NeuroBench / neurobench

Benchmark harness and baseline results for the NeuroBench algorithm track.
https://neurobench.readthedocs.io
Apache License 2.0
52 stars 12 forks source link

Dataset/mg revision #104

Closed jasonlyik closed 11 months ago

jasonlyik commented 11 months ago

@YounesBouhadjar @denkle

I have updated the MG dataset format to the 3D mode with lookback window as discussed.

Also, now train_data, train_labels = train_set[:] train_data will be format (batch, bin_window, 1), just like the DataLoader object output. Before it needed to be permuted.