Upload Date | September 15 2021 10:07 AM |
Views | 2 |
System Information | |
---|---|
Operating System | Android 10 |
Model | LG G8 ThinQ |
Model ID | LGE LM-G820N |
Motherboard | msmnile |
Governor | schedutil |
CPU Information | |
---|---|
Name | Qualcomm Qualcomm |
Topology | 1 Processor, 8 Cores |
Identifier | ARM implementer 81 architecture 8 variant 13 part 2052 revision 14 |
Base Frequency | 1.78 GHz |
Cluster 1 | 4 Cores @ 1.79 GHz |
Cluster 2 | 3 Cores @ 2.42 GHz |
Cluster 3 | 1 Core @ 2.84 GHz |
Memory Information | |
---|---|
Size | 5.35 GB |
Inference Information | |
---|---|
Framework | TensorFlow Lite |
Backend | CPU |
Device |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (F32)
|
100% |
293
31.4 IPS |
|
Image Classification (F16)
|
100% |
289
31.0 IPS |
|
Image Classification (I8)
|
81% |
175
18.8 IPS |
|
Image Segmentation (F32)
|
100% |
485
2.99 IPS |
|
Image Segmentation (F16)
|
100% |
485
3.00 IPS |
|
Image Segmentation (I8)
|
89% |
693
4.28 IPS |
|
Pose Estimation (F32)
|
100% |
222
0.90 IPS |
|
Pose Estimation (F16)
|
100% |
215
0.87 IPS |
|
Pose Estimation (I8)
|
80% |
188
0.76 IPS |
|
Object Detection (F32)
|
100% |
347
12.2 IPS |
|
Object Detection (F16)
|
100% |
345
12.1 IPS |
|
Object Detection (I8)
|
52% |
265
9.31 IPS |
|
Face Detection (F32)
|
100% |
553
6.36 IPS |
|
Face Detection (F16)
|
100% |
545
6.27 IPS |
|
Face Detection (I8)
|
75% |
441
5.07 IPS |
|
Text Classification (F32)
|
100% |
300
118.5 IPS |
|
Text Classification (F16)
|
100% |
289
114.4 IPS |
|
Machine Translation (F32)
|
100% |
384
59.1 IPS |
|
Machine Translation (F16)
|
100% |
379
58.3 IPS |