Upload Date | June 13 2021 04:37 AM |
Views | 1 |
System Information | |
---|---|
Operating System | Android 10 |
Model | OPPO CPH1933 |
Model ID | OPPO CPH1933 |
Motherboard | trinket |
Governor | schedutil |
CPU Information | |
---|---|
Name | Qualcomm Qualcomm |
Topology | 1 Processor, 8 Cores |
Identifier | ARM implementer 81 architecture 8 variant 10 part 2048 revision 2 |
Base Frequency | 1.80 GHz |
Cluster 1 | 4 Cores @ 1.80 GHz |
Cluster 2 | 4 Cores @ 2.02 GHz |
Memory Information | |
---|---|
Size | 3.56 GB |
Inference Information | |
---|---|
Framework | TensorFlow Lite |
Backend | CPU |
Device |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (F32)
|
100% |
86
9.25 IPS |
|
Image Classification (F16)
|
100% |
85
9.16 IPS |
|
Image Classification (I8)
|
81% |
247
26.5 IPS |
|
Image Segmentation (F32)
|
100% |
161
0.99 IPS |
|
Image Segmentation (F16)
|
100% |
165
1.02 IPS |
|
Image Segmentation (I8)
|
89% |
422
2.61 IPS |
|
Pose Estimation (F32)
|
100% |
79
0.32 IPS |
|
Pose Estimation (F16)
|
100% |
76
0.31 IPS |
|
Pose Estimation (I8)
|
80% |
129
0.52 IPS |
|
Object Detection (F32)
|
100% |
104
3.65 IPS |
|
Object Detection (F16)
|
100% |
99
3.48 IPS |
|
Object Detection (I8)
|
52% |
187
6.56 IPS |
|
Face Detection (F32)
|
100% |
142
1.63 IPS |
|
Face Detection (F16)
|
100% |
136
1.57 IPS |
|
Face Detection (I8)
|
75% |
386
4.43 IPS |
|
Text Classification (F32)
|
100% |
86
34.2 IPS |
|
Text Classification (F16)
|
100% |
85
33.7 IPS |
|
Machine Translation (F32)
|
100% |
82
12.6 IPS |
|
Machine Translation (F16)
|
100% |
82
12.7 IPS |