jonkahana/ProbeGen
An official implementation of ProbeGen
This project offers a method for evaluating the performance of neural networks, particularly for image classification tasks. It takes datasets of images (like MNIST or CIFAR-10) and applies different network architectures to them. The output is a prediction of how well a given neural network will generalize or classify new images, helping researchers understand network behavior without extensive retraining. This tool is for machine learning researchers and practitioners who work with neural network design and analysis.
No commits in the last 6 months.
Use this if you need to quickly assess the generalization capabilities or classification accuracy of various deep learning models, especially for image-based tasks, without the need for full training runs.
Not ideal if you are looking for a tool to train new deep learning models or perform traditional image recognition directly, as its primary focus is on evaluating existing models.
Stars
13
Forks
—
Language
Python
License
—
Category
Last pushed
Oct 20, 2024
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/jonkahana/ProbeGen"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
AdaptiveMotorControlLab/CEBRA
Learnable latent embeddings for joint behavioral and neural analysis - Official implementation of CEBRA
theolepage/sslsv
Toolkit for training and evaluating Self-Supervised Learning (SSL) frameworks for Speaker...
PaddlePaddle/PASSL
PASSL包含 SimCLR，MoCo v1/v2，BYOL，CLIP，PixPro，simsiam, SwAV, BEiT，MAE 等图像自监督算法以及 Vision...
YGZWQZD/LAMDA-SSL
30 Semi-Supervised Learning Algorithms
ModSSC/ModSSC
ModSSC: A Modular Framework for Semi Supervised Classification