lucid
lucid copied to clipboard
tensorflow
A collection of infrastructure and tools for research in neural network interpretability.
I get the following error when I run feature_inversion: **File "/usr/local/lib/python2.7/dist-packages/lucid/recipes/caricature.py", line 34, in feature_inversion return caricature(\*args, \*\*kwargs) File "/usr/local/lib/python2.7/dist-packages/lucid/recipes/caricature.py", line 50, in caricature for i, layer in enumerate(layers) TypeError:...
This is the provided code to setup the dataset: ``` data_split = imagenet.get_split(options['split']) provider = tf.contrib.slim.dataset_data_provider.DatasetDataProvider(data_split, seed=7) image_tensor, t_label, t_record_key, t_label_text = provider.get(["image", "label", "record_key", "label_text"]) ``` What is the...
Hi all, I was wondering if lucid can be applied to sequential models that use tabular data to visualise activation maps throughout the network based on how different layers/nodes in...
I'd like an easy way to know the error of the optimization for a `render_vis()` call so I can verify the veracity of the resulting image.
Will there be a MobilenetV3 model for the zoo? Can Lucid handle "squeeze_excite/AvgPool" I've tried using a basic MobilenetV3 Lucid model myself (like the MobilenetV2 example) but when I run...
I tried to use the objectives. direction () function on the full connection layer of Inception V1, but it would report an error. ``` InvalidArgumentErrorTraceback (most recent call last) in...
It looks like modelzoo could directly support the new SavedModel standard. We would still need the metadata entries in modelzoo, but no longer require manual freezing of Variables into Constants...
🔬 *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...
Hi, I understand that Lucid needs a three channel input to the network in order to function. Could someone explain: a. Why this is the case b. If there are...
Hello: The idea is that it looks something like this, and I need to find an image X, where the output at a certain layer is as close as possible...
Metadata
Owner
Metadata
A collection of infrastructure and tools for research in neural network interpretability.