Upload Date | January 19 2025 06:59 AM |
Views | 2 |
AI Information | |
---|---|
Framework | TensorFlow Lite |
Backend | CPU |
Device | ARM ARMv8 |
System Information | |
---|---|
Operating System | Android 14 |
Model | samsung SM-X826B |
Model ID | samsung SM-X826B |
Motherboard | gts10p |
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 | 10.96 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
1684
313.1 IPS |
|
Image Classification (HP)
|
100% |
1786
332.1 IPS |
|
Image Classification (Q)
|
100% |
2639
490.7 IPS |
|
Image Segmentation (SP)
|
100% |
2108
34.2 IPS |
|
Image Segmentation (HP)
|
100% |
2089
33.9 IPS |
|
Image Segmentation (Q)
|
98% |
2781
45.2 IPS |
|
Pose Estimation (SP)
|
100% |
3145
3.67 IPS |
|
Pose Estimation (HP)
|
100% |
2962
3.46 IPS |
|
Pose Estimation (Q)
|
84% |
4982
5.91 IPS |
|
Object Detection (SP)
|
98% |
1254
99.8 IPS |
|
Object Detection (HP)
|
98% |
1265
100.7 IPS |
|
Object Detection (Q)
|
83% |
1885
152.3 IPS |
|
Face Detection (SP)
|
100% |
2797
33.2 IPS |
|
Face Detection (HP)
|
100% |
2792
33.2 IPS |
|
Face Detection (Q)
|
95% |
4622
55.2 IPS |
|
Depth Estimation (SP)
|
99% |
3189
24.6 IPS |
|
Depth Estimation (HP)
|
99% |
3162
24.4 IPS |
|
Depth Estimation (Q)
|
64% |
4856
44.5 IPS |
|
Style Transfer (SP)
|
89% |
6584
8.55 IPS |
|
Style Transfer (HP)
|
89% |
6372
8.27 IPS |
|
Style Transfer (Q)
|
98% |
10995
14.2 IPS |
|
Image Super-Resolution (SP)
|
100% |
1305
48.2 IPS |
|
Image Super-Resolution (HP)
|
100% |
1315
48.6 IPS |
|
Image Super-Resolution (Q)
|
97% |
2732
101.3 IPS |
|
Text Classification (SP)
|
100% |
594
792.4 IPS |
|
Text Classification (HP)
|
99% |
596
795.8 IPS |
|
Text Classification (Q)
|
88% |
1050
1.42 KIPS |
|
Machine Translation (SP)
|
100% |
1524
26.2 IPS |
|
Machine Translation (HP)
|
100% |
1626
28.0 IPS |
|
Machine Translation (Q)
|
50% |
718
25.5 IPS |