Skip to content

issues Search Results · repo:tfjgeorge/nngeometry language:Python

Filter by

34 results
 (98 ms)

34 results

intfjgeorge/nngeometry (press backspace or delete to remove)

tfjgeorge/nngeometry
Gram Matrix Computation for NTKs

Hi, I am currently working with your NNGeometry library using the gram matrix calculator for NKT computations. In the source code (if I got this correctly), I ve seen that you compute the Jacobian w.r.t. ...
  • KonstiNik
  • 5
  • Opened 
    13 days ago
  • #94

tfjgeorge/nngeometry
Question on calculating square root of the FIM

I am currently writing a method to perform forgetting in RL. To do so I add to the model some noise based on the FIM. A snippet for such an approach is: def calculate_scrub_noise(self): gaus_noise ...
  • vimmoos
  • 4
  • Opened 
    on Sep 30, 2024
  • #85

tfjgeorge/nngeometry
[suggestion] Ignore unsupported modules option

Is it possible to just ignore not supported models (like nn.module.BatchNorm2d)? I want to use nngeometry with timm models.
  • fredguth
  • 2
  • Opened 
    on Jun 5, 2024
  • #82

tfjgeorge/nngeometry
Error: `I do not know what to do with layer Embedding(50304, 512)`

First of all great library, I ve always been looking for some ways to get jacobians and fisher information matrices for my PyTorch models. While the library is fine with my vision models based on simple ...
  • CarloNicolini
  • 4
  • Opened 
    on Jan 11, 2024
  • #79

tfjgeorge/nngeometry
Make differentiating inputs optional

Hello, I am calculating the EK-FAC representation on the linear layers of a model with an embedding layer. The inputs are integers which are lookup values and therefore should not be differentiated through. ...
  • Xuzzo
  • 2
  • Opened 
    on Nov 18, 2023
  • #74

tfjgeorge/nngeometry
Adding support for Conv1d layers

Hello and thanks again for your work. Would it be possible to add support for Conv1d layers in K-FAC? Thanks
  • Xuzzo
  • 2
  • Opened 
    on Nov 17, 2023
  • #73

tfjgeorge/nngeometry
Error with float64 tensors

Hello and thanks for your work. Ekfac seems to have issues with models that work on double precision. Here is a code to reproduce it: from nngeometry.metrics import FIM from nngeometry.object import PMatEKFAC ...
  • Xuzzo
  • 2
  • Opened 
    on Oct 31, 2023
  • #70

tfjgeorge/nngeometry
compute FIM of partial parameters

First, thanks for the amazing work! I want to compute the FIM of partial parameters which means only part of whole parameters requires gradients, is that possible?
  • JiaxiangRen
  • 1
  • Opened 
    on Sep 12, 2023
  • #69

tfjgeorge/nngeometry
Scaling of parameter space representations

Many thanks for this interesting library! Comparing with analytical expressions, I think the provided dense representation of Fisher information matrix is calculated as the expectation over the data points ...
  • ksnxr
  • 2
  • Opened 
    on Sep 2, 2023
  • #68

tfjgeorge/nngeometry
`LayerCollection.from_model` does not get all available layers

import torch.nn as nn from nngeometry.layercollection import LayerCollection layers = [nn.Flatten(), nn.Linear(28 * 28, 100), nn.ReLU()] + \ [nn.Linear(100, 100), nn.ReLU()] * 10 + \ ...
  • toontran
  • 2
  • Opened 
    on Jul 27, 2023
  • #60
Issue origami icon

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 Issues
ProTip! 
Restrict your search to the title by using the in:title qualifier.
Issue origami icon

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 Issues
ProTip! 
Press the
/
key to activate the search input again and adjust your query.
Issue search results · GitHub