CNN and multinomial logistic regression classifiers for MNIST digits (Guild AI)
Project description
gpkg.mnist
CNN and multinomial logistic regression classifiers for MNIST digits (Guild AI)
Models
_check
Operations
all
cnn
logreg
cnn
CNN classifier for MNIST
Operations
evaluate
Evaluate a trained CNN
train
Train the CNN
Flags
- batch-size
Number of images to include in a training batch (default is 100)
- epochs
Number of epochs to train (default is 5)
- learning-rate
Learning rate (default is 0.0001)
logreg
Multinomial logistic regression classifier for MNIST
Operations
evaluate
Evaluate a trained logistic regression
train
Train the logistic regression
Flags
- batch-size
Number of images to include in a training batch (default is 100)
- epochs
Number of epochs to train (default is 5)
- learning-rate
Learning rate (default is 0.5)
samples
Sample MNIST images
Operations
prepare
Generate a set of sample MNIST images
Flags
- count
Number of images to generate (default is 100)
Project details
Release history Release notifications | RSS feed
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distributions
Built Distribution
Hashes for gpkg.mnist-0.6.0.dev3-py2.py3-none-any.whl
Algorithm | Hash digest | |
---|---|---|
SHA256 | e90cdf7f7b01c581098fccb63e09fd3b10177ff33d921592b3e53482aadec8c0 |
|
MD5 | e4690174955e3a3baa3f8cb6e9fa665e |
|
BLAKE2b-256 | fea56f8385134d8912609063ad769444d0b13499e4dd8fcb76d6d260f6e2d16c |