anyone have a working version of this in Python 3.7?

[quinnliu]

1st of all this is an awesome repo.

Update: I have it working on Python 3.7 for science_rcn/run.py but had to make a few specific code design change to achieve the Total test accuracy = 0.7.

There were a few changes you had to make to update the code to Python 3.7. Unrelated to updating the code from Python 2.7 to Python 3.7 are the following design changes:

1 important change is in preproc.py fwd_infer(...) function I had to change

localized[localized < 1] = 0

to

localized[localized < background_threshold] = 0 & added a background_threshold=.001 function argument to fwd_infer(...)

I also changed max_cxn_length=100 in add_underconstraint_edges(...) to max_lateral_connection_pixel_length=15 to create graphs that looked like the following:

NOTE: changing max_cxn_length=100 to max_cxn_length=15 did not effect the Total test accuracy = 0.7.

If you do this & rerun science_rcn/run.py with 10 train & test images instead of the default 20 you also get Total test accuracy = 0.7.

[quinnliu]

I'm extremely interested in figuring out how to programmatically & automatically optimize all of the RCN model constraints such as:

1. train_size = 10
2. pool_shape = (25,25)
3. perturb_factor = 2.0
4. num_oriented_edge_features=16
5. filter_scale=4.0
6. gabor_size=21
7. get_gabor_filters(...) _get_sparse_gaussian() gaussian[gaussian < 0.05 * gaussian.max()] = 0 why 0.05?
8. brightness_diff_threshold = 40.0
9. background_threshold=.001
10. pooled_channel_weights = [(0, 1), (-1, 1), (1, 1)]
11. suppress_radius=3
12. % edge landmark features / total input image pixels = 0.00220 for above numbers on digit "0"
13. max_lateral_connection_pixel_length = 15 =
    The maximum radius to consider adding laterals. This number is dependent on the average length of pixels between landmark feature nodes.
14. tolerance = 4 = How much relative error to tolerate in how much two points vary relative to each other.
15. number of edge_factors?

[lazarox]

Updated (and somewhat simplified) code to work on Python 3.