metric-learning-divide-and-conquer

metric-learning-divide-and-conquer copied to clipboard

as title

jackft2

correction for the code

3

Hi, Thanks for the code. Lately, I worked with the code and found out that there are two slights errors in the code, my observations are for python version 3.7....

SidraHanif180

is the algorithm of calculating recall@k metrics correct?

1

https://github.com/CompVis/metric-learning-divide-and-conquer/blob/1766c2cffe1075692657898d2086af4bc9d92929/lib/evaluation/recall.py#L9 Hi, is the code above, which calculates recal@k metrics correct? it looks like top-k accuracy to me (when we add 1 to result sum, if we find at least...

JasonKll

Symbol ')' is placed in the wrong location

2

Hi: In sample function, I may have found a small mistake. Code in https://github.com/CompVis/metric-learning-divide-and-conquer/blob/master/lib/data/loader/sampler.py#L59 Maybe you meaning is ``` replace = len(self.C_index[class_]) < self.num_samples_per_class ``` Symbol ')' is placed in...

jinzhao1522

Undefined name '_sz_features' in ./lib/model.py

3

[flake8](http://flake8.pycqa.org) testing of https://github.com/CompVis/metric-learning-divide-and-conquer on Python 3.7.1 $ __flake8 . --count --select=E9,F63,F72,F82 --show-source --statistics__ ``` ./lib/model.py:84:36: F821 undefined name '_sz_features' model.sz_features_output = _sz_features[type(model)] ^ 1 F821 undefined name '_sz_features' 1...

cclauss

can someone explain to me? import numpy as np import torch import torch.nn.functional as F import matplotlib.pyplot as plt from time import time from torchvision import datasets, transforms from torch...

LUCASDNORONHA