dvgodoy/deepreplay
Deep Replay - Generate visualizations as in my "Hyper-parameters in Action!" series!
This tool helps machine learning practitioners visually understand how their deep learning models learn over time. You provide your Keras model's training data and configuration, and it generates animations and plots showing how the model's decision boundaries, feature spaces, and probabilities evolve with each training epoch. It's ideal for data scientists, ML engineers, or researchers who need to debug or explain the internal workings of binary classification models.
284 stars. No commits in the last 6 months. Available on PyPI.
Use this if you need to visualize the training process of your Keras deep learning model, especially to understand how hyper-parameters affect learning or to explain model behavior.
Not ideal if your deep learning model is for multi-class classification or if you need to visualize hidden layers with more than two units for feature space plots.
Stars
284
Forks
48
Language
Jupyter Notebook
License
MIT
Category
Last pushed
Mar 24, 2023
Commits (30d)
0
Dependencies
6
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/dvgodoy/deepreplay"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Related frameworks
lutzroeder/netron
Visualizer for neural network, deep learning and machine learning models
mert-kurttutan/torchview
torchview: visualize pytorch models
raghakot/keras-vis
Neural network visualization toolkit for keras
janosh/diagrams
Diagrams of concepts in physics/chemistry/ML
tensorspace-team/tensorspace
Neural network 3D visualization framework, build interactive and intuitive model in browsers,...