JOYAR 100011885
Geekbench ML Score
148
TensorFlow Lite GPU Inference Score
Geekbench ML 0.5.0 for Android AArch64
Result Information
| Upload Date | August 08 2023 09:33 AM |
| Views | 1 |
System Information
| System Information | |
|---|---|
| Operating System | Android 11 |
| Model | JOYAR 100011885 |
| Model ID | JOYAR 100011885 |
| Motherboard | tb8168p1_64_bsp |
| Governor | schedutil |
| CPU Information | |
|---|---|
| Name | ARM MT8168B |
| Topology | 1 Processor, 4 Cores |
| Identifier | ARM implementer 65 architecture 8 variant 0 part 3331 revision 4 |
| Base Frequency | 2.00 GHz |
| Cluster 1 | 4 Cores @ 2.00 GHz |
| Memory Information | |
|---|---|
| Size | 1.88 GB |
| Inference Information | |
|---|---|
| Framework | TensorFlow Lite |
| Backend | GPU |
| Device | |
Inference Performance
| Workload | Accuracy | Score | |
|---|---|---|---|
|
Image Classification (F32)
|
100% |
99
10.6 IPS |
|
|
Image Classification (F16)
|
100% |
217
23.2 IPS |
|
|
Image Classification (I8)
|
81% |
205
22.0 IPS |
|
|
Image Segmentation (F32)
|
100% |
176
1.09 IPS |
|
|
Image Segmentation (F16)
|
100% |
497
3.07 IPS |
|
|
Image Segmentation (I8)
|
89% |
512
3.16 IPS |
|
|
Pose Estimation (F32)
|
100% |
53
0.21 IPS |
|
|
Pose Estimation (F16)
|
0% |
199
0.80 IPS |
|
|
Pose Estimation (I8)
|
0% |
198
0.80 IPS |
|
|
Object Detection (F32)
|
100% |
84
2.94 IPS |
|
|
Object Detection (F16)
|
99% |
133
4.67 IPS |
|
|
Object Detection (I8)
|
54% |
138
4.86 IPS |
|
|
Face Detection (F32)
|
100% |
184
2.12 IPS |
|
|
Face Detection (F16)
|
97% |
399
4.58 IPS |
|
|
Face Detection (I8)
|
75% |
369
4.24 IPS |
|
|
Text Classification (F32)
|
100% |
133
52.6 IPS |
|
|
Text Classification (F16)
|
46% |
237
93.6 IPS |
|
|
Machine Translation (F32)
|
100% |
18
2.78 IPS |
|
|
Machine Translation (F16)
|
100% |
18
2.79 IPS |
