Skip to content

Recurrent models optimize deep learning by reducing computation and energy use, addressing carbon emissions, training time, and the need for powerful devices efficiently.

Notifications You must be signed in to change notification settings

thinkGrow/recurNet-image-classification

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

1 Commit
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

Run Train:

$ python train.py --data_dir data --scale_factor 4 --patch_size 48 --batch_size 16 --num_epochs 5 --lr 1e-4 --num_workers 4 --device cuda --save_dir results --save_interval 2

Run Test:

$ python test.py --data_dir data --scale_factor 4 --patch_size 48 --batch_size 32 --num_workers 4 --device cuda --save_dir output --model_dir results/run_0/

Run Tensorboard:

$ tensorboard --logdir=results/ --port=2171

Evaluate Results:

$ python utils/evaluate.py --stitched_path stitched_output --hr_path data/DIV2K_train_HR

About

Recurrent models optimize deep learning by reducing computation and energy use, addressing carbon emissions, training time, and the need for powerful devices efficiently.

Topics

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages