MLDL 2022

Project: Domain adaptation in real-time semantic segmentation

Backbone model: BiseNet

Model complexity

It is possible to print MACs, FLOPs and number of parameters of a model in this repository by using this script:

!pip install thop
!python complexity.py

An example with some parameters:

!python complexity.py --model "bisenet" --input_channels 3 --context_path "resnet18"

Name		Name	Last commit message	Last commit date
Latest commit History 69 Commits
dataset		dataset
model		model
.gitignore		.gitignore
README.md		README.md
adv.sh		adv.sh
complexity.py		complexity.py
loss.py		loss.py
main.py		main.py
seg.sh		seg.sh
train.py		train.py
utils.py		utils.py
validate.py		validate.py