-
```julia
using Flux
function fn_good(t0, τ, duration)
x = 1.0
t = t0
T = t0 + duration
while t < T
x += -τ*x
t += 0.01
end
x
end
f_good(τ) = fn_…
-
I am trying to differentiate [this function](https://github.com/gaelforget/ECCO.jl/blob/26d9118b338b86f3cf0ae05f7535a88fb5f54974/src/mountain_glacier.jl#L66) (main branch) and use the resulting adjoin…
-
I think the primitive added in #204 may not support automatic differentiation and batching transforms as we did not define Jacobian vector product and transpose operations (for autodiff) and a batcher…
-
I have a strange issue with backward() I have two generators, gen1 and gen2, I calculate loss on three ways, loss_1, loss_2, loss_3
All compute for gen1 are ok
Part 1.
let out = gen1.forward(inp…
-
Hey, I was wondering if mess is able to calculate forces on atoms with jax's autodiff? I tried it like this:
```
def struc_to_energy(r):
mol = Structure(
atomic_number=jnp.array(…
-
Hi,
Is some documentation available for the autodiff branch that we could have a look at to get familiar with the new wrapper. Thanks in anticipation.
-
The issue is probably due to my own inexperience.
The following snippet returns the value of the function rather than its derivative:
~~~~c++
const double x = 1.0;
const double dx = 1.…
-
Is it possible to do a try/catch on the evaluation of the Jac to turn on autodiff?
https://github.com/SciML/DifferentialEquations.jl/blob/master/src/ode_default_alg.jl#L49
-
Suppose I have 1000-5000 datasets, where each dataset has a 100 point or so time series and I want to independently fit a 2-4 parameter model to each of these. Essentially just fitting 1000-5000 curve…
-
**Describe the bug**
A clear and concise description of what the bug is, ideally within 20 words.
Wrong gradient when using taichi autodiff.grad and pytorch autodiff.function together.
**To…
zjcs updated
5 months ago