It seems that you used different criteria during training and testing as the code below shows:
IN TEST:
scores = np.dot(vecs.T, qvecs)
IN TRAIN:
dif = x1 - x2
D = torch.pow(dif+eps, 2).sum(dim=0).sqrt()
y = 0.5*lbl*torch.pow(D,2) + 0.5*(1-lbl)*torch.pow(torch.clamp(margin-D, min=0),2)
y = torch.sum(y)
A general framework for map-based visual localization. It contains 1) Map Generation which support traditional features or deeplearning features. 2) Hierarchical-Localizationvisual in visual(points or line) map. 3)Fusion framework with IMU, wheel odom and GPS sensors.
ACM Multimedia2020 University-1652: A Multi-view Multi-source Benchmark for Drone-based Geo-localization 🚁 annotates 1652 buildings in 72 universities around the world.
(ICML 2020) This repo contains code for our paper "Revisiting Training Strategies and Generalization Performance in Deep Metric Learning" (https://arxiv.org/abs/2002.08473) to facilitate consistent research in the field of Deep Metric Learning.
Various hashing methods for image retrieval and serves as the baselines
It seems that you used different criteria during training and testing as the code below shows:
IN TEST:
scores = np.dot(vecs.T, qvecs)
IN TRAIN:
dif = x1 - x2
D = torch.pow(dif+eps, 2).sum(dim=0).sqrt()
I did not get it why you do so?