minsoo2018

"TypeError: missing a required argument: 'x'" even though there is no 'x' in the code

1

Hi, everyone. I got `"TypeError: missing a required argument: 'x'` even though there is no `x` in the code. ```python def concat(a, b, dim = -1): return jnp.concatenate((a, b), axis...

differentiating through initialization

3

Hi, all I found that the parameters of NN model are not updated when using gradient descent solver right before SGD. ```python import haiku as hk import jax import jax.numpy...