Skip to main content
338 questions
Newest Active Bountied Unanswered
Filter by
Sorted by
Tagged with
1 vote
1 answer
77 views

I'm trying to understand why the Generalized Pareto distribution shows different results for the same parameters. The results from SciPy make sense, while the results from TensorFlow Probability do ...
PPR's user avatar
  • 447
1 vote
0 answers
49 views

I have the following situation: I’m given a univariate time-series dataset y that I wish to model using feature variables X, which are provided alongside y. Naturally, my instinct is to split the data ...
testing_dummy's user avatar
  • 11
0 votes
1 answer
61 views

I am working on TF Probability tutorials and working on a 2D grid approximation for mu, sigma of Normal distribution. I am trying to understand to what level I should expect broadcasting to work for ...
ChrisS's user avatar
  • 3
0 votes
0 answers
134 views

I'm encountering a runtime error when building my Bayesian neural network using tfp.layers.DenseVariational layers on QuantConnect. The error occurs during model construction and states: pgsql Copy ...
Luca Tabone's user avatar
  • 1
2 votes
1 answer
63 views

Tensorflow version is 2.17.1 Tensoflow probability version is 0.24.0 Example from the documentation https://www.tensorflow.org/probability/api_docs/python/tfp/layers/MixtureNormal?hl=en is the ...
R. Iv's user avatar
  • 127
1 vote
1 answer
46 views

I am trying to calculate the CDF of a multivariate normal distribution. The documentation at https://www.tensorflow.org/probability/api_docs/python/tfp/distributions/MultivariateNormalFullCovariance ...
Kenneth Train's user avatar
  • 11
1 vote
4 answers
227 views

I am trying to run the keras-tutorial Probabilistic Bayesian Neural Networks to get an understanding of Bayesian neural networks (BNN). The tutorial contains a google-colab notebook, so you can run it ...
Andi's user avatar
  • 81
0 votes
1 answer
32 views

The official page says, Compute Y = g(X; scale) = scale @ X. So I understand scale is left-multiplied to X, but I see that ScaleMatvecDiag calculates X @ scale. The following code produces import ...
user26459532's user avatar
  • 3
0 votes
0 answers
326 views

I'm trying to use bayesian neural networks, adding a bayesian layer to a neural networks model. Here is the code I'm using and it's from the keras website. import numpy as np import tensorflow as tf ...
sam's user avatar
  • 77
1 vote
1 answer
73 views

I've been doing some modeling of fantasy points for baseball players as a hobby. For a given team in a given game, there are nine (9) starting batters who bat in order. I've trained each of their ...
Steven Kelly's user avatar
  • 41
1 vote
0 answers
122 views

I wish to use the score function gradient estimator (also called the REINFORCE algorithm). Taking the notation and equations from the first link, this allows us to estimate gradients of the expected ...
Kyle Heuton's user avatar
  • 9,856
1 vote
1 answer
152 views

I am trying to set up a Bayesian Neural Network which is implemented with a statistical layer, tfp.layers.DenseVariational. I was about to test various activation functions. From my data, tanh or relu ...
Stine's user avatar
  • 21
1 vote
0 answers
107 views

I have a tensorflow model (keras sequential) that ends with a Tensorflow Probability (TFP) mixture layer. My goal is to fit this network with a custom loss function. The unexpected behaviour is the ...
joueswant's user avatar
  • 146
0 votes
1 answer
183 views

I built and trained a Keras Tensorflow Probability model. It's basically a fully connected Neural Network model with a DistributionLambda on the output layer. Last Layer code example here: tfp....
Jed's user avatar
  • 2,138
0 votes
1 answer
224 views

I want to export the training signature to train my model with the C++ API. However, I am not able to export the model, even after reading through https://github.com/tensorflow/probability/issues/742, ...
Usaint's user avatar
  • 43
1 vote
0 answers
47 views

I'm pretty new to TFP, and probabilistic programming in general, so apologies in advance. I'm wanting to know how to build a Hierarchical UCM in TFP state space. The idea would be to do something like ...
DBruwel's user avatar
  • 11
0 votes
1 answer
201 views

