Upload Date | September 17 2024 10:24 AM |
Views | 1 |
AI Information | |
---|---|
Framework | TensorFlow Lite |
Backend | GPU |
Device | ARM ARMv8 |
System Information | |
---|---|
Operating System | Android 14 |
Model | SHARP SH-M26 |
Model ID | SHARP SH-M26 |
Motherboard | Quess |
Governor | walt |
CPU Information | |
---|---|
Name | ARM ARMv8 |
Topology | 1 Processor, 8 Cores |
Identifier | ARM implementer 65 architecture 8 variant 1 part 3393 revision 2 |
Base Frequency | 1.80 GHz |
Cluster 1 | 4 Cores @ 1.80 GHz |
Cluster 2 | 4 Cores @ 2.21 GHz |
Memory Information | |
---|---|
Size | 7.29 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
125
23.2 IPS |
|
Image Classification (HP)
|
100% |
214
39.8 IPS |
|
Image Classification (Q)
|
97% |
209
39.0 IPS |
|
Image Segmentation (SP)
|
100% |
184
2.98 IPS |
|
Image Segmentation (HP)
|
100% |
234
3.79 IPS |
|
Image Segmentation (Q)
|
98% |
225
3.66 IPS |
|
Pose Estimation (SP)
|
100% |
170
0.20 IPS |
|
Pose Estimation (HP)
|
100% |
259
0.30 IPS |
|
Pose Estimation (Q)
|
95% |
258
0.30 IPS |
|
Object Detection (SP)
|
100% |
86
6.80 IPS |
|
Object Detection (HP)
|
100% |
125
9.94 IPS |
|
Object Detection (Q)
|
89% |
124
9.92 IPS |
|
Face Detection (SP)
|
100% |
321
3.81 IPS |
|
Face Detection (HP)
|
100% |
447
5.31 IPS |
|
Face Detection (Q)
|
97% |
423
5.04 IPS |
|
Depth Estimation (SP)
|
100% |
245
1.89 IPS |
|
Depth Estimation (HP)
|
99% |
411
3.18 IPS |
|
Depth Estimation (Q)
|
63% |
333
3.13 IPS |
|
Style Transfer (SP)
|
100% |
536
0.69 IPS |
|
Style Transfer (HP)
|
100% |
1081
1.39 IPS |
|
Style Transfer (Q)
|
98% |
913
1.18 IPS |
|
Image Super-Resolution (SP)
|
100% |
93
3.44 IPS |
|
Image Super-Resolution (HP)
|
100% |
130
4.81 IPS |
|
Image Super-Resolution (Q)
|
97% |
129
4.76 IPS |
|
Text Classification (SP)
|
100% |
48
64.1 IPS |
|
Text Classification (HP)
|
100% |
49
64.9 IPS |
|
Text Classification (Q)
|
91% |
90
121.0 IPS |
|
Machine Translation (SP)
|
100% |
86
1.48 IPS |
|
Machine Translation (HP)
|
100% |
86
1.48 IPS |
|
Machine Translation (Q)
|
57% |
68
1.66 IPS |