tfdiffeq

tfdiffeq copied to clipboard

Introducing time-varying independent variables into the neural ordinary differential equation

1

Hello thank you for implementing this library! I have a variable that depends on the time step, called aircon_power. It should take in the time step that the ode is...

zykhoo

Hello, I found a performance issue in the definition of `__main__`, examples/circular_ode_demo.py, [`tf.reduce_mean(tf.abs(pred_y - true_y))`](https://github.com/titu1994/tfdiffeq/blob/ef646f85cbd0821749a03e7ab51e03e16798fab1/examples/circular_ode_demo.py#L186) will be calculated repeatedly during program execution, resulting in reduced efficiency. I think `pred_y` in...

DLPerf

Hi, I want to use the prebuilt conv ODE blocks in a the network. However, there always shows below error: ------------------------------------------------------------------------- Traceback (most recent call last): File "C:\Program Files\JetBrains\PyCharm 2021.1.1\plugins\python\helpers\pydev\_pydevd_bundle\pydevd_exec2.py",...

zhengqing-cn

This example `ode_demo.py` under `Example` is considering a NN with input cubic nonlinearity. Since the original dynamics is `y**3` so it seems a bit weird. This implies that as long...

pswpswpsw

TypeError: To be compatible with tf.eager.defun, Python functions must return zero or more Tensors; in compilation of <function _tf_if_stmt.<locals>.aug_body at 0x7f3d989cfb00>, found return value of type <class 'function'>, which is not a Tensor.

4

:134 call * decoder_outputs = self.odeblock(encoder_inputs) :75 call * outputs = odeint(self.odefunc, x, integration_time) /usr/local/lib/python3.7/dist-packages/tfdiffeq/odeint.py:68 odeint * tensor_input, func, y0, t = _check_inputs(func, y0, t) /usr/local/lib/python3.7/dist-packages/tfdiffeq/misc.py:317 _check_inputs * if _decreasing(t):...

poojitharamachandra

Examples broken in rewrite branch

1

I am sure you are probably aware, but the basic examples like ode_demo and latent_ode are broken in the rewrite branch. The size of the tensor returned from odeint is...

adam-hartshorne

Poor performance with a 'steady-state' population

8

Hi, thanks for making this lovely package. I have a simple ODE model with the following code: ```python import tensorflow as tf import matplotlib.pyplot as plt from tfdiffeq import odeint...

Jhsmit