Upload Date | May 15 2022 09:21 PM |
Views | 10 |
System Information | |
---|---|
Operating System | Android 10 |
Model | samsung SM-G965F |
Model ID | samsung SM-G965F |
Motherboard | universal8890 |
Governor | bioshock |
CPU Information | |
---|---|
Name | ARMv8 |
Topology | 1 Processor, 8 Cores |
Identifier | ARM implementer 83 architecture 8 variant 1 part 1 revision 1 |
Base Frequency | 1.59 GHz |
Cluster 1 | 4 Cores @ 1.59 GHz |
Cluster 2 | 4 Cores @ 2.60 GHz |
Memory Information | |
---|---|
Size | 3.70 GB |
Inference Information | |
---|---|
Framework | TensorFlow Lite |
Backend | CPU |
Device |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (F32)
|
100% |
161
17.2 IPS |
|
Image Classification (F16)
|
100% |
157
16.9 IPS |
|
Image Classification (I8)
|
81% |
134
14.3 IPS |
|
Image Segmentation (F32)
|
100% |
254
1.57 IPS |
|
Image Segmentation (F16)
|
100% |
254
1.57 IPS |
|
Image Segmentation (I8)
|
89% |
520
3.21 IPS |
|
Pose Estimation (F32)
|
100% |
100
0.40 IPS |
|
Pose Estimation (F16)
|
100% |
96
0.39 IPS |
|
Pose Estimation (I8)
|
80% |
144
0.58 IPS |
|
Object Detection (F32)
|
100% |
172
6.03 IPS |
|
Object Detection (F16)
|
100% |
169
5.93 IPS |
|
Object Detection (I8)
|
52% |
182
6.40 IPS |
|
Face Detection (F32)
|
100% |
266
3.05 IPS |
|
Face Detection (F16)
|
100% |
264
3.03 IPS |
|
Face Detection (I8)
|
75% |
332
3.81 IPS |
|
Text Classification (F32)
|
100% |
178
70.2 IPS |
|
Text Classification (F16)
|
100% |
177
69.9 IPS |
|
Machine Translation (F32)
|
100% |
97
14.9 IPS |
|
Machine Translation (F16)
|
100% |
100
15.4 IPS |