CODEWITHSUNDEEP
pythonautograd
honeybadger
honeybadger

Reputation: 1575

Gradient using Autograd package in Python

I am trying to replicate this standard example using Autograd package.

While I am able to replicate other examples from this repository, this particular example throws an error as follows:

    /home/avuis/anaconda/lib/python3.6/sitepackages/autograd/numpy/numpy_vjps.py:444: FutureWarning: 
Using a non-tuple sequence for multidimensional indexing is deprecated; use `arr[tuple(seq)]` instead of `arr[seq]`. 
In the future this will be interpreted as an array index, `arr[np.array(seq)]`, which will result either in an error or a different result.
      return lambda g: g[idxs]

Is this related version incompatibility? If so, any quick ways to fix this?

Thanks in advance,

Upvotes: 0

Views: 337

Answers (1)

Đorđe Relić
Đorđe Relić

Reputation: 428

Try updating your scipy package to a newer version. Version I'm using is 1.0.0 and the example works.

However, even with that change, this example doesn't work. It runs without errors but doesn't produce any results. My guess is that Hessian and Jacobian approximations are wrong and the minimization algorithm doesn't converge. If one tries with another minimization algorithm, it does converge (slowly but steadily). Current image in the repo that should represent the output is outdated since in the newest version of the code, number of classes in the pinwheel is 3 and not 5.

Upvotes: 1

Related Questions