Upload Date | November 20 2024 05:22 AM |
Views | 1 |
AI Information | |
---|---|
Framework | TensorFlow Lite |
Backend | CPU |
Device | Qualcomm Snapdragon 865 |
System Information | |
---|---|
Operating System | Android 13 |
Model | Samsung Galaxy Tab S7+ |
Model ID | samsung SM-T970 |
Motherboard | kona |
Governor | schedutil |
CPU Information | |
---|---|
Name | ARM Qualcomm |
Topology | 1 Processor, 8 Cores |
Identifier | ARM implementer 65 architecture 8 variant 1 part 3341 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 @ 3.09 GHz |
Memory Information | |
---|---|
Size | 5.50 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
457
85.0 IPS |
|
Image Classification (HP)
|
100% |
348
64.8 IPS |
|
Image Classification (Q)
|
100% |
1322
245.8 IPS |
|
Image Segmentation (SP)
|
100% |
551
8.93 IPS |
|
Image Segmentation (HP)
|
100% |
511
8.29 IPS |
|
Image Segmentation (Q)
|
98% |
1563
25.4 IPS |
|
Pose Estimation (SP)
|
100% |
1913
2.23 IPS |
|
Pose Estimation (HP)
|
100% |
1885
2.20 IPS |
|
Pose Estimation (Q)
|
84% |
3124
3.71 IPS |
|
Object Detection (SP)
|
100% |
443
35.1 IPS |
|
Object Detection (HP)
|
100% |
440
34.9 IPS |
|
Object Detection (Q)
|
83% |
1210
97.7 IPS |
|
Face Detection (SP)
|
100% |
1287
15.3 IPS |
|
Face Detection (HP)
|
100% |
1370
16.3 IPS |
|
Face Detection (Q)
|
95% |
2959
35.3 IPS |
|
Depth Estimation (SP)
|
100% |
1557
12.0 IPS |
|
Depth Estimation (HP)
|
99% |
1670
12.9 IPS |
|
Depth Estimation (Q)
|
64% |
2381
21.8 IPS |
|
Style Transfer (SP)
|
89% |
3610
4.69 IPS |
|
Style Transfer (HP)
|
89% |
3592
4.66 IPS |
|
Style Transfer (Q)
|
98% |
7277
9.38 IPS |
|
Image Super-Resolution (SP)
|
100% |
976
36.0 IPS |
|
Image Super-Resolution (HP)
|
100% |
970
35.8 IPS |
|
Image Super-Resolution (Q)
|
97% |
1831
67.8 IPS |
|
Text Classification (SP)
|
100% |
536
715.7 IPS |
|
Text Classification (HP)
|
100% |
173
230.6 IPS |
|
Text Classification (Q)
|
88% |
282
380.4 IPS |
|
Machine Translation (SP)
|
100% |
252
4.33 IPS |
|
Machine Translation (HP)
|
100% |
250
4.30 IPS |
|
Machine Translation (Q)
|
50% |
164
5.83 IPS |