User | RolandFromHolland85 |
Upload Date | August 20 2024 12:14 AM |
Views | 5 |
AI Information | |
---|---|
Framework | TensorFlow Lite |
Backend | NNAPI |
Device | ARM Qualcomm |
System Information | |
---|---|
Operating System | Android 13 |
Model | Fairphone FP4 |
Model ID | Fairphone FP4 |
Motherboard | FP4 |
Governor | schedutil |
CPU Information | |
---|---|
Name | ARM Qualcomm |
Topology | 1 Processor, 8 Cores |
Identifier | ARM implementer 65 architecture 8 variant 1 part 3341 revision 0 |
Base Frequency | 1.80 GHz |
Cluster 1 | 6 Cores @ 1.80 GHz |
Cluster 2 | 2 Cores @ 2.21 GHz |
Memory Information | |
---|---|
Size | 5.36 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
189
35.2 IPS |
|
Image Classification (HP)
|
100% |
244
45.3 IPS |
|
Image Classification (Q)
|
97% |
584
109.0 IPS |
|
Image Segmentation (SP)
|
100% |
237
3.84 IPS |
|
Image Segmentation (HP)
|
100% |
155
2.51 IPS |
|
Image Segmentation (Q)
|
98% |
755
12.3 IPS |
|
Pose Estimation (SP)
|
100% |
535
0.62 IPS |
|
Pose Estimation (HP)
|
100% |
1235
1.44 IPS |
|
Pose Estimation (Q)
|
96% |
4337
5.08 IPS |
|
Object Detection (SP)
|
100% |
178
14.1 IPS |
|
Object Detection (HP)
|
100% |
115
9.10 IPS |
|
Object Detection (Q)
|
89% |
630
50.4 IPS |
|
Face Detection (SP)
|
100% |
363
4.31 IPS |
|
Face Detection (HP)
|
100% |
283
3.36 IPS |
|
Face Detection (Q)
|
97% |
1687
20.1 IPS |
|
Depth Estimation (SP)
|
99% |
333
2.57 IPS |
|
Depth Estimation (HP)
|
100% |
244
1.88 IPS |
|
Depth Estimation (Q)
|
79% |
3259
25.9 IPS |
|
Style Transfer (SP)
|
100% |
554
0.71 IPS |
|
Style Transfer (HP)
|
100% |
408
0.52 IPS |
|
Style Transfer (Q)
|
98% |
2586
3.33 IPS |
|
Image Super-Resolution (SP)
|
100% |
310
11.5 IPS |
|
Image Super-Resolution (HP)
|
100% |
579
21.4 IPS |
|
Image Super-Resolution (Q)
|
97% |
1960
72.6 IPS |
|
Text Classification (SP)
|
71% |
3
4.60 IPS |
|
Text Classification (HP)
|
100% |
161
214.5 IPS |
|
Text Classification (Q)
|
93% |
112
150.5 IPS |
|
Machine Translation (SP)
|
100% |
99
1.71 IPS |
|
Machine Translation (HP)
|
100% |
268
4.62 IPS |
|
Machine Translation (Q)
|
54% |
149
4.20 IPS |