What is -eq in tlt yolo_v4 prune

Accelerated Computing Intelligent Video Analytics TAO Toolkit
1

I found this explanation:
-eq, --equalization_criterion : Criteria to equalize the stats of inputs to an element-wise op layer or depth-wise convolutional layer. This parameter is useful for ResNets and MoblieNets. Options are arithmetic_mean ,:code:geometric_mean, union , and intersection . The default value is union .
but I still don’t understand why it is necessary and what each option does.

Thanks

3

See Frequently Asked Questions — Transfer Learning Toolkit 3.0 documentation,

equalization_criterion is to choose method to merge weights from different branches of element wise or depth wise layers, default is union

4

Is there any webpage that explains the different methods?

5

Sorry for late reply.
Please see PRUNING NEURAL NETWORKS THAT INCLUDE ELEMENT-WISE OPERATIONS and Pruning Models with NVIDIA Transfer Learning Toolkit | NVIDIA Technical Blog