Brad Neuberg

Sounds like the approach we will use is: http://arxiv.org/pdf/1311.2524v5.pdf via this Python open source library: https://github.com/jhauswald/selective_search_py Updating this issue to indicate that we found an algorithm to use for iteration...

Now that I'm done prepping the data I'm going to move onto this (and also #3).

This is done but it's not generalizing terribly well. Once I get EC2 GPU instances setup I'll explore this again or perhaps shift over to VGG-128 to match what Planet...

+1 on this. I'm using this in a Python project and the Python 3 dependency creates alot of awkwardness.

I'd like to take a stab at converting the codebase to Python 2.7. What specific Python3 features do you use so I can see if this is feasible?

Looking through the code base I actually don't see any Python 3 features actually being used. Does one of the libraries selective search depends on have Python 3 dependencies?

FYI I've forked selective_search.py and back ported it to Python 2.7; I've also gotten it running on Mac OS X. The fork: https://github.com/BradNeuberg/selective_search_py I can submit this upstream if @belltailjp...

I've serialized the training and validation data to disk in numpy npz format: ``` train_indices, val_indices, train_labels, val_labels = train_test_split( user_indices, user_labels, stratify=user_labels, test_size=0.3, random_state=42 ) np.save("X", inputs[train_indices, :]) np.save("X_labels",...

I tried earlier versions of Python to see if that was causing the issue; Python 3.6 is impossible due to version skew between imageio and numpy. I was able to...

Thanks!