lucent
lucent copied to clipboard
greentfrapp
Lucid library adapted for PyTorch
I am working on visualising a custom model with Lucent, and need to save the images for my research. When setting save_image and show_inline to true in the render_vis function,...
This pull request addresses a TypeError triggered by the random_scale function in transform.py The error is encountered when running certain Colab notebooks based on lucent ( (eg:[neuron_interaction](https://github.com/greentfrapp/lucent-notebooks/blob/master/notebooks/neuron_interaction.ipynb)) with PyTorch 2.1....
If a custom model is being used where the optimized parameter image only has one channel, then the tensor_to_img_array function in render.py crashes. By handling that possibility, the error is...
Set numpy seed as well. `np.random.choice` is used for example in the transformations: https://github.com/greentfrapp/lucent/blob/dev/lucent/optvis/transform.py#L53
Hi, I noticed this strange behavior using the render_vis function when optimizing multiple images (like when you use it with videos). The time spent to otpimize the same image with...
Tool looks really cool, but I don't want to get started on a tool that might break with a new release.
In section 4 of https://distill.pub/2018/differentiable-parameterizations/ they described a way to add an alpha channel to generate Semi-Transparent image that improved feature visualization. Is there a way we can do this...
When using GPU, this codebase only works for `torch.device('cuda:0')` -- the GPU index has to be `0`. For example, if you choos `torch.device('cuda:1')`, then when you run the code demo...
Hi, is there a way to visualize the activation grid for a custom model with nested modules, which are not explicitely named as a model's attribute? E.g. when I call...
