-
Here's a quick toy with 1D state and batch dimension.
```julia
using Flux
using DiffEqFlux
using MLDataUtils
using Distributions
using OrdinaryDiffEq
D = 1
N = 10000
BS = 100
train_x =…
-
DiffEqFlux is not updated to Zygote yet. There is a [pull request](https://github.com/JuliaDiffEq/DiffEqFlux.jl/pull/52/files) but it is has not been worked on for a few months.
Including the changes…
-
Hey @rtqichen!
While doing experiments on a model, I found out that the L2 norm of the distance between subsequent states is increasing with the relative tolerance set to 0 and different values of …
-
When I run it it prints out:
```
import os
import argparse
import logging
import time
import numpy as np
import torch
import torch.nn as nn
from torch.utils.data import DataLoader
import tor…
-
Hi, thanks a lot for the code and work! I am trying to run the code on Google Colab; every thing was going well, this error popped up!
`TypeError Traceback (most rec…
-
I changed parameters in `gen_flow` like `gen_flow([32,32,3])`, and it threw an error saying shape (40,) and (24,) are incompatible. I want to use your model to train on 3 channels images and it failed…
-
This issue is superficially similar to #81 but the resolution there was to use a newer Julia. However, this happens in the latest available stable Julia (v1.3).
**Problem**
In julia 1.3 on MacOS…
cems2 updated
4 years ago
-
3019182fd3a4bd0ec1d3184f72859e6aca3c0c40
-
This test here fails on master:
https://github.com/jessebett/DiffEqFlux.jl/blob/057baa62f9eb5a2d40f147252aa83dc5bdc1bf99/test/neural_de_gpu.jl#L152-L168
Calling `neural_ode` with initial condition…
-
MWE:
```julia
using OrdinaryDiffEq, StochasticDiffEq, Flux, DiffEqFlux
x = Float32[2.; 0.]
tspan = (0.0f0,25.0f0)
dudt = Chain(Dense(2,50,tanh),Dense(50,2))
Flux.back!(sum(neural_ode(dudt,x,…