Upload Date | January 27 2025 05:09 PM |
Views | 3 |
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% |
469
87.1 IPS |
|
Image Classification (HP)
|
100% |
21029
3.91 KIPS |
|
Image Classification (Q)
|
97% |
49578
9.25 KIPS |
|
Image Segmentation (SP)
|
100% |
604
9.80 IPS |
|
Image Segmentation (HP)
|
100% |
13688
221.9 IPS |
|
Image Segmentation (Q)
|
98% |
42477
690.7 IPS |
|
Pose Estimation (SP)
|
100% |
780
0.91 IPS |
|
Pose Estimation (HP)
|
100% |
122832
143.3 IPS |
|
Pose Estimation (Q)
|
98% |
478684
560.3 IPS |
|
Object Detection (SP)
|
100% |
432
34.3 IPS |
|
Object Detection (HP)
|
100% |
19695
1.56 KIPS |
|
Object Detection (Q)
|
85% |
22900
1.84 KIPS |
|
Face Detection (SP)
|
100% |
1093
13.0 IPS |
|
Face Detection (HP)
|
100% |
44395
527.5 IPS |
|
Face Detection (Q)
|
97% |
164098
1.96 KIPS |
|
Depth Estimation (SP)
|
100% |
958
7.38 IPS |
|
Depth Estimation (HP)
|
99% |
84758
653.0 IPS |
|
Depth Estimation (Q)
|
63% |
147255
1.36 KIPS |
|
Style Transfer (SP)
|
100% |
1586
2.04 IPS |
|
Style Transfer (HP)
|
98% |
98848
127.5 IPS |
|
Style Transfer (Q)
|
98% |
491224
633.4 IPS |
|
Image Super-Resolution (SP)
|
100% |
388
14.3 IPS |
|
Image Super-Resolution (HP)
|
100% |
54963
2.03 KIPS |
|
Image Super-Resolution (Q)
|
97% |
135009
5.00 KIPS |
|
Text Classification (SP)
|
100% |
621
829.4 IPS |
|
Text Classification (HP)
|
100% |
3927
5.24 KIPS |
|
Text Classification (Q)
|
93% |
8065
10.8 KIPS |
|
Machine Translation (SP)
|
100% |
1083
18.7 IPS |
|
Machine Translation (HP)
|
100% |
4862
83.8 IPS |
|
Machine Translation (Q)
|
56% |
3242
83.5 IPS |