probability
probability copied to clipboard
tensorflow
Probabilistic reasoning and statistical analysis in TensorFlow
Hi, I am playing with the default Glow model implemented in tensorflow_probability and I find that many variables have duplicated names in the graph (e.g. many variables are called 'Variable:0')....
Hello How can be applied `tfp.bijectors.Tanh` to `tfp.layers.MultivariateNormalTriL` layer? Thanks.
I am trying to use a Categorical distributions inside of a function with JAX vmap. I also tested pmap and jit and both are working fine. Thanks for the help....
Hello all, for a paper I'm writing, I'm making use of the DenseFlipout layer. I'm reweighing the KL-loss as follows: kl_divergence_function_output = (lambda q, p, _: tensorflow_probability.distributions.kl_divergence(q, p) / scale)...
I would like to propose the following enhancement. In tfp.bijectors.AutoregressiveNetwork (https://www.tensorflow.org/probability/api_docs/python/tfp/bijectors/AutoregressiveNetwork) there does not seem to be a way to specify different activations for different hidden layers. Specifically, `hidden_units` allows...
Dear all, I am trying to implement a conditional MAF based on the [example](https://www.tensorflow.org/probability/api_docs/python/tfp/bijectors/AutoregressiveNetwork) provided. It works fine when there is only one bijector used in TransformedDistribution, but as soon...
I followed the example https://github.com/tensorflow/probability/blob/master/tensorflow_probability/examples/jupyter_notebooks/Structural_Time_Series_Modeling_Case_Studies_Atmospheric_CO2_and_Electricity_Demand.ipynb to build and fit a sts model for time series prediction which is easy and works pretty well as long as one sticks to the...
SARIMAX is another model with a lot of potential in the time-series forecasting space due to its ability to factor in extra covariants as well as factor in seasonality into...
f distribution which is frequently used in f test is not available in tfp.distributions. please support this distribution.
Hello, My research needs to change the prior distribution parameters to train a Bayesian Neural Network model. More specifically, I want to change the prior Gaussian distribution mu and sigma....
Metadata
Owner
Metadata
Probabilistic reasoning and statistical analysis in TensorFlow