Fashion-MNIST
A dataset of grayscale images of fashion products in 10 categories, commonly used for training and benchmarking machine learning models.
Timeline (last 90 days)
LIPS-PC was evaluated on the MNIST, Fashion-MNIST and RIAWELC datasets under measurement budgets M ∈ {8,16,32,64,128}.
In simulation, four phase plates at a single wavelength achieve 72.3% accuracy on Caltech-10 color photographs, 96.8% on MNIST, 86.7% on Fashion-MNIST, and 47.9% on color CIFAR-10.
The tutorial code uses the Fashion-MNIST dataset, sets T=200 (the original paper used 2000), and demonstrates the generation process on CPU.
In the code implementation of the diffusion model, the total number of diffusion steps is set to 200, with β increasing linearly from 0.001 to 0.002, and it can run on an ordinary CPU.
All Facts (4)
LIPS-PC was evaluated on the MNIST, Fashion-MNIST and RIAWELC datasets under measurement budgets M ∈ {8,16,32,64,128}.
50%UnverifiedIn simulation, four phase plates at a single wavelength achieve 72.3% accuracy on Caltech-10 color photographs, 96.8% on MNIST, 86.7% on Fashion-MNIST, and 47.9% on color CIFAR-10.
50%UnverifiedThe tutorial code uses the Fashion-MNIST dataset, sets T=200 (the original paper used 2000), and demonstrates the generation process on CPU.
50%UnverifiedIn the code implementation of the diffusion model, the total number of diffusion steps is set to 200, with β increasing linearly from 0.001 to 0.002, and it can run on an ordinary CPU.
50%