TastyPancakes
/
Efficiency-of-Neural-Architectures
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity
This repository contains code for a paper
16 Commits 1 Branch 0 Tags 107 KiB
Python 99.8%
Shell 0.2%
Go to file
Eduardo Cueto-Mendoza 43aae48415 New size on start and removed paths 2023-07-11 14:12:23 +01:00
Mixtures Update for 04-16-22 2022-04-16 13:20:44 +01:00
layers Removed imports for old config files 2023-06-28 17:04:24 +01:00
models Update for 04-16-22 2022-04-16 13:20:44 +01:00
tests Update for 04-16-22 2022-04-16 13:20:44 +01:00
.gitignore Modified the code for frequentist experiment 2023-06-29 11:45:28 +01:00
LICENSE Update for 04-16-22 2022-04-16 13:22:03 +01:00
README.md Update for 04-16-22 2022-04-16 13:20:44 +01:00
amd_sample_draw.py Did some Python formatting 2023-06-30 11:09:54 +01:00
arguments.py Did some Python formatting 2023-06-30 11:09:54 +01:00
cpu_watt.sh New size on start and removed paths 2023-07-11 14:12:23 +01:00
gpu_power_func.py Did some Python formatting 2023-06-30 11:09:54 +01:00
gpu_sample_draw.py Solved killing pipes, renewed how training sampling works 2023-06-28 17:02:56 +01:00
main_bayesian.py New size on start and removed paths 2023-07-11 14:12:23 +01:00
main_frequentist.py New size on start and removed paths 2023-07-11 14:12:23 +01:00
mem_free.sh Ignore save files 2023-06-01 09:20:51 +01:00
metrics.py Update for 04-16-22 2022-04-16 13:20:44 +01:00
radeontop.sh Solved killing pipes, renewed how training sampling works 2023-06-28 17:02:56 +01:00
read_pickle.py Solved killing pipes, renewed how training sampling works 2023-06-28 17:02:56 +01:00
run_service.py New size on start and removed paths 2023-07-11 14:12:23 +01:00
stopping_crit.py Solved killing pipes, renewed how training sampling works 2023-06-28 17:02:56 +01:00
uncertainty_estimation.py Update for 04-16-22 2022-04-16 13:20:44 +01:00
utils.py Solved killing pipes, renewed how training sampling works 2023-06-28 17:02:56 +01:00

README.md

Energy efficiency comparison

This experiment compares a Frequentist CNN model against a Bayesian CNN model