ToVoxelGrid

ToVoxelGrid

Once Loop Reflect

Downloading https://prod-dcd-datasets-public-files-eu-west-1.s3.eu-west-1.amazonaws.com/a99d0fee-a95b-4231-ad22-988fdb0a2411 to ../../tutorials/data/NMNIST/test.zip

  0%|          | 0/169674850 [00:00<?, ?it/s]
  0%|          | 52224/169674850 [00:00<08:35, 329219.16it/s]
  0%|          | 242688/169674850 [00:00<03:23, 833316.34it/s]
  0%|          | 696320/169674850 [00:00<01:37, 1735739.84it/s]
  2%|▏         | 2896896/169674850 [00:00<00:25, 6443468.62it/s]
  5%|▍         | 8446976/169674850 [00:00<00:09, 16471602.34it/s]
  9%|▉         | 15408128/169674850 [00:00<00:05, 26563787.78it/s]
 11%|█▏        | 19464192/169674850 [00:01<00:05, 29596138.22it/s]
 13%|█▎        | 22580224/169674850 [00:01<00:04, 29788663.30it/s]
 17%|█▋        | 29080576/169674850 [00:01<00:04, 33907435.28it/s]
 21%|██        | 35999744/169674850 [00:01<00:03, 38329591.68it/s]
 24%|██▎       | 40099840/169674850 [00:01<00:03, 38712580.08it/s]
 26%|██▌       | 44521472/169674850 [00:01<00:03, 40112349.50it/s]
 29%|██▉       | 49608704/169674850 [00:01<00:02, 41070142.57it/s]
 32%|███▏      | 54135808/169674850 [00:01<00:02, 40104581.28it/s]
 36%|███▌      | 61020160/169674850 [00:02<00:02, 40614439.78it/s]
 38%|███▊      | 65084416/169674850 [00:02<00:02, 38652081.25it/s]
 42%|████▏     | 70933504/169674850 [00:02<00:02, 38257594.46it/s]
 46%|████▌     | 77712384/169674850 [00:02<00:02, 41578232.13it/s]
 48%|████▊     | 81867776/169674850 [00:02<00:02, 40640200.41it/s]
 51%|█████     | 85913600/169674850 [00:02<00:02, 39562714.32it/s]
 54%|█████▎    | 90973184/169674850 [00:02<00:01, 40353154.67it/s]
 56%|█████▌    | 95031296/169674850 [00:02<00:01, 38705146.30it/s]
 61%|██████    | 102993920/169674850 [00:03<00:01, 49425919.41it/s]
 64%|██████▎   | 108081152/169674850 [00:03<00:01, 42928787.48it/s]
 66%|██████▋   | 112602112/169674850 [00:03<00:01, 41564466.06it/s]
 69%|██████▉   | 116911104/169674850 [00:03<00:01, 41885646.89it/s]
 71%|███████▏  | 121211904/169674850 [00:03<00:01, 41718055.09it/s]
 74%|███████▍  | 125819904/169674850 [00:03<00:01, 37107881.88it/s]
 79%|███████▊  | 133412864/169674850 [00:03<00:00, 46908784.46it/s]
 82%|████████▏ | 138386432/169674850 [00:03<00:00, 41792796.23it/s]
 86%|████████▌ | 146040832/169674850 [00:04<00:00, 43646992.27it/s]
 89%|████████▊ | 150574080/169674850 [00:04<00:00, 43493707.46it/s]
 93%|█████████▎| 157418496/169674850 [00:04<00:00, 48197586.76it/s]
 96%|█████████▌| 162366464/169674850 [00:04<00:00, 44553941.99it/s]
 99%|█████████▉| 167759872/169674850 [00:04<00:00, 41686471.30it/s]
169675776it [00:04, 36819867.91it/s]
Extracting ../../tutorials/data/NMNIST/test.zip to ../../tutorials/data/NMNIST

import tonic

nmnist = tonic.datasets.NMNIST("../../tutorials/data", train=False)
events, label = nmnist[0]

transform = tonic.transforms.ToVoxelGrid(
    sensor_size=nmnist.sensor_size,
    n_time_bins=20,
)

frames = transform(events)

ani = tonic.utils.plot_animation(frames)