72327845050d904f59315f32ac21578c393e9905,unrestricted-advex/unrestricted_advex/eval_kit.py,,evaluate_tcu_model,#,50
Before Change
confidences = logits_to_confidences(
bicycle_logits=logits[:, BICYCLE_IDX],
bird_logits=logits[:, BIRD_IDX])
coverages, cov_to_confident_error_idxs = get_coverage_to_confident_error_idxs(
preds, confidences, labels)
After Change
confidences = np.max(logits, axis=1)
// We will plot accuracy at various coverages
coverages = np.linspace(0.01, .99, 99)
cov_to_confident_error_idxs = get_coverage_to_confident_error_idxs(
coverages, preds, confidences, labels, )
In pattern: SUPERPATTERN
Frequency: 3
Non-data size: 2
Instances
Project Name: google/unrestricted-adversarial-examples
Commit Name: 72327845050d904f59315f32ac21578c393e9905
Time: 2018-08-28
Author: nottombrown@gmail.com
File Name: unrestricted-advex/unrestricted_advex/eval_kit.py
Class Name:
Method Name: evaluate_tcu_model
Project Name: librosa/librosa
Commit Name: b9a5f7d2bf056e397ee527425c41d214265ca59c
Time: 2013-11-14
Author: brm2132@columbia.edu
File Name: librosa/display.py
Class Name:
Method Name: specshow
Project Name: etal/cnvkit
Commit Name: fff30b5d161bc5ad17af26af65704a03e1b4611d
Time: 2019-04-09
Author: etalevich@dnanexus.com
File Name: cnvlib/smoothing.py
Class Name:
Method Name: convolve_weighted