| User | harsidh |
| Upload Date | July 06 2025 09:05 AM |
| Views | 11 |
| AI Information | |
|---|---|
| Framework | TensorFlow Lite |
| Backend | GPU |
| Device | Samsung Exynos 9611 |
| System Information | |
|---|---|
| Operating System | Android 12 |
| Model | Samsung Galaxy M31 |
| Model ID | samsung SM-M315F |
| Motherboard | exynos9611 |
| Governor | schedutil |
| CPU Information | |
|---|---|
| Name | ARM ARMv8 |
| Topology | 1 Processor, 8 Cores |
| Identifier | ARM implementer 65 architecture 8 variant 0 part 3337 revision 2 |
| Base Frequency | 1.74 GHz |
| Cluster 1 | 4 Cores @ 1.74 GHz |
| Cluster 2 | 4 Cores @ 2.31 GHz |
| Memory Information | |
|---|---|
| Size | 5.44 GB |
| Workload | Accuracy | Score | |
|---|---|---|---|
|
Image Classification (SP)
|
100% |
170
31.5 IPS |
|
|
Image Classification (HP)
|
100% |
269
50.0 IPS |
|
|
Image Classification (Q)
|
97% |
251
46.8 IPS |
|
|
Image Segmentation (SP)
|
100% |
264
4.27 IPS |
|
|
Image Segmentation (HP)
|
100% |
477
7.73 IPS |
|
|
Image Segmentation (Q)
|
98% |
442
7.19 IPS |
|
|
Pose Estimation (SP)
|
100% |
1105
1.29 IPS |
|
|
Pose Estimation (HP)
|
100% |
2150
2.51 IPS |
|
|
Pose Estimation (Q)
|
95% |
2098
2.46 IPS |
|
|
Object Detection (SP)
|
100% |
168
13.3 IPS |
|
|
Object Detection (HP)
|
99% |
289
22.9 IPS |
|
|
Object Detection (Q)
|
83% |
271
21.9 IPS |
|
|
Face Detection (SP)
|
100% |
604
7.18 IPS |
|
|
Face Detection (HP)
|
100% |
1003
11.9 IPS |
|
|
Face Detection (Q)
|
96% |
850
10.1 IPS |
|
|
Depth Estimation (SP)
|
100% |
665
5.13 IPS |
|
|
Depth Estimation (HP)
|
98% |
1240
9.58 IPS |
|
|
Depth Estimation (Q)
|
62% |
975
9.26 IPS |
|
|
Style Transfer (SP)
|
100% |
1412
1.81 IPS |
|
|
Style Transfer (HP)
|
100% |
2896
3.72 IPS |
|
|
Style Transfer (Q)
|
98% |
2885
3.72 IPS |
|
|
Image Super-Resolution (SP)
|
100% |
454
16.8 IPS |
|
|
Image Super-Resolution (HP)
|
100% |
735
27.1 IPS |
|
|
Image Super-Resolution (Q)
|
97% |
764
28.3 IPS |
|
|
Text Classification (SP)
|
35% |
10
102.2 IPS |
|
|
Text Classification (HP)
|
35% |
14
123.1 IPS |
|
|
Text Classification (Q)
|
33% |
11
127.5 IPS |
|
|
Machine Translation (SP)
|
100% |
187
3.23 IPS |
|
|
Machine Translation (HP)
|
100% |
218
3.75 IPS |
|
|
Machine Translation (Q)
|
43% |
49
2.82 IPS |