mert-kurttutan/torchview
torchview: visualize pytorch models
This tool helps machine learning engineers and researchers understand the internal structure of their PyTorch neural network models. It takes your PyTorch model definition and visualizes it as a clear graph, showing how data tensors flow between different layers and operations. You get a visual diagram that makes it easier to debug and optimize complex models.
1,038 stars. Used by 3 other packages. Available on PyPI.
Use this if you need a clear visual representation of your PyTorch model's architecture, including tensor shapes and module interactions.
Not ideal if you are looking for performance monitoring, training metrics visualization, or an interactive debugging environment beyond model structure.
Stars
1,038
Forks
47
Language
Python
License
MIT
Category
Last pushed
Feb 26, 2026
Commits (30d)
0
Dependencies
1
Reverse dependents
3
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/mert-kurttutan/torchview"
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
raghakot/keras-vis
Neural network visualization toolkit for keras
janosh/diagrams
Diagrams of concepts in physics/chemistry/ML
dvgodoy/deepreplay
Deep Replay - Generate visualizations as in my "Hyper-parameters in Action!" series!
tensorspace-team/tensorspace
Neural network 3D visualization framework, build interactive and intuitive model in browsers,...