OmniXAI
OmniXAI copied to clipboard
salesforce
OmniXAI: A Library for eXplainable AI
Hi, Thanks for this useful package. I want to check how long it takes for you to run the 'nlp.ipynb' in tutorials folder. It seems to take more than 10...
Hello, I am running OmniXAI on tabular data for a binary classification task. All the functions are working well except the Ipython plot ones, which all throws this same error...
While installing OmniXAI with pip install getting an error: "Building wheel for hnswlib (pyproject.toml) ... error error: subprocess-exited-with-error" Here is the error log: Building wheel for hnswlib (pyproject.toml) ... error...
Dear author: I love your code very much, but I don't know which interpretable method works on 3D images,could you tell me if possible?
A conda installation option could be very helpful. I have already started working on this, to add `omnixai` to conda-forge. Conda-forge PR: - https://github.com/conda-forge/staged-recipes/pull/20089 Once the conda-forge PR is merged,...
So i am doing XAI on Timeseries and therefore testing SHAP and MACE. I am doing nothing different to the data but it is working with SHAP and not with...
RuntimeError Traceback (most recent call last) ~/anaconda3/envs/ntnu_meticos/lib/python3.7/site-packages/omnixai/explainers/base.py in explain(self, X, params, run_predict) 283 param = params.get(name, {}) --> 284 explanations[name] = self.explainers[name].explain(X=X, **param) 285 except Exception as e: ~/anaconda3/envs/ntnu_meticos/lib/python3.7/site-packages/omnixai/explainers/tabular/counterfactual/mace/mace.py in...
Hi, I have a Pytorch regression model. Could you please help me by providing a generic syntax for using OmniXAI to do so?
Is it possible to use different data or models and display a single dashboard? I would like to create multiple dashboards in one "show()". Thank you so much!
`model = tf.keras.models.Sequential() model.add(tf.keras.layers.Conv2D(32, kernel_size=(3, 3), activation='relu', input_shape=input_shape)) model.add(tf.keras.layers.Conv2D(64, (3, 3), activation='relu')) model.add(tf.keras.layers.MaxPooling2D(pool_size=(2, 2))) model.add(tf.keras.layers.BatchNormalization()) > after removing this batchnorm layer it is working model.add(tf.keras.layers.Dropout(0.1)) model.add(tf.keras.layers.Flatten()) model.add(tf.keras.layers.Dense(128, activation='relu')) model.add(tf.keras.layers.Dropout(0.1)) model.add(tf.keras.layers.Dense(num_classes))`...
