loryruta/async_torchwindow
An async window to visualize an Image tensor or a Gaussian Splatting scene
This tool helps developers visualize image tensors or Gaussian Splatting scenes directly from GPU memory, enabling real-time inspection without performance bottlenecks. It takes raw image data or 3D scene parameters as input and renders them in a separate, non-blocking window. Developers working with GPU-accelerated graphics or machine learning models would find this useful for monitoring visual outputs.
No commits in the last 6 months.
Use this if you need to visualize large image tensors or complex 3D Gaussian Splatting scenes directly from GPU memory without interrupting your main Python program's execution.
Not ideal if you need a full-featured, interactive visualization toolkit with extensive UI controls or if your data is primarily on the CPU.
Stars
18
Forks
—
Language
Cuda
License
MIT
Category
Last pushed
Jan 29, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/loryruta/async_torchwindow"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
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
dvgodoy/deepreplay
Deep Replay - Generate visualizations as in my "Hyper-parameters in Action!" series!