samsung SM-F936B
Geekbench ML Score
3274
TensorFlow Lite NNAPI Inference Score
Geekbench ML 0.5.0 for Android AArch64
Result Information
| Upload Date | October 07 2022 01:05 PM |
| Views | 15 |
System Information
| System Information | |
|---|---|
| Operating System | Android 12 |
| Model | samsung SM-F936B |
| Model ID | samsung SM-F936B |
| Motherboard | taro |
| Governor | walt |
| CPU Information | |
|---|---|
| Name | ARM ARMv8 |
| Topology | 1 Processor, 8 Cores |
| Identifier | ARM implementer 65 architecture 8 variant 2 part 3400 revision 0 |
| Base Frequency | 2.02 GHz |
| Cluster 1 | 4 Cores @ 2.02 GHz |
| Cluster 2 | 3 Cores @ 2.75 GHz |
| Cluster 3 | 1 Core @ 3.19 GHz |
| Memory Information | |
|---|---|
| Size | 10.99 GB |
| Inference Information | |
|---|---|
| Framework | TensorFlow Lite |
| Backend | NNAPI |
| Device | |
Inference Performance
| Workload | Accuracy | Score | |
|---|---|---|---|
|
Image Classification (F32)
|
100% |
1386
148.5 IPS |
|
|
Image Classification (F16)
|
100% |
9535
1.02 KIPS |
|
|
Image Classification (I8)
|
80% |
23258
2.49 KIPS |
|
|
Image Segmentation (F32)
|
100% |
3016
18.6 IPS |
|
|
Image Segmentation (F16)
|
100% |
8271
51.1 IPS |
|
|
Image Segmentation (I8)
|
89% |
43920
271.3 IPS |
|
|
Pose Estimation (F32)
|
100% |
643
2.60 IPS |
|
|
Pose Estimation (F16)
|
100% |
10894
44.1 IPS |
|
|
Pose Estimation (I8)
|
80% |
55333
223.9 IPS |
|
|
Object Detection (F32)
|
100% |
1096
38.4 IPS |
|
|
Object Detection (F16)
|
100% |
1880
66.0 IPS |
|
|
Object Detection (I8)
|
53% |
2118
74.3 IPS |
|
|
Face Detection (F32)
|
100% |
2159
24.8 IPS |
|
|
Face Detection (F16)
|
97% |
7102
81.6 IPS |
|
|
Face Detection (I8)
|
76% |
50138
576.0 IPS |
|
|
Text Classification (F32)
|
100% |
17
6.73 IPS |
|
|
Text Classification (F16)
|
100% |
712
281.5 IPS |
|
|
Machine Translation (F32)
|
100% |
1074
165.5 IPS |
|
|
Machine Translation (F16)
|
100% |
1075
165.7 IPS |
