| Upload Date | October 30 2025 10:49 PM | 
| Views | 2 | 
| AI Information | |
|---|---|
| Framework | TensorFlow Lite | 
| Backend | GPU | 
| Device | ARM ARMv8 | 
| System Information | |
|---|---|
| Operating System | Android 14 | 
| Model | samsung SM-I610 | 
| Model ID | samsung SM-I610 | 
| Motherboard | anorak | 
| Governor | walt | 
| CPU Information | |
|---|---|
| Name | ARM ARMv8 | 
| Topology | 1 Processor, 6 Cores | 
| Identifier | ARM implementer 65 architecture 8 variant 0 part 3403 revision 2 | 
| Base Frequency | 2.36 GHz | 
| Cluster 1 | 6 Cores @ 2.36 GHz | 
| Memory Information | |
|---|---|
| Size | 15.32 GB | 
| Workload | Accuracy | Score | |
|---|---|---|---|
| Image Classification (SP) | 100% | 954 177.5 IPS | |
| Image Classification (HP) | 100% | 1451 269.9 IPS | |
| Image Classification (Q) | 100% | 1203 223.7 IPS | |
| Image Segmentation (SP) | 100% | 1757 28.5 IPS | |
| Image Segmentation (HP) | 100% | 3077 49.9 IPS | |
| Image Segmentation (Q) | 98% | 2530 41.1 IPS | |
| Pose Estimation (SP) | 100% | 6543 7.63 IPS | |
| Pose Estimation (HP) | 99% | 12433 14.5 IPS | |
| Pose Estimation (Q) | 96% | 12301 14.4 IPS | |
| Object Detection (SP) | 100% | 888 70.4 IPS | |
| Object Detection (HP) | 99% | 1272 100.9 IPS | |
| Object Detection (Q) | 87% | 1191 95.6 IPS | |
| Face Detection (SP) | 100% | 2708 32.2 IPS | |
| Face Detection (HP) | 100% | 4488 53.3 IPS | |
| Face Detection (Q) | 97% | 3858 46.0 IPS | |
| Depth Estimation (SP) | 100% | 3371 26.0 IPS | |
| Depth Estimation (HP) | 98% | 4522 35.0 IPS | |
| Depth Estimation (Q) | 61% | 3434 33.8 IPS | |
| Style Transfer (SP) | 100% | 8672 11.1 IPS | |
| Style Transfer (HP) | 100% | 18684 24.0 IPS | |
| Style Transfer (Q) | 98% | 18593 24.0 IPS | |
| Image Super-Resolution (SP) | 100% | 1991 73.5 IPS | |
| Image Super-Resolution (HP) | 100% | 3266 120.6 IPS | |
| Image Super-Resolution (Q) | 97% | 3238 120.0 IPS | |
| Text Classification (SP) | 35% | 32 313.6 IPS | |
| Text Classification (HP) | 35% | 52 476.9 IPS | |
| Text Classification (Q) | 33% | 39 471.7 IPS | |
| Machine Translation (SP) | 100% | 644 11.1 IPS | |
| Machine Translation (HP) | 97% | 675 11.7 IPS | |
| Machine Translation (Q) | 43% | 177 10.1 IPS |