why does yolov4-tiny use leaky instead of mish? #6178
Comments
yolov4-tiny is developed for both of cpu and gpu, exponential and log functions in mish is not friendly for cpu inference. |
Can someone share pre-trained weights for yolov4-tiny with mish? |
Can someone clarify for me, as I'm new to this. I understand Mish is one of the best now, but since slow, it would also be (more so) for training on GPU (or CPU). Pre-trained with Mish, would not work for inference with Leaky [ReLU, assuming]. My understanding is you could substitute one activation function for some other (to some degree); but they would need to match. Or maybe not...: I'm looking into better activation functions, making my own, would you be interested in a better Mish, an approximation (or of similar function)? Could you train on a more accurate version and do inference with an approximate? I'm not familiar enough with Yolo, 4 or 5 or any. Do the non-tiny variants use Mish or other, and only tiny Leaky ReLU? My (unoptimized) Mish implementaion here: sylvaticus/BetaML.jl#6 (comment) was 14.8x slower than (regular) ReLU. My PLU was however just as fast as ReLU (I only timed on CPU), so maybe a candidate? |
the "hard-mish" function (https://forums.fast.ai/t/hard-mish-activation-function/59238) is a runtime-efficient approximation of mish |
@AlexeyAB
The text was updated successfully, but these errors were encountered: