Comments (3)
We perform the same number of function evaluations. Thus, I don't get how x
affects the training.
from torchdyn.
@mrpositron Although it is not possible to answer your question in a concise manner, I would say that the phenomenon you are experiencing is related to the following models choice (which you did not specify):
- Vector field type if your vector field explicitly depends on time (i.e. f=f(s, z))), then different
s_span
in training should likely lead to very different vector fields and thus different training dynamics. - ODE solver and backprop sensitivity
from torchdyn.
Thanks for your reply!
I did not specify abot my model choise. I am sorry.
My model consists of GRU encoder and NODE decoder. (i.e. RNN-NODE). Here is a chunk of my code that defines Neural ODE:
self.ode_solve = NeuralDE(self.func, sensitivity = 'autograd', solver = 'rk4', s_span = self.span)
During forward pass I get values from the trajectory obtained from the self.ode_solve
(trajectory = self.ode_solve.trajectory(hidden, self.span)
) and pass it to fc layer.
from torchdyn.
Related Issues (20)
- NeuralODE raises error with deepcopy HOT 2
- Does the odeint method support complex tensors?
- Sklearn dependency push to pypi HOT 4
- Can we use Neural ODE Block with a normal neural network block? HOT 3
- ModuleNotFoundError: No module named 'torchdyn' for torchdyn==1.0.4 on pypi HOT 2
- Hypersolvers missing `args` kwarg
- Multiple shooting solvers missing coarse/fine solver attributes
- 1.0.4 torchdyn not found HOT 11
- Example of controlled dynamical system? HOT 2
- Is there any example of 3D input tensors?
- Module not found error for 'import torchdyn' HOT 4
- Argument mismatch and hard-coded `return_all_eval`
- Parallel integration routines with different t_spans ?
- PyTorch Version Compatibility HOT 1
- Model require `forward` to have `*args, **kwargs` in 1.0.6
- AttributeError: 'NeuralODE' object has no attribute 'defun
- __init__() got an unexpected keyword argument 'func' HOT 1
- shape of gradient does not match the parameter shape in vector field while using adjoint method
- How should i set the seminorm option like it is in the torchdiffeq?
- Boring default setting: will uninstall the installed torch which makes trouble.
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from torchdyn.