issues
search
MadryLab
/
trak
A fast, effective data attribution method for neural networks in PyTorch
https://trak.csail.mit.edu/
MIT License
170
stars
22
forks
source link
issues
Newest
Newest
Most commented
Recently updated
Oldest
Least commented
Least recently updated
`CLIPModelOutput` gradient computation wrong dimensionality
#73
dwahdany
closed
13 hours ago
1
fix: CLIP out to loss grad dim
#72
dwahdany
closed
13 hours ago
2
Add NaN checks for inverse computation. PyTorch 2.0 - 2.4 deadlocks on matrix inversion
#71
BrunoKM
closed
13 hours ago
1
TRAK and fast-jl use deprecated `setup.py install` method
#70
BrunoKM
opened
4 weeks ago
1
`fast-jl` doesn't work with `pip` version of 23 and above
#69
BrunoKM
opened
4 months ago
2
RuntimeError: CUDA error: the provided PTX was compiled with an unsupported toolchain.
#68
simplelifetime
closed
4 months ago
3
Fast_jl undefined symbol
#67
Bas-2k
closed
3 months ago
4
Request for a ChatBot Example
#66
Taha-Bahadori
closed
4 months ago
1
Trouble Matching Margin Values in cifar_quickstart.ipynb
#65
amberyzheng
closed
4 months ago
2
0.3.2
#64
kristian-georgiev
closed
8 months ago
1
[added feature] regularization term for inv(xtx) calculation
#63
heale04
closed
8 months ago
1
Remove dependency of proj_matrix during scoring
#61
JD-ETH
closed
8 months ago
0
fix finalize features floods CPU memory: remove log and load mapped gradients to device
#59
JD-ETH
closed
8 months ago
1
[Bug Fix] fix `is_grads_dict` for `IterativeGradientComputer`
#58
TheaperDeng
closed
8 months ago
3
Support the LDS metric
#55
Jiaxin-Wen
closed
9 months ago
1
0.3.1
#54
kristian-georgiev
closed
10 months ago
0
Error when execute `finalize_scores`
#53
Jiaxin-Wen
closed
10 months ago
2
Regarding the model input during `traker.featurize`
#52
Jiaxin-Wen
closed
10 months ago
5
Regarding the implementation of `TextClassificationModelOutput`
#51
Jiaxin-Wen
closed
10 months ago
4
0.3.0
#50
kristian-georgiev
closed
10 months ago
0
0.2.2
#49
kristian-georgiev
closed
10 months ago
1
RuntimeError: input.dtype() == torch::kFloat16 || input.dtype() == torch::kFloat32 error on QNLI
#48
rishabluthra
closed
10 months ago
1
How to implement get_output() function for segmentation task?
#47
yangchaohua
closed
12 months ago
1
Order of Arguments in LLM can mismatch
#46
awe2
closed
10 months ago
2
Parallelized score finalization?
#45
nickk124
closed
10 months ago
4
Gradient_Computers grad.dtype shouldn't inherit from batch[0].dtype?
#44
awe2
closed
10 months ago
2
Blockwise matmul for scoring
#43
kristian-georgiev
closed
10 months ago
5
CLIP Fixes updates
#42
andrewilyas
closed
1 year ago
0
all NaN or all zero scores?
#41
nickk124
closed
1 year ago
6
0.2.1
#40
kristian-georgiev
closed
1 year ago
0
0.2.0
#38
kristian-georgiev
closed
1 year ago
0
Can trak be applied to diffusion models?
#37
xszheng2020
closed
1 year ago
0
fixed model output function when computing gradients in float16
#36
AlaaKhaddaj
closed
1 year ago
1
Clean up docs & tutorials to match >=0.2.0 methods
#35
kristian-georgiev
closed
1 year ago
1
Migrate from `functorch` to `torch.func`
#34
kristian-georgiev
closed
1 year ago
2
Save scores in memory-mapped files and allow loading existing scores from the `TRAKer` class
#33
kristian-georgiev
closed
1 year ago
1
0.1.3
#32
kristian-georgiev
closed
1 year ago
0
Add a colab where one can download pre-computed TRAK scores and visualize them.
#31
kristian-georgiev
closed
1 year ago
1
Save scores in half-precision format by default
#30
kristian-georgiev
closed
1 year ago
3
Support dataset sharding
#29
scoutsaachi
closed
1 year ago
5
0.1.2
#28
kristian-georgiev
closed
1 year ago
0
Allow changing saver and score computer directly from `TRAKer`
#27
kristian-georgiev
closed
1 year ago
1
CudaProjector gives `CUDA error: too many resources requested for launch` on V100
#26
kristian-georgiev
closed
1 year ago
1
Fix bug with custom model output and add test
#25
jvendrow
closed
1 year ago
1
[cifar_quickstart.ipynb] _LinAlgError: linalg.inv: The diagonal element 1 is zero, the inversion could not be completed because the input matrix is singular.
#24
xszheng2020
closed
1 year ago
10
FAILED tests/test_rademacher.py::test_odd - AssertionError: Expected <True>, but was not.
#23
xszheng2020
closed
1 year ago
1
CIFAR-10 Trak Scores Reproduction
#22
vasusingla
closed
1 year ago
5
Default to `BasicProjector` if `fast_jl` import fails
#21
kristian-georgiev
closed
1 year ago
3
Add instructions for using `BasicProjector`
#20
kristian-georgiev
closed
1 year ago
1
Add `allow_skip` to `finalize_scores`
#19
kristian-georgiev
closed
1 year ago
1
Next