lucid
lucid copied to clipboard
A collection of infrastructure and tools for research in neural network interpretability.
🔬 *This is an experiment in doing radically open research. I plan to post all my work on this openly as I do it, tracking it in this issue. I'd...
There are two dead links in the Semantic Dictionaries - Building Blocks of Interpretability Colab. The two links that are broken are `https://storage.googleapis.com/lucid-static/building-blocks/examples/dog_cat.png` (the dog_cat image) and the `https://storage.googleapis.com/lucid-static/building-blocks/examples/flowers.png` (the...
### Describe the bug I am working in colab, and I am following the tutorial from [Using OpenGL with Colab Cloud GPUs](https://colab.research.google.com/github/tensorflow/lucid/blob/master/notebooks/differentiable-parameterizations/appendix/colab_gl.ipynb#scrollTo=qxRuD3-WMqh5). **_It is important to mention that the version...
The cover image of this library is missing, and nobody cares? ... Is this library still maintained actively?
I am running Lucid inside WSL2 Ubuntu 20.04, conda installed environment with python 3.7, tf-gpu 1.15, and the latest lucid. Still, I can't run any of the provided examples. Each...
Resolves: https://github.com/tensorflow/lucid/issues/287 Verified against this video: https://www.youtube.com/watch?v=--7GDGQXuw4
The first image on the readme is missing: When I go to the link to the image in the README https://storage.googleapis.com/lucid-static/common/stickers/channels-visualizations.jpg There is an error there as well : `NoSuchBucket`...
The first image on the readme is missing: When I go to the link to the image in the README https://storage.googleapis.com/lucid-static/common/stickers/channels-visualizations.jpg There is an error there as well : `NoSuchBucket`...
style transfer example requires content and style photo to be both same sized (800x,533) for example, and it requires they are in jpeg format with no transperency layer. following these...
hello contributors: I've tried to use Lucid with a customized model using the .save function. This model has an input layer that is split into three branches (red, green, and...