Upload Date | April 07 2022 09:35 PM |
Views | 2 |
System Information | |
---|---|
Operating System | Android 12 |
Model | samsung SM-S908B |
Model ID | samsung SM-S908B |
Motherboard | s5e9925 |
Governor | energy_aware |
CPU Information | |
---|---|
Name | ARM ARMv8 |
Topology | 1 Processor, 8 Cores |
Identifier | ARM implementer 65 architecture 8 variant 2 part 3400 revision 0 |
Base Frequency | 1.82 GHz |
Cluster 1 | 4 Cores @ 1.82 GHz |
Cluster 2 | 3 Cores @ 2.52 GHz |
Cluster 3 | 1 Core @ 2.80 GHz |
Memory Information | |
---|---|
Size | 10.27 GB |
Inference Information | |
---|---|
Framework | TensorFlow Lite |
Backend | GPU |
Device |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (F32)
|
100% |
324
34.7 IPS |
|
Image Classification (F16)
|
100% |
766
82.0 IPS |
|
Image Classification (I8)
|
80% |
646
69.3 IPS |
|
Image Segmentation (F32)
|
100% |
1304
8.05 IPS |
|
Image Segmentation (F16)
|
100% |
3085
19.1 IPS |
|
Image Segmentation (I8)
|
89% |
2801
17.3 IPS |
|
Pose Estimation (F32)
|
100% |
520
2.10 IPS |
|
Pose Estimation (F16)
|
100% |
1108
4.48 IPS |
|
Pose Estimation (I8)
|
80% |
1095
4.43 IPS |
|
Object Detection (F32)
|
100% |
263
9.22 IPS |
|
Object Detection (F16)
|
100% |
504
17.7 IPS |
|
Object Detection (I8)
|
54% |
459
16.1 IPS |
|
Face Detection (F32)
|
100% |
1191
13.7 IPS |
|
Face Detection (F16)
|
97% |
2312
26.6 IPS |
|
Face Detection (I8)
|
76% |
2075
23.8 IPS |
|
Text Classification (F32)
|
100% |
314
124.0 IPS |
|
Text Classification (F16)
|
98% |
518
204.9 IPS |
|
Machine Translation (F32)
|
100% |
698
107.6 IPS |
|
Machine Translation (F16)
|
100% |
700
107.8 IPS |