-
## Description of bug / unexpected behavior
trying to set up logging in a config file fails
## Expected behavior
logs written to a file
## How to reproduce the issue
Code for reproduci…
-
## Feature description
Have a `pyepal` class that supports [neural tangent kernels. ](https://arxiv.org/pdf/1912.02803.pdf)
## Implementation idea
Use the `neural_tangents` package and take as in…
-
I'm running the simple demo as facing the array problem:
`from jax import random
import jax.numpy as np
from jax.api import jit
from neural_tangents import stax
init_fn, apply_fn, kernel_fn…
-
Hi, could anyone explain to me the reason for composing `(akey,)` and `{}` as the input for the `tree_flatten` function in [https://github.com/google/neural-tangents/blob/master/neural_tangents/stax.p…
-
Hello!
I'm trying to run simple model with ntk kernel. Running in Google Colab. Here is my code:
`!pip install -q git+https://www.github.com/google/neural-tangents`
```python
import jax.nump…
-
Thanks for your kind reply. It seems that the only difference between them is the covariance matrix. Does it mean that if I set ```compute_cov=False``` in ```predict_fn``` returned by ```gradient_desc…
-
For shape information, need to call `shape` for TF symbolic tensors.
https://github.com/DarrenZhang01/TensorFlow_GSoC/blob/master/neural-tangents/neural_tangents/stax.py#L438
-
In https://github.com/QuantConnect/Lean/issues/4930 I already flagged that a docker image can not be build out of the box. I now have managed to do so by moving some packages from conda to pip for ins…
-
Hi, I am encountering the issue https://github.com/DarrenZhang01/TensorFlow_GSoC/issues/26 for the test case `MaskingTest.test_mask_fc_ [different_inputs_get=nngp_axis=(0, 1, 2, 3)_mask=10.0_concat=0_…
-
Thanks for your efforts on creating this library! However, when I'm using neural-tangents to compute NTK matrix values, I find it hard to tell the value of kernel_fn for specific inputs, as it's flood…
ybj14 updated
4 years ago