ContraD
similarity
Our great sponsors
| ContraD | similarity | |
|---|---|---|
| 1 | 7 | |
| 186 | 994 | |
| - | 0.2% | |
| 0.0 | 6.5 | |
| over 2 years ago | 16 days ago | |
| Python | Python | |
| MIT License | Apache License 2.0 |
Stars - the number of stars that a project has on GitHub. Growth - month over month growth in stars.
Activity is a relative number indicating how actively a project is being developed. Recent commits have higher weight than older ones.
For example, an activity of 9.0 indicates that a project is amongst the top 10% of the most actively developed projects that we are tracking.
ContraD
-
[D] What is the smallest dataset you styleGAN2 trained?
Well, I've been trying to train a 1024 GAN from scratch on stylegan2-ada-pytorch with a small dataset 300 samples of not so diversity in images of painting faces. Fact is that on first try FID went as low as 71 and started deteriorating. Now I x-flip augmented the dataset (700 images) and at 900kimg FID went 64 but I doubt it will get lower. I lowered the learning rate to 0.0001 as they say it might help... Recently found this way of dataset augmentation... probably will use this https://github.com/jh-jeong/ContraD
similarity
-
New free tool that uses fine-tuned BERT model to surface answers from research papers
Tensorflow Ranking and Tensorflow similarity (maybe relevant/irrelevant contrastive learning?) look like they could be useful.
-
Non-Machine Learning Image Matching with a Vector DB
There is the metric learning problem to learn a hash for similarity https://github.com/tensorflow/similarity
That said, I don't see many good models available for download on tfhub or huggingface optimized for it, but you can always programmatically modify your images (if you truly mean identical to humans) - change white balance, crop, rotate, select adjacent frames from videos, etc. and optimize a network that is small enough for you to be satisfied and see if that works, as a possible alternative.
-
Face Detection for 520 People
Metric learning has great implementations inside Tensorflow Similarity library: https://github.com/tensorflow/similarity Although the documentation is quite bad, but the jupyter notebooks are great.
-
[P] TensorFlow Similarity 0.16 is out
Just a quick note that TensorFlow Similarity 0.16 is out -- this release beside adding the XMB loss is mostly focus on refactoring and optimizing the core components to ensure everything works smoothly and accurately. Details are in the changelog as usual and a simple pip install -U tensorflow_similarity should just work.
- Self-supervised learning added to TensorFlow Similarity
-
[P] TensorFlow Similarity now self-supervised training
Very happy to announce that as part of the 0.15 release, TensorFlow Similarity now support self-supervised learning using STOA algorithms. To help you get started we included in the release a detailed getting started notebook that you can run in Colab. This notebook shows you how to use SimSiam self-supervised pre-training to almost double the accuracy compared to a model trained from scratch on CIFAR 10.
-
TensorFlow Introduces ‘TensorFlow Similarity’, An Easy And Fast Python Package To Train Similarity Models Using TensorFlow
Github: https://github.com/tensorflow/similarity
What are some alternatives?
stylegan2-ada-pytorch - StyleGAN2-ADA - Official PyTorch implementation
pytorch-metric-learning - The easiest way to use deep metric learning in your application. Modular, flexible, and extensible. Written in PyTorch.
co-mod-gan - [ICLR 2021, Spotlight] Large Scale Image Completion via Co-Modulated Generative Adversarial Networks
pgANN - Fast Approximate Nearest Neighbor (ANN) searches with a PostgreSQL database.
DETReg - Official implementation of the CVPR 2022 paper "DETReg: Unsupervised Pretraining with Region Priors for Object Detection".
quaterion - Blazing fast framework for fine-tuning similarity learning models
pytorch-CycleGAN-and-pix2pix - Image-to-Image Translation in PyTorch
Real-Time-Voice-Cloning - Clone a voice in 5 seconds to generate arbitrary speech in real-time
LinkDist - Distillation Self-Knowledge From Contrastive Links to Classify Graph Nodes Without Passing Messages.
sparse_dot_topn - Python package to accelerate the sparse matrix multiplication and top-n similarity selection
AdamP - AdamP: Slowing Down the Slowdown for Momentum Optimizers on Scale-invariant Weights (ICLR 2021)
Keras - Deep Learning for humans