Skip to content
New issue

Have a question about this project? # for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “#”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? # to your account

pavpu.py file format? #8

Open
dhlee-jubilee opened this issue Sep 26, 2021 · 0 comments
Open

pavpu.py file format? #8

dhlee-jubilee opened this issue Sep 26, 2021 · 0 comments

Comments

@dhlee-jubilee
Copy link

dhlee-jubilee commented Sep 26, 2021

I'm trying to evaluate my dataset using pavpu.py
Could you upload npy files ('label', 'pred', 'std') in def main(): or show type and shape?

@ex.automain
def main():
label = np.load("/data/wg-cee-dev-dgx/output/bcnn/predict/graphite/Litarion/test_targets.npy")[324]
pred = np.load("/data/wg-cee-dev-dgx/output/bcnn/predict/graphite/Litarion/dropout/dropout_pred.npy")[324]
std = np.load("/data/wg-cee-dev-dgx/output/bcnn/predict/graphite/Litarion/dropout/dropout_unc.npy")[324]

val = std.mean()# + (std.std())
calculate_pavpu(pred, label, std, accuracy_threshold=0.78, uncertainty_threshold=val)
print()

pred = np.load("/data/wg-cee-dev-dgx/output/bcnn/predict/graphite/Litarion/bayesian/bayesian_pred.npy")[324]
std = np.load("/data/wg-cee-dev-dgx/output/bcnn/predict/graphite/Litarion/bayesian/bayesian_unc.npy")[324]

val = std.mean()# + (std.std())
calculate_pavpu(pred, label, std, accuracy_threshold=0.78, uncertainty_threshold=val)

# for free to join this conversation on GitHub. Already have an account? # to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

1 participant