probability

probability copied to clipboard

AttributeError: 'UserRegisteredTypeKerasTensor' object has no attribute 'mean' error raised.

10

Please can anyone let me know why the following code: from tensorflow.keras.layers import Input from tensorflow.keras.layers import Dense from tensorflow.keras.layers import Concatenate from tensorflow.keras.models import Model from tensorflow.keras.optimizers import Adam...

Diogenes4Sinope

Unable to pass `aux` data to `tfp.math.minimize_stateless`

1

Hi, I was trying to use `tfp.math.minimize_stateless` for one of my applications and found that it automatically optimizes all the arguments passed to the `loss_fun`. For example, here is a...

patel-zeel

Avoid custom_gradient warnings

1

python.interlnal.custom_gradient.custom_gradient generate warnings: "@custom_gradient grad_fn has 'variables' in signature, but no ResourceVariables were used on the forward pass.". TF will specify not only arg 'variabels' but also **kwargs. In 'f_wrapped',...

tk2lab

Would be cool to have, could double up as a Keras.io tutorial

LukeWood

RelaxedOneHotCategorical not working with bfloat16 mixed precision

3

Hi, I was trying to train a model using a RelaxedOneHotCategorical wrapped in a DistributionLambda layer on TPU. Unfortunately when using the bfloat16 TPU mixed precision option I run into...

0xtristan

AttributeError: 'Tensor' object has no attribute 'log_prob'

41

The following code ``` import tensorflow as tf import tensorflow_probability as tfp from tensorflow_probability import distributions as tfd def get_mnist_data(normalize=True): img_rows, img_cols = 28, 28 (x_train, y_train), (x_test, y_test) =...

nbro

`TypeSpec` issue using `JointDistribution` with `DistributionLambda` layer

1

I'm getting an error trying to build a Keras model (using either the sequential or functional API) using a `DistributionLambda` output layer with a lambda function that returns `JointDistribution` as...

psilentp

Glow coupling blocks conditioning

1

Hi, I am currently using the tensorflow probability Glow model (tfb.Glow) and I am interested on conditioning the coupling blocks on a different tensor than the input data. Can anyone...

ivallesp

> On Mon, Jul 27, 2020 at 10:25 AM Simeon Carstens ***@***.***> wrote: Looks like so far, there's still no negative binomial regression in TFP. I will give it a...

Jingyi-Qiu

Variational Gaussian process loss- possible math error

1

In the documentation for variational Gaussian process applied to minibatches (https://github.com/tensorflow/probability/blob/v0.12.1/tensorflow_probability/python/distributions/variational_gaussian_process.py#L572), the KL term is rescaled by batch_size/num_training_points_. I assume the reconstruction error term (expected log-likelihood) is not scaled and...

willtownes