Harly-1506/MNIST-Classification-report
Basic CNN and ANN
This project helps deep learning students understand how different neural network settings impact performance on image classification tasks. You input the MNIST dataset of handwritten digits, and it outputs a report showing how various learning rates and activation functions affect the accuracy of both basic and convolutional neural networks. It's designed for students learning the fundamentals of deep learning and neural network architecture.
No commits in the last 6 months.
Use this if you are a student or beginner in deep learning looking to explore and compare the impact of different hyperparameter choices on image classification models.
Not ideal if you need a production-ready solution for classifying handwritten digits or are looking for advanced deep learning techniques beyond basic CNNs and ANNs.
Stars
13
Forks
—
Language
Jupyter Notebook
License
—
Category
Last pushed
Jul 04, 2022
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/Harly-1506/MNIST-Classification-report"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
greydanus/mnist1d
A 1D analogue of the MNIST dataset for measuring spatial biases and answering Science of Deep...
potterhsu/SVHNClassifier
A TensorFlow implementation of Multi-digit Number Recognition from Street View Imagery using...
potterhsu/SVHNClassifier-PyTorch
A PyTorch implementation of Multi-digit Number Recognition from Street View Imagery using Deep...
kensanata/numbers
Handwritten digits, a bit like the MNIST dataset.
kdexd/digit-classifier
A single handwritten digit classifier, using the MNIST dataset. Pure Numpy.