Upload Date | September 11 2024 09:58 AM |
Views | 1 |
AI Information | |
---|---|
Framework | TensorFlow Lite |
Backend | CPU |
Device | ARM MT6762V/WB |
System Information | |
---|---|
Operating System | Android 13 |
Model | HMD Global Nokia G10 |
Model ID | HMD Global Nokia G10 |
Motherboard | MT6762 |
CPU Information | |
---|---|
Name | ARM MT6762V/WB |
Topology | 1 Processor, 8 Cores |
Identifier | ARM implementer 65 architecture 8 variant 0 part 3331 revision 4 |
Base Frequency | 2.00 GHz |
Cluster 1 | 4 Cores @ 1.50 GHz |
Cluster 2 | 4 Cores @ 2.00 GHz |
Memory Information | |
---|---|
Size | 2.74 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
134
24.8 IPS |
|
Image Classification (HP)
|
100% |
136
25.3 IPS |
|
Image Classification (Q)
|
100% |
162
30.2 IPS |
|
Image Segmentation (SP)
|
100% |
165
2.67 IPS |
|
Image Segmentation (HP)
|
100% |
151
2.45 IPS |
|
Image Segmentation (Q)
|
98% |
250
4.07 IPS |
|
Pose Estimation (SP)
|
100% |
660
0.77 IPS |
|
Pose Estimation (HP)
|
100% |
642
0.75 IPS |
|
Pose Estimation (Q)
|
84% |
475
0.56 IPS |
|
Object Detection (SP)
|
100% |
143
11.4 IPS |
|
Object Detection (HP)
|
100% |
144
11.4 IPS |
|
Object Detection (Q)
|
83% |
199
16.1 IPS |
|
Face Detection (SP)
|
100% |
356
4.23 IPS |
|
Face Detection (HP)
|
100% |
357
4.24 IPS |
|
Face Detection (Q)
|
95% |
547
6.53 IPS |
|
Depth Estimation (SP)
|
100% |
493
3.80 IPS |
|
Depth Estimation (HP)
|
99% |
483
3.72 IPS |
|
Depth Estimation (Q)
|
64% |
440
4.03 IPS |
|
Style Transfer (SP)
|
89% |
1155
1.50 IPS |
|
Style Transfer (HP)
|
89% |
1164
1.51 IPS |
|
Style Transfer (Q)
|
98% |
1189
1.53 IPS |
|
Image Super-Resolution (SP)
|
100% |
170
6.29 IPS |
|
Image Super-Resolution (HP)
|
100% |
171
6.31 IPS |
|
Image Super-Resolution (Q)
|
97% |
240
8.89 IPS |
|
Text Classification (SP)
|
100% |
100
133.8 IPS |
|
Text Classification (HP)
|
100% |
141
188.6 IPS |
|
Text Classification (Q)
|
88% |
96
129.6 IPS |
|
Machine Translation (SP)
|
100% |
149
2.57 IPS |
|
Machine Translation (HP)
|
100% |
196
3.37 IPS |
|
Machine Translation (Q)
|
50% |
66
2.34 IPS |