User | CME |
Upload Date | August 15 2024 07:43 PM |
Views | 4 |
AI Information | |
---|---|
Framework | TensorFlow Lite |
Backend | NNAPI |
Device | Qualcomm Snapdragon 835 |
System Information | |
---|---|
Operating System | Android 14 |
Model | OnePlus 5T |
Model ID | OnePlus ONEPLUS A5010 |
Motherboard | msm8998 |
Governor | schedutil |
CPU Information | |
---|---|
Name | Qualcomm Qualcomm |
Topology | 1 Processor, 8 Cores |
Identifier | ARM implementer 81 architecture 8 variant 10 part 2048 revision 1 |
Base Frequency | 1.90 GHz |
Cluster 1 | 4 Cores @ 1.90 GHz |
Cluster 2 | 4 Cores @ 2.46 GHz |
Memory Information | |
---|---|
Size | 7.54 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
49
9.13 IPS |
|
Image Classification (HP)
|
100% |
49
9.19 IPS |
|
Image Classification (Q)
|
97% |
83
15.5 IPS |
|
Image Segmentation (SP)
|
100% |
66
1.07 IPS |
|
Image Segmentation (HP)
|
100% |
67
1.08 IPS |
|
Image Segmentation (Q)
|
98% |
92
1.50 IPS |
|
Pose Estimation (SP)
|
100% |
92
0.11 IPS |
|
Pose Estimation (HP)
|
100% |
92
0.11 IPS |
|
Pose Estimation (Q)
|
98% |
182
0.21 IPS |
|
Object Detection (SP)
|
100% |
50
3.95 IPS |
|
Object Detection (HP)
|
100% |
50
3.96 IPS |
|
Object Detection (Q)
|
89% |
86
6.88 IPS |
|
Face Detection (SP)
|
100% |
129
1.54 IPS |
|
Face Detection (HP)
|
100% |
131
1.56 IPS |
|
Face Detection (Q)
|
97% |
199
2.37 IPS |
|
Depth Estimation (SP)
|
100% |
115
0.88 IPS |
|
Depth Estimation (HP)
|
100% |
115
0.89 IPS |
|
Depth Estimation (Q)
|
73% |
187
1.53 IPS |
|
Style Transfer (SP)
|
100% |
216
0.28 IPS |
|
Style Transfer (HP)
|
100% |
216
0.28 IPS |
|
Style Transfer (Q)
|
98% |
407
0.53 IPS |
|
Image Super-Resolution (SP)
|
100% |
57
2.11 IPS |
|
Image Super-Resolution (HP)
|
100% |
57
2.11 IPS |
|
Image Super-Resolution (Q)
|
97% |
106
3.92 IPS |
|
Text Classification (SP)
|
100% |
72
96.1 IPS |
|
Text Classification (HP)
|
100% |
72
95.9 IPS |
|
Text Classification (Q)
|
91% |
93
125.1 IPS |
|
Machine Translation (SP)
|
100% |
125
2.16 IPS |
|
Machine Translation (HP)
|
100% |
126
2.17 IPS |
|
Machine Translation (Q)
|
57% |
89
2.19 IPS |