| User | gbirkin |
| Upload Date | July 02 2025 04:18 PM |
| Views | 5 |
| AI Information | |
|---|---|
| Framework | TensorFlow Lite |
| Backend | GPU |
| Device | Qualcomm Snapdragon 855 |
| System Information | |
|---|---|
| Operating System | Android 12 |
| Model | Samsung Galaxy Tab S6 |
| Model ID | samsung SM-T865 |
| Motherboard | msmnile |
| Governor | schedutil |
| CPU Information | |
|---|---|
| Name | Qualcomm Qualcomm |
| Topology | 1 Processor, 8 Cores |
| Identifier | ARM implementer 81 architecture 8 variant 13 part 2052 revision 14 |
| Base Frequency | 1.78 GHz |
| Cluster 1 | 4 Cores @ 1.79 GHz |
| Cluster 2 | 3 Cores @ 2.42 GHz |
| Cluster 3 | 1 Core @ 2.84 GHz |
| Memory Information | |
|---|---|
| Size | 5.32 GB |
| Workload | Accuracy | Score | |
|---|---|---|---|
|
Image Classification (SP)
|
100% |
557
103.6 IPS |
|
|
Image Classification (HP)
|
100% |
851
158.2 IPS |
|
|
Image Classification (Q)
|
99% |
796
148.4 IPS |
|
|
Image Segmentation (SP)
|
100% |
879
14.2 IPS |
|
|
Image Segmentation (HP)
|
100% |
1358
22.0 IPS |
|
|
Image Segmentation (Q)
|
98% |
1231
20.0 IPS |
|
|
Pose Estimation (SP)
|
100% |
3341
3.90 IPS |
|
|
Pose Estimation (HP)
|
99% |
5622
6.56 IPS |
|
|
Pose Estimation (Q)
|
97% |
5482
6.42 IPS |
|
|
Object Detection (SP)
|
100% |
441
35.0 IPS |
|
|
Object Detection (HP)
|
99% |
615
48.8 IPS |
|
|
Object Detection (Q)
|
85% |
585
47.0 IPS |
|
|
Face Detection (SP)
|
100% |
1619
19.2 IPS |
|
|
Face Detection (HP)
|
100% |
2527
30.0 IPS |
|
|
Face Detection (Q)
|
97% |
2233
26.6 IPS |
|
|
Depth Estimation (SP)
|
100% |
1694
13.1 IPS |
|
|
Depth Estimation (HP)
|
98% |
2457
19.0 IPS |
|
|
Depth Estimation (Q)
|
63% |
2019
18.6 IPS |
|
|
Style Transfer (SP)
|
100% |
4156
5.34 IPS |
|
|
Style Transfer (HP)
|
100% |
7910
10.2 IPS |
|
|
Style Transfer (Q)
|
98% |
7779
10.0 IPS |
|
|
Image Super-Resolution (SP)
|
100% |
862
31.8 IPS |
|
|
Image Super-Resolution (HP)
|
100% |
1293
47.8 IPS |
|
|
Image Super-Resolution (Q)
|
97% |
1273
47.2 IPS |
|
|
Text Classification (SP)
|
35% |
28
276.8 IPS |
|
|
Text Classification (HP)
|
35% |
40
361.8 IPS |
|
|
Text Classification (Q)
|
35% |
38
348.4 IPS |
|
|
Machine Translation (SP)
|
100% |
375
6.46 IPS |
|
|
Machine Translation (HP)
|
97% |
413
7.14 IPS |
|
|
Machine Translation (Q)
|
64% |
333
6.84 IPS |