Model
UNet_Medical TensorFlow2 checkpoint trained with AMP
Use the NGC CLI to download:
Copied!
2 Versions
21.02.0Selected03/10/2021 6:38 PM UTC394.99 MBAccuracy: 00 EpochsBatch Size: 8GPU: V100 Copied!
21.02.0Selected
03/10/2021 6:38 PM UTC394.99 MBAccuracy: 00 EpochsBatch Size: 8GPU: V100
Copied!
architecture
| Key | Value |
|---|---|
| type | base |
performance
| Key | Value |
|---|---|
| eval_ce_loss | 0.21992358565330505 |
| eval_dice_loss | 0.1065923273563385 |
| eval_dice_score | 0.8934076726436615 |
| eval_total_loss | 0.32651591300964355 |
training
| Key | Value |
|---|---|
| batch_size | 8 |
| dataset | EM segmentation challenge |
| iterations | 6400 |
| learning_rate | 0.0001 |
| training_precision | AMP |
08/21/2020 3:26 AM UTC395 MBAccuracy: 00 EpochsBatch Size: 8GPU: V100 Copied!
08/21/2020 3:26 AM UTC395 MBAccuracy: 00 EpochsBatch Size: 8GPU: V100
Copied!
architecture
| Key | Value |
|---|---|
| type | base |
performance
| Key | Value |
|---|---|
| eval_ce_loss | 0.22019703686237335 |
| eval_dice_loss | 0.10762041807174683 |
| eval_dice_score | 0.8923795819282532 |
| eval_total_loss | 0.327817440032959 |
training
| Key | Value |
|---|---|
| batch_size | 8 |
| dataset | EM segmentation challenge |
| iterations | 6400 |
| learning_rate | 0.0001 |
| training_precision | AMP |