search

harveyslash / Facial-Similarity-with-Siamese-Networks-in-Pytorch

Implementing Siamese networks with a contrastive loss for similarity learning
https://hackernoon.com/one-shot-learning-with-siamese-networks-in-pytorch-8ddaab10340e
MIT License
970 stars 274 forks source link

Looking for contributors! #35

Open harveyslash opened 4 years ago

harveyslash commented 4 years ago

I have not spent any time over the past couple years on this project, and I believe it is time to make it more robust, as well as improve the quality of the results.

I am looking for collaborators who would like to work on this with me. Specifically, I am looking to:

change to larger dataset train a larger model, with pooling layers

Adding better documentation.

Respond to this issue if you would be interested. Any help is greatly appreciated

trungnt11 commented 4 years ago

Hi @harveyslash, i am also working on this task and looking for ways to optimize it, if you still need it, can i join with you? Thanks you

harveyslash commented 4 years ago

I am developing an updated version that relies on ms-celeb dataset. You can find a tool I made to extract the dataset https://github.com/harveyslash/ms-celeb-extractor

ghost commented 4 years ago

am Up!

ghost commented 4 years ago

i would do it in TF for you. Dataloader in tf would be a bit hard to make.

fastaimldata commented 4 years ago

Hello Harsh,

I would like to contribute as well. I would love to become proficient in pytorch and this would be a great learning exercise. Please breakdown the features you want to add into small manageable tasks and create an issue for each. I will jump in and see what I can do. Thanks buddy

kj5699 commented 4 years ago

I would like to join !

Keyu-Yan commented 3 years ago

Hi Harsh,I would like to ontribute as well. I want to use PyTorch with deeper networks and larger data sets.And then we can add opencV.