computer_vision_light_weight_modeling_pjt

Naver connect boostcamp AI Tech pjt

computer vision light weight modeling task

using optuna

efficient search using pruning

VBMF MUSCO

hyperparameter(loss(F1, label smoothing, cross entropy), optimizer, scheduler, learning rate)

skip connection customizing

data augmentation(cutMix, MixUp, random augmentation..)

boosting training

data downsampling, upsampling to handle unbalanced class problem

Name		Name	Last commit message	Last commit date
Latest commit History 2 Commits
code		code
EDA.ipynb		EDA.ipynb
README.md		README.md
advance_automl_search.ipynb		advance_automl_search.ipynb
base_automl_search.ipynb		base_automl_search.ipynb
musco.ipynb		musco.ipynb
pretrain_search.ipynb		pretrain_search.ipynb
random_rank_search.ipynb		random_rank_search.ipynb
resizing_network for lightweight.ipynb		resizing_network for lightweight.ipynb
skip_connection.ipynb		skip_connection.ipynb
vbmf.ipynb		vbmf.ipynb

Provide feedback