Hi. May I know if i missed out any important steps? as i obtained a lower accuracy rather than 99.65% as reported for the entire LFW dataset.
Accuracy: 0.95450+-0.00667
Validation rate: 0.88633+-0.02442 @ FAR=0.00100
Area Under Curve (AUC): 0.966
Equal Error Rate (EER): 0.072
my settings are as follows:
distance_metric=1, image_size=160, lfw_batch_size=100, lfw_dir='../data/lfw_mtcnn', lfw_nrof_folds=10, lfw_pairs='../data/pairs.txt', model='../models/facenet/20180402-114759', subtract_mean=True, use_fixed_image_standardization=True, use_flipped_images=True)
Model directory: ../models/facenet/20180402-114759
Metagraph file: model-20180402-114759.meta
Checkpoint file: model-20180402-114759.ckpt-275
Runnning forward pass on LFW images
Hi. May I know if i missed out any important steps? as i obtained a lower accuracy rather than 99.65% as reported for the entire LFW dataset.
Accuracy: 0.95450+-0.00667 Validation rate: 0.88633+-0.02442 @ FAR=0.00100 Area Under Curve (AUC): 0.966 Equal Error Rate (EER): 0.072
my settings are as follows: distance_metric=1, image_size=160, lfw_batch_size=100, lfw_dir='../data/lfw_mtcnn', lfw_nrof_folds=10, lfw_pairs='../data/pairs.txt', model='../models/facenet/20180402-114759', subtract_mean=True, use_fixed_image_standardization=True, use_flipped_images=True)
Model directory: ../models/facenet/20180402-114759 Metagraph file: model-20180402-114759.meta Checkpoint file: model-20180402-114759.ckpt-275 Runnning forward pass on LFW images