| Upload Date | August 15 2024 03:48 AM |
| Views | 15 |
| AI Information | |
|---|---|
| Framework | TensorFlow Lite |
| Backend | CPU |
| Device | Qualcomm Snapdragon 888 |
| System Information | |
|---|---|
| Operating System | Android 14 |
| Model | Samsung Galaxy S21 Ultra 5G |
| Model ID | samsung SM-G998W |
| Motherboard | lahaina |
| Governor | schedutil |
| CPU Information | |
|---|---|
| Name | ARM SM8350 |
| Topology | 1 Processor, 8 Cores |
| Identifier | ARM implementer 65 architecture 8 variant 1 part 3396 revision 0 |
| Base Frequency | 1.80 GHz |
| Cluster 1 | 4 Cores @ 1.80 GHz |
| Cluster 2 | 3 Cores @ 2.42 GHz |
| Cluster 3 | 1 Core @ 2.84 GHz |
| Memory Information | |
|---|---|
| Size | 10.07 GB |
| Workload | Accuracy | Score | |
|---|---|---|---|
|
Image Classification (SP)
|
100% |
183
34.0 IPS |
|
|
Image Classification (HP)
|
100% |
177
32.9 IPS |
|
|
Image Classification (Q)
|
100% |
488
90.8 IPS |
|
|
Image Segmentation (SP)
|
100% |
201
3.26 IPS |
|
|
Image Segmentation (HP)
|
100% |
216
3.50 IPS |
|
|
Image Segmentation (Q)
|
98% |
539
8.77 IPS |
|
|
Pose Estimation (SP)
|
100% |
644
0.75 IPS |
|
|
Pose Estimation (HP)
|
100% |
635
0.74 IPS |
|
|
Pose Estimation (Q)
|
84% |
1091
1.29 IPS |
|
|
Object Detection (SP)
|
100% |
170
13.5 IPS |
|
|
Object Detection (HP)
|
100% |
170
13.5 IPS |
|
|
Object Detection (Q)
|
87% |
491
39.4 IPS |
|
|
Face Detection (SP)
|
100% |
378
4.49 IPS |
|
|
Face Detection (HP)
|
100% |
387
4.59 IPS |
|
|
Face Detection (Q)
|
95% |
934
11.1 IPS |
|
|
Depth Estimation (SP)
|
100% |
523
4.03 IPS |
|
|
Depth Estimation (HP)
|
100% |
526
4.05 IPS |
|
|
Depth Estimation (Q)
|
75% |
1224
9.92 IPS |
|
|
Style Transfer (SP)
|
89% |
1116
1.45 IPS |
|
|
Style Transfer (HP)
|
89% |
1121
1.46 IPS |
|
|
Style Transfer (Q)
|
98% |
2412
3.11 IPS |
|
|
Image Super-Resolution (SP)
|
100% |
308
11.4 IPS |
|
|
Image Super-Resolution (HP)
|
100% |
304
11.2 IPS |
|
|
Image Super-Resolution (Q)
|
97% |
620
23.0 IPS |
|
|
Text Classification (SP)
|
100% |
214
286.2 IPS |
|
|
Text Classification (HP)
|
100% |
171
227.9 IPS |
|
|
Text Classification (Q)
|
88% |
271
366.0 IPS |
|
|
Machine Translation (SP)
|
100% |
264
4.54 IPS |
|
|
Machine Translation (HP)
|
100% |
246
4.24 IPS |
|
|
Machine Translation (Q)
|
50% |
160
5.69 IPS |