Results for SSC-UNet
Submission data
| Full name | SSC-UNet64 |
| Description | UNet with 64 filters in the first layer, and double the number of filters each time the data is downsampled. Ran with 5cm voxel
https://github.com/facebookresearch/SparseConvNet |
| Input Data Types | Uses Color Uses 3D |
| Programming language(s) | pytorch |
| Hardware | Titan X |
| Submission creation date | 9 Nov, 2018 |
| Last edited | 10 Nov, 2018 |
3D semantic label results
| Info | avg iou | bathtub | bed | bookshelf | cabinet | chair | counter | curtain | desk | door | floor | otherfurniture | picture | refrigerator | shower curtain | sink | sofa | table | toilet | wall | window |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
 | 0.308 | 0.353 | 0.290 | 0.278 | 0.166 | 0.553 | 0.169 | 0.286 | 0.147 | 0.148 | 0.908 | 0.182 | 0.064 | 0.023 | 0.018 | 0.354 | 0.363 | 0.345 | 0.546 | 0.685 | 0.278 |