search

NeuromorphicProcessorProject / snn_toolbox

Toolbox for converting analog to spiking neural networks (ANN to SNN), and running them in a spiking neuron simulator.
MIT License
360 stars 104 forks source link

index -1 is out of bounds for axis 1 with size 0 #136

Closed rkchunduri closed 1 year ago

rkchunduri commented 1 year ago

I am trying to run snntool box on spinnaker and see the following error. It worked fine earlier. I am seeing this issue while using INI simulator

File "/home/bbpnrsoa/sPyNNaker/lib/python3.8/site-packages/snntoolbox/bin/run.py", line 31, in main run_pipeline(config) File "/home/bbpnrsoa/sPyNNaker/lib/python3.8/site-packages/snntoolbox/bin/utils.py", line 145, in run_pipeline results = run(spiking_model, testset) File "/home/bbpnrsoa/sPyNNaker/lib/python3.8/site-packages/snntoolbox/bin/utils.py", line 220, in wrapper results.append(run_single(snn, testset)) File "/home/bbpnrsoa/sPyNNaker/lib/python3.8/site-packages/snntoolbox/bin/utils.py", line 142, in run return snn.run(test_set) File "/home/bbpnrsoa/sPyNNaker/lib/python3.8/site-packages/snntoolbox/simulation/utils.py", line 631, in run guesses_d += list(guesses_b_t[:, -1]) IndexError: index -1 is out of bounds for axis 1 with size 0**

rbodo commented 1 year ago

Hard to tell exactly without more information. If you say that it worked earlier, can you track down what changed since then?

It seems the time axis has size 0 (in the variable name, "b" stands for batch dimension, "t" for time). Could it be that you changed something in the config about the time step dt or the number of timesteps? Otherwise you could use a debugger to check what happens when guesses_b_t is initialized.

rkchunduri commented 1 year ago

Thank you. Changing config file worked for me .

On Sun, May 21, 2023 at 4:08 PM Bodo Rueckauer @.***> wrote:

Hard to tell exactly without more information. If you say that it worked earlier, can you track down what changed since then?

It seems the time axis has size 0 (in the variable name, "b" stands for batch dimension, "t" for time). Could it be that you changed something in the config about the time step dt or the number of timesteps? Otherwise you could use a debugger to check what happens when guesses_b_t is initialized.

— Reply to this email directly, view it on GitHub https://github.com/NeuromorphicProcessorProject/snn_toolbox/issues/136#issuecomment-1556292960, or unsubscribe https://github.com/notifications/unsubscribe-auth/ABI32EGJ7MAULIH5NEO3EYDXHJ75VANCNFSM6AAAAAAYGU6NTU . You are receiving this because you authored the thread.Message ID: @.*** com>

-- Sent from my iPhone