Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Refactor block.py #270

Draft
wants to merge 7 commits into
base: main
Choose a base branch
from
Draft

Refactor block.py #270

wants to merge 7 commits into from

Commits on Jan 22, 2020

  1. Do not create dummy axons/synapses

    For population connections, these dummy axons were still having
    an effect. The synapses associated with these axons cause index
    errors in the NxSDK axon compiler, so those are removed as well.
    
    Fixes the "invalid index" error raised in #246.
    hunse authored and tbekolay committed Jan 22, 2020
    Configuration menu
    Copy the full SHA
    1013470 View commit details
    Browse the repository at this point in the history
  2. Configuration menu
    Copy the full SHA
    20dada2 View commit details
    Browse the repository at this point in the history
  3. Spike generator supports population spikes

    This allows population spikes to be sent from host to chip
    when `precompute=True`.
    
    Also add spikes to spike generator more quickly by doing
    deobfuscation once only per group of spikes.
    
    Co-authored-by: Eric Hunsberger <[email protected]>
    2 people authored and tbekolay committed Jan 22, 2020
    Configuration menu
    Copy the full SHA
    97035e2 View commit details
    Browse the repository at this point in the history
  4. Return proper weights for convolution transforms

    We were accidentally returning the Loihi weights, due to double usage
    of the term `weights`. This is now less ambiguous.
    hunse authored and tbekolay committed Jan 22, 2020
    Configuration menu
    Copy the full SHA
    a8b44b0 View commit details
    Browse the repository at this point in the history
  5. Convolution transforms work with larger outputs

    We avoid the restriction of the axon compartment bases being less
    than 256, by taking any part of the required offset over this
    and adding it into the indices instead.
    
    Also clarified the `conv2d_loihi_weights` function.
    
    Also remove nengo-dl from `test_conv.py:test_conv_connection`. The
    nengo-dl portions have not been run in a long time, since they
    were only enabled if `channels_last=True`, and we were x-failing
    the test for `channels_last=True` due to lack of nengo-loihi
    support. It contributes nothing to testing nengo-loihi, so remove it.
    hunse authored and tbekolay committed Jan 22, 2020
    Configuration menu
    Copy the full SHA
    525d385 View commit details
    Browse the repository at this point in the history
  6. Fix bug with no inputs to a neuron

    hunse authored and tbekolay committed Jan 22, 2020
    Configuration menu
    Copy the full SHA
    6d354e8 View commit details
    Browse the repository at this point in the history
  7. Refactor axons

    tbekolay committed Jan 22, 2020
    Configuration menu
    Copy the full SHA
    872acc0 View commit details
    Browse the repository at this point in the history