nn_vis
Longhand
nn_vis | Longhand | |
---|---|---|
3 | 2 | |
1,045 | 16 | |
- | - | |
5.9 | 7.1 | |
4 months ago | 5 months ago | |
Python | Python | |
MIT License | MIT License |
Stars - the number of stars that a project has on GitHub. Growth - month over month growth in stars.
Activity is a relative number indicating how actively a project is being developed. Recent commits have higher weight than older ones.
For example, an activity of 9.0 indicates that a project is amongst the top 10% of the most actively developed projects that we are tracking.
nn_vis
-
[D] Is there a tool to visualise my neural network in real time?
In my master Thesis I did some work on visualizing a neural network. It is not trivial to show the weights in a meaningful/understandable way. https://github.com/julrog/nn_vis You need a portion of training data and it's just for fully connected layers currently. The visualization is 3D and in realtime, but it needs some preprocessing, so i'm not sure if it fits your needs at all.
-
Finding important connections
I had some some success on pruning weights with adding batch normalization layer between existing layer, freezing the existing layer and then and retrain the model with the batch normalization layer (training can be much shorter because of way less weights to train). Then using magnitude of the original weights with the weights from the batch normalization, you can prune the original model. You can see an example for fully connected layer in my code: https://github.com/julrog/nn_vis
-
[D] Convolution Neural Network Visualization - Made with Unity 3D and lots of Code / source - stefsietz (IG)
I just made my project public on GitHub, which seems similar to yours https://github.com/julrog/nn_vis
Longhand
-
A working implementation of text-to-3D DreamFusion, powered by Stable Diffusion
Currently working with a student group to build out 3D word cloud generator (https://github.com/Cook4986/Longhand), and the prospect of arbitrary, hyper-specific mesh arrays on demand is thrilling.
Right now, we are relying on the Sketchfab API to populate our (Blender) scenes, which is an imperfect lens through which to visualize the sort of humanities-centric corpora our non-technical "clientele" are studying.
Since we are publishing these scenes via WebXR (Hubs), we have specific criteria related to poly counts (associated latency, bandwidth, etc) and usability. Regarding the latter concern, it's not clear that our end users will want to wait for compute.
-
Ask HN: What projects are you working on this weekend?
Revising a sci-fi story about the first pizza place on Mars: https://www.dropbox.com/s/wdwj6fn2qjywoct/Best%20Pizza_Cook2...
Also, trying to figure out how to distribute ~1000 arbitrary meshes in 3D space (https://github.com/Cook4986/Longhand), and installing the window AC units (Boston suburbs).
What are some alternatives?
DeepFaceLab - DeepFaceLab is the leading software for creating deepfakes.
stable-dreamfusion - Text-to-3D & Image-to-3D & Mesh Exportation with NeRF + Diffusion.
pyomyo - PyoMyo - Python Opensource Myo armband library
ngs - Next Generation Shell (NGS)
nn-visualizer
dogfight-sandbox-hg2 - Air to air combat sandbox, created in Python 3 using the HARFANG 3D 2 framework.
OpenXR-SDK-Source - Sources for OpenXR loader, basic API layers, and example code.
EyeTrackVR - Open Source and Affordable, Virtual Reality Eye Tracking Platform.
rf2_video_settings - Create presets of your rFactor 2 settings and quickly change between performance focused VR setup or an eye-candy favoured Replay setup.
WeightVis - Visualize neural network weights from different kind of libraries