Model
UNet3D TensorFlow checkpoint trained with AMP
Use the NGC CLI to download:
Copied!
1 Version
20.06.0_ampSelected09/22/2022 4:50 PM UTC371.72 MBAccuracy: 00 EpochsBatch Size: 2GPU: V100 Copied!
20.06.0_ampSelected
09/22/2022 4:50 PM UTC371.72 MBAccuracy: 00 EpochsBatch Size: 2GPU: V100
Copied!
architecture
| Key | Value |
|---|---|
| type | base |
performance
| Key | Value |
|---|---|
| EnchancingTumor | 0.732291579246521 |
| MeanDice | 0.7127919594446818 |
| PeritumoralEdema | 0.7337265610694885 |
| TumorCore | 0.6723577380180359 |
| WholeTumor | 0.892531156539917 |
training
| Key | Value |
|---|---|
| batch_size | 2 |
| training_precision | AMP |
| dataset | Brain Tumor Segmentation Challenge 2019 |
| learning_rate | 0.0002 |
| iterations | 16000 |