probability
probability copied to clipboard
tensorflow
Probabilistic reasoning and statistical analysis in TensorFlow
Hi, I've been building some structural time-series models with Tensorflow Probability over the past week. I've begun to look into the impute_missing_variable method to smooth in my missing time-series values,...
Not sure if this is Keras bug or tfp bug. I'm trying to make some dense layers that output the parameters of Gaussian mixture (a mixture density network). I want...
Similar to the idea from https://github.com/tensorflow/probability/pull/928, it seems like internally the (l)bgfs optimisers will go through points that already have reached convergence if any other points in the problem have...
I'm using tensorflow version 2.11.0 and tensorflow_probability 0.19.0. The following code succeeds: ```python import tensorflow as tf import tensorflow_probability as tfp class MyModule(tf.Module): def __init__(self): self.dist = tfp.distributions.Normal(0.0, 1.0) my_module...
Hello! Our static bug checker has found a performance issue in discussion/turnkey_inference_candidate/window_tune_nuts_sampling.py: Python type argument [`num_steps`](https://github.com/tensorflow/probability/blob/23f6c22ae5fb68610a7c83b5ce235082c6f708e5/discussion/turnkey_inference_candidate/window_tune_nuts_sampling.py#L272) is passed to tf.function decorated function [`slow_adaptation_interval`](https://github.com/tensorflow/probability/blob/23f6c22ae5fb68610a7c83b5ce235082c6f708e5/discussion/turnkey_inference_candidate/window_tune_nuts_sampling.py#L183) instead of tensors. As there is a...
This PR fixes a few warnings when using layers from `conv_variational.py` and `dense_variational.py`. This PR is also related to #623, but the warnings mentioned there differ a bit from the...
I am currently trying to implement a Bayesian Neural Network for image classification. However, two warnings are raised: ``` /usr/local/lib/python3.10/dist-packages/tensorflow_probability/python/layers/util.py:95: UserWarning: `layer.add_variable` is deprecated and will be removed in a...
Fixes a small typo in a section heading in the Jupyter notebook of the distribution tutorial.
Trying to initialize an instance of `tfb.AutoregressiveNetwork` using the jax substrate fails with an AttributeError. With the example usage from the [docs](https://www.tensorflow.org/probability/api_docs/python/tfp/substrates/jax/bijectors/AutoregressiveNetwork): ```python from tensorflow_probability.substrates import jax as tfp tfb...
Adding new samples using RunningCentralMoments updates the exponentiated residuals and adjustment terms for each new individual sample, making it very slow to add a large number of new samples. Pebay's...
Metadata
Owner
Metadata
Probabilistic reasoning and statistical analysis in TensorFlow