Upload Date | September 16 2024 01:57 PM |
Views | 1 |
AI Information | |
---|---|
Framework | TensorFlow Lite |
Backend | GPU |
Device | ARM ARMv8 |
System Information | |
---|---|
Operating System | Android 14 |
Model | samsung SM-X926B |
Model ID | samsung SM-X926B |
Motherboard | gts10u |
CPU Information | |
---|---|
Name | ARM ARMv8 |
Topology | 1 Processor, 8 Cores |
Identifier | ARM implementer 65 architecture 8 variant 0 part 3458 revision 1 |
Base Frequency | 2.00 GHz |
Cluster 1 | 4 Cores @ 2.00 GHz |
Cluster 2 | 3 Cores @ 2.85 GHz |
Cluster 3 | 1 Core @ 3.40 GHz |
Memory Information | |
---|---|
Size | 10.79 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
663
123.4 IPS |
|
Image Classification (HP)
|
100% |
694
129.1 IPS |
|
Image Classification (Q)
|
99% |
670
125.0 IPS |
|
Image Segmentation (SP)
|
100% |
1517
24.6 IPS |
|
Image Segmentation (HP)
|
100% |
1782
28.9 IPS |
|
Image Segmentation (Q)
|
98% |
1664
27.1 IPS |
|
Pose Estimation (SP)
|
100% |
791
0.92 IPS |
|
Pose Estimation (HP)
|
100% |
1199
1.40 IPS |
|
Pose Estimation (Q)
|
96% |
1203
1.41 IPS |
|
Object Detection (SP)
|
100% |
651
51.6 IPS |
|
Object Detection (HP)
|
100% |
732
58.1 IPS |
|
Object Detection (Q)
|
83% |
917
74.2 IPS |
|
Face Detection (SP)
|
100% |
2839
33.7 IPS |
|
Face Detection (HP)
|
100% |
2746
32.6 IPS |
|
Face Detection (Q)
|
97% |
2487
29.7 IPS |
|
Depth Estimation (SP)
|
100% |
1607
12.4 IPS |
|
Depth Estimation (HP)
|
99% |
2132
16.4 IPS |
|
Depth Estimation (Q)
|
62% |
1784
16.9 IPS |
|
Style Transfer (SP)
|
100% |
4284
5.51 IPS |
|
Style Transfer (HP)
|
100% |
5633
7.24 IPS |
|
Style Transfer (Q)
|
98% |
5595
7.21 IPS |
|
Image Super-Resolution (SP)
|
100% |
826
30.5 IPS |
|
Image Super-Resolution (HP)
|
100% |
1156
42.7 IPS |
|
Image Super-Resolution (Q)
|
97% |
1105
41.0 IPS |
|
Text Classification (SP)
|
100% |
306
408.5 IPS |
|
Text Classification (HP)
|
100% |
474
632.7 IPS |
|
Text Classification (Q)
|
91% |
763
1.03 KIPS |
|
Machine Translation (SP)
|
100% |
683
11.8 IPS |
|
Machine Translation (HP)
|
100% |
678
11.7 IPS |
|
Machine Translation (Q)
|
57% |
549
13.4 IPS |