siamese-triplet

siamese-triplet copied to clipboard

About generating all possible triplets using combinations() function

1

Hi, I am using your code to generate all possible triplet pairs. I see you are using combinations() functions to generate anchor positive pairs. Shouldn't you generate these pairs using...

sandipan211

BalancedBatchSampler: classes vs samples

1

I'm extremely new to machine learning so this might be a bit of a dumb question, but I'm curious anyway: I don't have a lot of GPU memory. For 224x224...

sk-zk

Hi! I am using your custom sampler for a project of mine. I am currently using MNIST dataset loaded from torchvision. When I use your sampler I got the following...

SergioQuijanoRey

datasets.py

1

Hello, I would like to know why there is no equal sign here in datasets.py as shown in the picture. Looking forward to your reply!  

PangXuejiao

Tripletloss finally returns to zero

1

I used the code to train my own data.After training a few epochs, loss returned to zero. I changed the parameters and checked the data,but it still didn't work.

Ryhs-gao

Hi, If i have trained a siamese model, how can i use this model for my classification task? Change the embedding_net into siamese_net and call its get_embedding to get feature...

yuhengShii

How can I train on these networks on a custom dataset?

snehashis1997

I have applied your online triplet loss (hard neagtive) on casia web face dataset but the loss equals to the margin after some epochs. Also the model is not giving...

engrkhanwrt

utils.py:FunctionNegativeTripletSelector - 'anchor_positive' referenced before assignment when len(label_indices) < 2

6

Hi, First off I'd like to say thank you for making this repo, it has been immensely helpful to my research! I believe I have found a bug in utils.py:...

Trotts

@adambielski hi! thanks for your works and its helpful to me! but I fall into troubles when I using my own network into the siamese module, there are some errors...

Geroge-W