cmasch/cnn-text-classification

Text classification with Convolution Neural Networks on Yelp, IMDB & sentence polarity dataset v1.0

39
/ 100
Emerging

# Technical Summary Implements parallel convolutional layers with varying kernel sizes (3, 4, 5) to capture n-gram features, optionally combining word-level embeddings with character-based input for robustness to misspellings. Built on TensorFlow 2 with support for both binary and multiclass sentiment classification, featuring separable convolutions, global max pooling with average pooling fusion, and optional GloVe pre-trained embeddings to improve performance across document lengths from ~10K to 800K samples.

123 stars. No commits in the last 6 months.

No License Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 8 / 25
Community 21 / 25

How are scores calculated?

Stars

123

Forks

35

Language

Jupyter Notebook

License

Last pushed

Sep 10, 2021

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/cmasch/cnn-text-classification"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.