Upload Date | January 24 2025 04:38 AM |
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% |
479
89.0 IPS |
|
Image Classification (HP)
|
100% |
21713
4.04 KIPS |
|
Image Classification (Q)
|
97% |
49584
9.25 KIPS |
|
Image Segmentation (SP)
|
100% |
608
9.86 IPS |
|
Image Segmentation (HP)
|
100% |
13682
221.8 IPS |
|
Image Segmentation (Q)
|
98% |
42300
687.8 IPS |
|
Pose Estimation (SP)
|
100% |
778
0.91 IPS |
|
Pose Estimation (HP)
|
100% |
123496
144.1 IPS |
|
Pose Estimation (Q)
|
98% |
480470
562.4 IPS |
|
Object Detection (SP)
|
100% |
453
35.9 IPS |
|
Object Detection (HP)
|
100% |
19946
1.58 KIPS |
|
Object Detection (Q)
|
85% |
22947
1.85 KIPS |
|
Face Detection (SP)
|
100% |
1120
13.3 IPS |
|
Face Detection (HP)
|
100% |
44464
528.3 IPS |
|
Face Detection (Q)
|
97% |
162175
1.93 KIPS |
|
Depth Estimation (SP)
|
100% |
976
7.52 IPS |
|
Depth Estimation (HP)
|
99% |
84609
651.9 IPS |
|
Depth Estimation (Q)
|
63% |
145435
1.35 KIPS |
|
Style Transfer (SP)
|
100% |
1612
2.07 IPS |
|
Style Transfer (HP)
|
98% |
98793
127.4 IPS |
|
Style Transfer (Q)
|
98% |
492150
634.6 IPS |
|
Image Super-Resolution (SP)
|
100% |
463
17.1 IPS |
|
Image Super-Resolution (HP)
|
100% |
54467
2.01 KIPS |
|
Image Super-Resolution (Q)
|
97% |
134169
4.97 KIPS |
|
Text Classification (SP)
|
100% |
687
916.8 IPS |
|
Text Classification (HP)
|
100% |
3920
5.23 KIPS |
|
Text Classification (Q)
|
93% |
8078
10.8 KIPS |
|
Machine Translation (SP)
|
100% |
1102
19.0 IPS |
|
Machine Translation (HP)
|
100% |
4894
84.3 IPS |
|
Machine Translation (Q)
|
56% |
3275
84.4 IPS |