image-similarity-deep-ranking
image-similarity-deep-ranking copied to clipboard
akarshzingade
Thanks for your work firstly. when I train my own dataset---10 types of bmw cars, totally 512 images (the url is http://ai.stanford.edu/~jkrause/cars/car_dataset.html), but the loss nearly can't be cut down...
Hey Akarsh, thank you for sharing your great work! I'm new to deep learning, what I'm confused is that you did not implement the SubSample but enlarge the strides. As...
Hello I want to use a deep ranking to compare photos of people The goal is to identify the Same people with same clothes one different photo. I have construct...
As Mentioned in the Paper [Link](https://users.eecs.northwestern.edu/~jwa368/pdfs/deep_ranking.pdf) There is a subsampling layer before the conv2D in the shallow block of 4:1 and 8:1 I can't find any subsampling layer is your...
Dear akarshzingade, when use the function get_train_generator,I notice the output is much larger then files generated by triplets.txt, the I noticed it copy all filenames in triplets.txt by each class....
Hi @akarshzingade, I've been trying to convert the model to run only in grayscale mode however I keep running across an error stating `ValueError: Error when checking input: expected input_2...
Fixed a small typo in the argument parser.
Hi, According to the original，I have two question below: 1) the original use muti-scale model, you demo can not use, why? 2) the original use pairwise relevance scores to choose...
