Conversation
1 similar comment
Bihaqo
left a comment
Bihaqo
left a comment
There was a problem hiding this comment.
Awesome, thanks!
I think we at least need a test that the code runs, if not that it trains to a reasonable performance.
| CRITERIONS = ['entropy', 'var'] | ||
|
|
||
|
|
||
| def _to_list(p): |
There was a problem hiding this comment.
Docstring here and everywhere with the style
"""One line TLDR.
(optional details)
Args:
arg1: ...
Returns:
lorem ipsum
"""
|
|
||
| def _roundrobin(*iterables): | ||
| "roundrobin('ABC', 'D', 'EF') --> A D E B F C" | ||
| # Recipe credited to George Sakkis |
There was a problem hiding this comment.
Are you obeying the license of this code if it is not you who wrote it?
There was a problem hiding this comment.
This is from the examples here https://docs.python.org/2.7/library/itertools.html#recipes
t3f/nn.py
Outdated
| _counter = count(0) | ||
|
|
||
| def __init__(self, input_dims, output_dims, tt_rank=2, | ||
| def __init__(self, in_dim=None, out_dim=None, d=None, mode='mixed', |
There was a problem hiding this comment.
I don't like the naming in_dim vs input_dims. Maybe in_dim vs in_shape?
There was a problem hiding this comment.
BTW, do you actually need in_dims? Can you use just "units" like keras does?
| return _to_list(factorint(p)) | ||
|
|
||
|
|
||
| def auto_shape(n, d=3, criterion='entropy', mode='ascending'): |
There was a problem hiding this comment.
You have default d here but not in KerasDense. Is it intentional?
| return list(factors[i]) | ||
|
|
||
|
|
||
| def suggest_shape(n, d=3, criterion='entropy', mode='ascending'): |
3 participants
No description provided.