LambdaSection/NeuralDBG
A causal inference engine for deep learning training that provides structured explanations of neural network training failures. Understand why your model failed during training through semantic analysis and abductive reasoning, not raw tensor inspection.
This tool helps deep learning researchers and PhD students understand why their neural networks fail during training. It takes your existing PyTorch model and training loop, monitors the learning process, and provides clear, ranked explanations for issues like vanishing gradients or dead activations. It helps machine learning practitioners quickly pinpoint the root causes of training instability without sifting through raw data.
Use this if you are an ML researcher or PhD student struggling to diagnose why your deep learning model isn't training effectively and need causal explanations rather than just metrics.
Not ideal if you need a production monitoring solution, a general-purpose metric tracking dashboard, or a no-code solution.
Stars
20
Forks
2
Language
Python
License
MIT
Last pushed
Mar 09, 2026
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/LambdaSection/NeuralDBG"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
obss/sahi
Framework agnostic sliced/tiled inference + interactive ui + error analysis plots
tensorflow/tcav
Code for the TCAV ML interpretability project
MAIF/shapash
🔅 Shapash: User-friendly Explainability and Interpretability to Develop Reliable and Transparent...
TeamHG-Memex/eli5
A library for debugging/inspecting machine learning classifiers and explaining their predictions
csinva/imodels
Interpretable ML package 🔍 for concise, transparent, and accurate predictive modeling...