I am trying to train a bayesian NN for noisy time series prediction. I have problems in getting the model to learn the linear releationship in the data getting the model to learn the increasing noise ...
Usaint's user avatar
  • 43
0 votes
1 answer
396 views

I study Bayesian Deep learning and for implement it, i found a library tensor-flow probability , for Dense layer in standard deep learning , there Dense-Variational ,Dense-reparameterize and Dense-...
a-eng's user avatar
  • 37
0 votes
1 answer
78 views

I'm currently learning Bayesian approaches through the book "Rethinking" and would like to utilize TensorFlow Probability. Specifically, I'm working on this chapter : https://colab.research....
Sosa's user avatar
  • 141
0 votes
1 answer
503 views

I have a Problem with tensorflow-probability, I want to calculate the variance of my tensor using tfp.stats.variance(E) But I am always getting the following error message: AttributeError: module '...
EleniSop's user avatar
  • 13
1 vote
0 answers
193 views

I’m trying to install TensorFlow probability on a CentOS 7 machine. My Tensorflow (v 2.6) installation runs on virtual environment with Python 3.8. I have tried installing the package using pip3 ...
Francisco Enriquez's user avatar
  • 11
0 votes
0 answers
79 views

I've been testing Tensorflow Probability on some use cases and have some error. Working backwards, I found that, at least in the Normal distribution, you can see that while the PDF value for 0.9568... ...
Ignacio Ojeda Aguirre's user avatar
  • 1
0 votes
1 answer
50 views

I train a model using tensorflow_probability and distributions. To train it I format my data like this (2 heads model so 2 inputs set): input_1 = tf.data.Dataset.from_tensor_slices(Xdata) input_2 = tf....
Jonathan Roy's user avatar
  • 453
0 votes
1 answer
58 views

I build a test of tensorflow lstm 2 heads and 2 ouputs model with oune of the output is probalilist. This odel work fine. I do the same work but adding more layers, following the same procedure... but ...
Jonathan Roy's user avatar
  • 453
0 votes
1 answer
73 views

UP DATE and ANSWER: My error was using tf.dataset to feed my model like y_hat=model(x_tst) using numpy array data give me the good type of output and work as supposed I try to run tensorflow probality,...
Jonathan Roy's user avatar
  • 453
0 votes
1 answer
174 views

Is there any possibility of changing the dtype of a tensorflow_probability.distribution, either on instantiation or with a respective setter()? I want to use tf.float64 instead of the standard tf....
tobnie's user avatar
  • 3
2 votes
1 answer
143 views

Suppose I have a tensorflow-probability distribution import tensorflow as tf import tensorflow_probability as tfp tfd = tfp.distributions distr = tfd.Normal(loc=0, scale=1) and I want to evaluate ...
Inosen_Infinity's user avatar
  • 51
0 votes
2 answers
397 views

I'm trying to use TensorFlow Probability to learn the alpha and beta parameters of a beta distribution. I can't get it to work for some reason - the loss is all NaN values. Here's what I have: from ...
AI92's user avatar
  • 407
1 vote
0 answers
296 views

I have been building a simple sequential network in Keras. So far I used Adam optimizer for fine-tuning the results. Now I need LBFGS Optimizer in the training to improve the loss. It seems like the ...
Ashwin Raikar's user avatar
  • 128
0 votes
1 answer
118 views

I was experimenting with tensorflow-probability (tfp). I wanted to check, if the density of a Normal-distribution in tfp does integrate (sum) to one. I thought the following calculation inside the ...
H_Man's user avatar
  • 13
0 votes
2 answers
483 views

I am trying to find a TensorFlow equivalent of np.quantile(). I have found tfp.stats.quantiles() (tfp stands for TensorFlow Probability). However, its constructs are a bit different from that of np....
S. P's user avatar
  • 400
2 votes
1 answer
1k views

I am trying to import tensorflow_probability.substrates.jax (specifically to use the distributions) and getting the error shown below (it looks like a self-import). I have installed tensorflow (2.8.2),...
ConorJoseph's user avatar
  • 23
1 vote
0 answers
313 views

Implemented L-BFGS from TensorFlow Probability with Tf2 neural network model, referring to the method in this article https://pychao.com/2019/11/02/optimize-tensorflow-keras-models-with-l-bfgs-from-...
Pavan Kumar J's user avatar
  • 11
0 votes
2 answers
136 views

