issues Search Results · repo:rtqichen/torchdiffeq language:Python
Filter by
226 results
(71 ms)226 results
inrtqichen/torchdiffeq (press backspace or delete to remove)Does anyone know how to fit the nonlinear yet periodic function like this using torchdiffeq?
- ( torch.sin(t) + torch.sin(0.75 * t) ) / 2.0
MADONOKOUKI
- Opened 18 days ago
- #270
Hi, I ran into a problem when using nn.parallel model sampling. odeint s t parameter needs to be 1-D, and integrate()
needs to be put into a t0, which is 0-dim. So this goes against the design of nn.parallel, ...
cb6e310
- Opened on Apr 16
- #268
Mentioned in #265 , the Jacobian inverse is explicitly calculated for the FIRK and DIRK solvers. To avoid this expensive
calculation, the Sherman-Morrison formula can be used to calculate and store the ...
psv4
- Opened on Apr 4
- #267
Hi torchdiffeq maintainers,
First, thank you for the excellent work on this library! It has been incredibly useful for differentiable ODE solutions.
With the recent addition of the odeint_dense function, ...
lixfrank
- Opened on Mar 31
- #266
While deploying an FNO in a an ajoint neural ODE setup, we run into this error of dtype mismatch: RuntimeError: mat1 and
mat2 must have the same dtype, but got ComplexFloat and Float Would there be further ...
gitvicky
- Opened on Feb 25
- #264
Hi I was trying to use the odeint funciton within a numba cuda jit kernel function, but i got the error msg
numba.core.errors.TypingError: Failed in cuda mode pipeline (step: nopython frontend) Untyped ...
anbonimus
- Opened on Feb 11
- #262
Hi, Thank you so much for such an amazing work. In the MNIST example, the integration interval is from 0 to 1. I
understand that the initial condition is h(0), which is also the input tensor. But why using ...
xliu99
- 1
- Opened on Jan 7
- #260
Hi, I tried to use the following code to test the effects of using adjoint method
import torch
import torch.nn as nn
from torchdiffeq import odeint_adjoint as odeint
import time
class LargeODEFunc(nn.Module): ...
petercmh01
- Opened on Dec 23, 2024
- #259
In order to allow access of maps device the datatype should have an option to be set to torch.float32, not only
torch.float64.
The best solution would be to have a parameter dtype when calling the torchdiffeq.odeint ...
bkrenusz
- 1
- Opened on Dec 4, 2024
- #257
When I use half-precision reasoning, I encounter this problem, how can I solve it? Thanks~
./torchdiffeq/_impl/misc.py , line 193, in forward
t = _nextafter(t, t - 1)
^^^^^^^^^^^^^^^^^^^^ ...
maxin-cn
- Opened on Oct 1, 2024
- #255
Learn how you can use GitHub Issues to plan and track your work.
Save views for sprints, backlogs, teams, or releases. Rank, sort, and filter issues to suit the occasion. The possibilities are endless.Learn more about GitHub IssuesProTip!
Restrict your search to the title by using the in:title qualifier.Learn how you can use GitHub Issues to plan and track your work.
Save views for sprints, backlogs, teams, or releases. Rank, sort, and filter issues to suit the occasion. The possibilities are endless.Learn more about GitHub IssuesProTip!
Restrict your search to the title by using the in:title qualifier.