rdevon / DIM

Deep InfoMax (DIM), or "Learning Deep Representations by Mutual Information Estimation and Maximization"
BSD 3-Clause "New" or "Revised" License
806 stars 102 forks source link

a bug in the code? #8

Closed Cory-M closed 5 years ago

Cory-M commented 5 years ago

thanks a lot for your amazing work! However, as I tried to run the code, it raised the error:

 File "deep_infomax.py", line 107, in build
    self.classifier_c.build(dim_in=conv_units * conv_x * conv_y)
  File "XXX/.local/lib/python3.6/site-packages/cortex/_lib/models.py", line 186, in wrapped
    return fn(*args, **kwargs)
File "XXX/.local/lib/python3.6/site-packages/cortex/built_ins/models/classifier.py", line 35, in build
    classifier = FullyConnectedNet(dim_in, dim_out=dim_l, **classifier_args)
TypeError: type object argument after ** must be a mapping, not NoneType

I didn't change anything neither in cortex nor in DIM; since I couldn't find the __init__ in class SimpleClassifier, I have no idea about how to fix the bug. Would you mind checking that?

rdevon commented 5 years ago

Give me a day or two: the backend changed I need to update. (this will be accompanied by a number of features in the TODO)

rdevon commented 5 years ago

Sorry for the delay! I'm still working on putting out a solid next release. For those who are still experiencing problems, please revert to an earlier version of cortex until I get this finally pushed out.

rdevon commented 5 years ago

I've pushed a lot of changes. Things should work now, and there are more features. https://github.com/rdevon/DIM/commit/e6622e1de4dc9e15ab4fbb8f72ad495a813e780e

Let me know if your problems in this issue are fixed.