FedScale
fashion-mnist
Our great sponsors
FedScale | fashion-mnist | |
---|---|---|
4 | 15 | |
365 | 11,439 | |
3.0% | 1.8% | |
7.9 | 0.0 | |
4 months ago | almost 2 years ago | |
Python | Python | |
Apache License 2.0 | MIT License |
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.
FedScale
-
University of Michigan Researchers Open-Source ‘FedScale’: a Federated Learning (FL) Benchmarking Suite with Realistic Datasets and a Scalable Runtime to Enable Reproducible FL Research on Privacy-Preserving Machine Learning
Continue reading | Checkout the paper, github link
- We created the most comprehensive benchmark datasets for federated learning to date!
- The most comprehensive benchmark datasets for federated learning to date!
-
The most comprehensive benchmark datasets for federated learning to date
We created FedScale, which has a diverse set of challenging and realistic benchmark datasets to facilitate scalable, comprehensive, and reproducible federated learning (FL) research. FedScale datasets are large-scale, encompassing a diverse range of important FL tasks, such as image classification, object detection, word prediction, and speech recognition. Our evaluation platform provides flexible APIs to implement new FL algorithms and includes new execution backends with minimal developer efforts. Check it out, and feel free to join the FedScale community via Slack(https://join.slack.com/t/fedscale/shared_invite/zt-uzouv5wh-ON8ONCGIzwjXwMYDC2fiKw)!
Paper: https://arxiv.org/abs/2105.11367 and Github repo: https://github.com/symbioticlab/fedscale
Cheers!
fashion-mnist
-
Logistic Regression for Image Classification Using OpenCV
In this case there's no advantage to using logistic regression on an image other than the novelty. Logistic regression is excellent for feature explainability, but you can't explain anything from an image.
Traditional classification algorithms but not deep learning such as SVMs and Random Forest perform a lot better on MNIST, up to 97% accuracy compared to the 88% from logistic regression in this post. Check the Original MNIST benchmarks here: http://fashion-mnist.s3-website.eu-central-1.amazonaws.com/#
- Pre-Trained ML models for labeling retail images? Upload an image of a dress shirt and the labels output are “long sleeve, men’s, button down, collar, formal, dress shirt” or better?
-
The Paradigm Shift Towards Multimodal AI Jina AI MLOps for Multimodal AI Neural Search and Creative AI
Compared to NLP, I came to the field of computer vision (CV) pretty late. While at Zalando in 2017, I published a paper on the Fashion-MNIST dataset. This dataset is a drop-in replacement of Yann LeCun's original MNIST dataset from 1990 (a set of simple handwritten digits for benchmarking computer vision algorithms.) The original MNIST dataset was too trivial for many algorithms – shallow learning algorithms such as logistic regression, decision trees, and support vector machines could easily hit 90% accuracy, leaving little room for deep learning algorithms to shine.
-
MNIST classification using pytorch/I will do data science, data analysis, machine learning in python
Fashion MNIST: This dataset from Zalando Research contains images of 10 classes consisting of clothing apparel and accessories like ankle boots, bags, coats, dresses, pullovers, sandals, shirts, sneakers, etc. instead of handwritten digits. The images are grayscale just like the original MNIST.
-
Computer Vision 101 - Fashion MNIST
Link to the dataset : Fashion Mnist You dont need to download the dataset manually, they are included as part of pytorch Its better if you use jupyter-notebook as the code in this blog is a step by step process with data visualisation in between for better understanding.
- How to produce data visualizations like this?
-
Image recognition and linear regression.
[1] https://github.com/zalandoresearch/fashion-mnist
-
A New Google AI Research Study Discovers Anomalous Data Using Self Supervised Learning
New Google AI research introduces a 2-stage framework that uses recent progress on self-supervised representation learning and classic one-class algorithms. This framework is simple to train and shows SOTA performance on various benchmarks, including CIFAR, f-MNIST, Cat vs. Dog, and CelebA. Following that, they offer a novel representation learning approach for a practical industrial defect detection problem using the same architecture. On the MVTec benchmark, the framework achieves a new state-of-the-art.
-
Staying in Tune: A guide to optimizing hyperparameters
Xiao H, et al. Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithms. arXiv:1708.07747
-
Machine Learning Orchestration on Kubernetes using Kubeflow
About the Dataset Fashion-MNIST is a dataset of Zalando's article images—consisting of a training set of 60,000 examples and a test set of 10,000 examples. Each example is a 28x28 grayscale image associated with a label from 10 classes. We intend Fashion-MNIST to serve as a direct drop-in replacement for the original MNIST dataset for benchmarking machine learning algorithms. It shares the exact image size and structure of training and testing splits. source: https://github.com/zalandoresearch/fashion-mnist
What are some alternatives?
flower - Flower: A Friendly Federated Learning Framework
image-super-resolution - 🔎 Super-scale your images and run experiments with Residual Dense and Adversarial Networks.
FederatedScope - An easy-to-use federated learning platform
kmnist - Repository for Kuzushiji-MNIST, Kuzushiji-49, and Kuzushiji-Kanji
fedjax - FedJAX is a JAX-based open source library for Federated Learning simulations that emphasizes ease-of-use in research.
kubeflow - Machine Learning Toolkit for Kubernetes
ORBIT-Dataset - The ORBIT dataset is a collection of videos of objects in clean and cluttered scenes recorded by people who are blind/low-vision on a mobile phone. The dataset is presented with a teachable object recognition benchmark task which aims to drive few-shot learning on challenging real-world data.
zozo-shift15m - SHIFT15M: Fashion-specific dataset for set-to-set matching with several distribution shifts
datasets - TFDS is a collection of datasets ready to use with TensorFlow, Jax, ...
tape - Tasks Assessing Protein Embeddings (TAPE), a set of five biologically relevant semi-supervised learning tasks spread across different domains of protein biology.
FATE - An Industrial Grade Federated Learning Framework
Anime-face-generation-DCGAN-webapp - A port of my Anime face generation using Pytorch into a Webapp