Upload Date | September 25 2024 02:39 PM |
Views | 3 |
AI Information | |
---|---|
Framework | TensorFlow Lite |
Backend | QNN |
Device | Qualcomm Snapdragon 888 |
System Information | |
---|---|
Operating System | Android 13 |
Model | Sony Xperia 5 III |
Model ID | Sony SOG05 |
Motherboard | lahaina |
Governor | schedutil |
CPU Information | |
---|---|
Name | ARM ARMv8 |
Topology | 1 Processor, 8 Cores |
Identifier | ARM implementer 65 architecture 8 variant 1 part 3396 revision 0 |
Base Frequency | 1.80 GHz |
Cluster 1 | 4 Cores @ 1.80 GHz |
Cluster 2 | 3 Cores @ 2.42 GHz |
Cluster 3 | 1 Core @ 2.84 GHz |
Memory Information | |
---|---|
Size | 7.03 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
209
38.9 IPS |
|
Image Classification (HP)
|
100% |
210
39.1 IPS |
|
Image Classification (Q)
|
99% |
9554
1.78 KIPS |
|
Image Segmentation (SP)
|
100% |
261
4.23 IPS |
|
Image Segmentation (HP)
|
100% |
264
4.27 IPS |
|
Image Segmentation (Q)
|
98% |
10334
168.0 IPS |
|
Pose Estimation (SP)
|
100% |
320
0.37 IPS |
|
Pose Estimation (HP)
|
100% |
315
0.37 IPS |
|
Pose Estimation (Q)
|
94% |
89813
105.3 IPS |
|
Object Detection (SP)
|
100% |
128
10.2 IPS |
|
Object Detection (HP)
|
100% |
129
10.2 IPS |
|
Object Detection (Q)
|
88% |
5534
443.3 IPS |
|
Face Detection (SP)
|
100% |
499
5.92 IPS |
|
Face Detection (HP)
|
100% |
499
5.93 IPS |
|
Face Detection (Q)
|
97% |
30712
366.2 IPS |
|
Depth Estimation (SP)
|
100% |
411
3.17 IPS |
|
Depth Estimation (HP)
|
99% |
408
3.14 IPS |
|
Depth Estimation (Q)
|
64% |
32166
296.1 IPS |
|
Style Transfer (SP)
|
100% |
452
0.58 IPS |
|
Style Transfer (HP)
|
100% |
673
0.87 IPS |
|
Style Transfer (Q)
|
98% |
94129
121.4 IPS |
|
Image Super-Resolution (SP)
|
100% |
141
5.21 IPS |
|
Image Super-Resolution (HP)
|
100% |
141
5.21 IPS |
|
Image Super-Resolution (Q)
|
97% |
30074
1.11 KIPS |
|
Text Classification (SP)
|
100% |
319
425.5 IPS |
|
Text Classification (HP)
|
100% |
319
426.2 IPS |
|
Text Classification (Q)
|
94% |
2189
2.94 KIPS |
|
Machine Translation (SP)
|
100% |
490
8.43 IPS |
|
Machine Translation (HP)
|
100% |
479
8.25 IPS |
|
Machine Translation (Q)
|
37% |
136
13.7 IPS |