search

JingjunYi / SET

[ACM MM2024] Learning Spectral-Decomposed Tokens for Domain Generalized Semantic Segmentation
https://arxiv.org/abs/2407.18568
11 stars 1 forks source link

How to get trainable parameter number? #2

Open FlyingMark77 opened 1 day ago

FlyingMark77 commented 1 day ago

Great job for the field of Semantic Segmentation! However, when I'm trying to count the trainable parameter number of this network, I found the mmseg official tool_(tools/analysis_tools/getflops.py) doesn't support MaskFormer and Mask2Former, for which I have no idea how to get the trainable parameter number of the network. May I have any advice on it?

JingjunYi commented 1 day ago

Hi, thanks for your attention. I think you can try the script from mask2former project, I successed to get the trainable parameters from here. https://github.com/facebookresearch/Mask2Former/blob/main/tools/analyze_model.py

FlyingMark77 commented 10 hours ago

Appreciate your reply! Am I supposed to directly use the config files like citys_rein_dinov2_mask2former_512x512_bs1x4.py or others? And how to convert it into the format for analyze_model.py?

FlyingMark77 commented 9 hours ago

There is a #similar issue published on Rein yesterday. It works on getting parameters of the model. However, FLOPs and MACs are not mentioned. Is there any possible way to get FLOPs?