Upload Date | May 04 2022 10:04 AM |
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 | 7.12 GB |
Inference Information | |
---|---|
Framework | TensorFlow Lite |
Backend | GPU |
Device |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (F32)
|
100% |
308
33.0 IPS |
|
Image Classification (F16)
|
100% |
774
82.9 IPS |
|
Image Classification (I8)
|
80% |
640
68.6 IPS |
|
Image Segmentation (F32)
|
100% |
1050
6.49 IPS |
|
Image Segmentation (F16)
|
100% |
2889
17.8 IPS |
|
Image Segmentation (I8)
|
89% |
2821
17.4 IPS |
|
Pose Estimation (F32)
|
100% |
433
1.75 IPS |
|
Pose Estimation (F16)
|
100% |
1082
4.38 IPS |
|
Pose Estimation (I8)
|
80% |
1057
4.28 IPS |
|
Object Detection (F32)
|
100% |
220
7.73 IPS |
|
Object Detection (F16)
|
100% |
487
17.1 IPS |
|
Object Detection (I8)
|
54% |
472
16.6 IPS |
|
Face Detection (F32)
|
100% |
1169
13.4 IPS |
|
Face Detection (F16)
|
97% |
2369
27.2 IPS |
|
Face Detection (I8)
|
76% |
2054
23.6 IPS |
|
Text Classification (F32)
|
100% |
277
109.4 IPS |
|
Text Classification (F16)
|
98% |
500
197.8 IPS |
|
Machine Translation (F32)
|
100% |
962
148.2 IPS |
|
Machine Translation (F16)
|
100% |
973
149.9 IPS |