Upload Date | January 27 2025 05:20 PM |
Views | 4 |
AI Information | |
---|---|
Framework | TensorFlow Lite |
Backend | QNN |
Device | Qualcomm ARMv8 |
System Information | |
---|---|
Operating System | Android 15 |
Model | samsung SM-S938B |
Model ID | samsung SM-S938B |
Motherboard | sun |
Governor | walt |
CPU Information | |
---|---|
Name | Qualcomm ARMv8 |
Topology | 1 Processor, 8 Cores |
Identifier | ARM implementer 81 architecture 8 variant 3 part 1 revision 4 |
Base Frequency | 3.53 GHz |
Cluster 1 | 6 Cores @ 3.53 GHz |
Cluster 2 | 2 Cores @ 4.47 GHz |
Memory Information | |
---|---|
Size | 10.86 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
467
86.8 IPS |
|
Image Classification (HP)
|
100% |
21936
4.08 KIPS |
|
Image Classification (Q)
|
97% |
49474
9.23 KIPS |
|
Image Segmentation (SP)
|
100% |
598
9.70 IPS |
|
Image Segmentation (HP)
|
100% |
13679
221.8 IPS |
|
Image Segmentation (Q)
|
98% |
42650
693.5 IPS |
|
Pose Estimation (SP)
|
100% |
769
0.90 IPS |
|
Pose Estimation (HP)
|
100% |
123951
144.6 IPS |
|
Pose Estimation (Q)
|
98% |
479439
561.2 IPS |
|
Object Detection (SP)
|
100% |
392
31.1 IPS |
|
Object Detection (HP)
|
100% |
19513
1.55 KIPS |
|
Object Detection (Q)
|
85% |
22519
1.81 KIPS |
|
Face Detection (SP)
|
100% |
1106
13.1 IPS |
|
Face Detection (HP)
|
100% |
44398
527.5 IPS |
|
Face Detection (Q)
|
97% |
162385
1.94 KIPS |
|
Depth Estimation (SP)
|
100% |
963
7.42 IPS |
|
Depth Estimation (HP)
|
99% |
84468
650.8 IPS |
|
Depth Estimation (Q)
|
63% |
146339
1.35 KIPS |
|
Style Transfer (SP)
|
100% |
1427
1.83 IPS |
|
Style Transfer (HP)
|
98% |
99047
127.7 IPS |
|
Style Transfer (Q)
|
98% |
495188
638.5 IPS |
|
Image Super-Resolution (SP)
|
100% |
458
16.9 IPS |
|
Image Super-Resolution (HP)
|
100% |
55515
2.05 KIPS |
|
Image Super-Resolution (Q)
|
97% |
135466
5.02 KIPS |
|
Text Classification (SP)
|
100% |
622
830.0 IPS |
|
Text Classification (HP)
|
100% |
3936
5.25 KIPS |
|
Text Classification (Q)
|
93% |
8058
10.8 KIPS |
|
Machine Translation (SP)
|
100% |
1085
18.7 IPS |
|
Machine Translation (HP)
|
100% |
4834
83.3 IPS |
|
Machine Translation (Q)
|
56% |
3249
83.7 IPS |