I would like to develop a TensorFlow probability regression model locally and deploy as Sagemaker endpoint. I have deployed standard XGB models like this previously and understand that one can deploy ...
cs0815's user avatar
  • 17.6k
2 votes
1 answer
3k views

Problem I am trying to create a conda environment and it seems that conda/mamba can't resolve tensorflow_probability dependencies with respect to tensorflow. More context I am trying to create a conda ...
Luca Clissa's user avatar
  • 936
0 votes
1 answer
145 views

i was training a mlp through variational inference for a regression task on a small dataset with 1 feature. The nn works and the training loss goes down but the validation loss has random spikes ...
Alucard's user avatar
  • 197
0 votes
1 answer
130 views

I'm building a TensorFlow Probability Bayesian network. In the example below, I've got a simple 2 distribution output, but both outputs are coming from the last distribution added to the network (...
Jed's user avatar
  • 2,138
1 vote
0 answers
77 views

As an exercise, I'm trying to perform a simple polynomial linear regression in tensorflow probability. I'm getting consistent, but bad results. It's a very simple problem, but somehow I can't see what'...
SU3's user avatar
  • 5,499
0 votes
0 answers
130 views

I'm trying to run a model using tensorflow-probability on an Apple M1 (I've successfully run other tensorflow models on this computer, but I mention the architecture in case it's part of the issue). I ...
user1675330's user avatar
  • 41
0 votes
1 answer
73 views

I am new in Tensor Flow Probability. I am trying to create an Overdispersion Poisson Distribution, that have as rate parameter a continuous Gamma random variable. How I should create this ...
Guilherme Namen's user avatar
  • 101
1 vote
0 answers
66 views

I am computing the different terms of the ELBO and its expectations to illustrate and get a better grasp of the reparametrization trick, as nicely explained here under undifferentiable expectations. ...
rramosp's user avatar
  • 11
0 votes
2 answers
426 views

I have a Keras/TensorFlow Probability model where I would like to include values from the prior layer in the convert_to_tensor_fn parameter in the following DistributionLambda layer. Ideally, I wish ...
Jed's user avatar
  • 2,138
0 votes
1 answer
197 views

I am trying to build a graphical model in Tensorflow Probability, where we first sample a number of positive (1) and negative (0) examples (count_i) from Categorical distribution and then construct ...
Karina's user avatar
  • 27
0 votes
1 answer
221 views

I have a TensorFlow Probability model that is built similar to models described in this YouTube Video. I'm using python==3.8.11 tensorflow==2.10.0 tensorflow-probability==0.18.0 Here's the code to ...
Jed's user avatar
  • 2,138
2 votes
1 answer
443 views

I have made a small bayesian neural network with few dense variational layers. import numpy as np from sklearn.model_selection import train_test_split from tqdm.notebook import tqdm import ...
Alucard's user avatar
  • 197
0 votes
2 answers
830 views

I am trying to learn working with TensorFlow and so I was trying to make a probablistic ML model to get the probability distribution of the next day stock price based on the last n days price sequence,...
Uri Kauffmann's user avatar
  • 13
0 votes
0 answers
147 views

I'm making a Mixture Density Network model class in Tensorflow Probability that combines a fully connected left-hand side with a distribution layer right-hand. I want to instantiate the class with the ...
TheGitPuller's user avatar
  • 51
1 vote
1 answer
213 views

I am trying to use tensorflow probability to predict the distribution of a time series in the future, improving my current model which is based on a classical time series model (GARCH). Essentially I ...
JonathanSchmied's user avatar
  • 137
0 votes
1 answer
124 views

in Bounding hyperparameter optimization with Tensorflow bijector chain in GPflow 2.0, I found an excellent explanation of how to set boundaries to my hyperparameters. Unfortunately, I noticed that ...
HansDoe's user avatar
  • 52
1 vote
0 answers
65 views

I have a bayesian network that I call several times to predict value and estimate epistemic uncertainty. I've seen here that it is better to use model(X) than model.predict(X) as first option is ...
user19296578's user avatar
  • 59

1
2 3 4 5
…
7