nubia NX659J
Geekbench ML Score
1314
TensorFlow Lite GPU Inference Score
Geekbench ML 0.5.0 for Android AArch64
Result Information
| Upload Date | May 14 2022 08:57 PM |
| Views | 1 |
System Information
| System Information | |
|---|---|
| Operating System | Android 11 |
| Model | nubia NX659J |
| Model ID | nubia NX659J |
| Motherboard | kona |
| Governor | schedutil |
| CPU Information | |
|---|---|
| Name | ARM Qualcomm |
| Topology | 1 Processor, 8 Cores |
| Identifier | ARM implementer 65 architecture 8 variant 1 part 3341 revision 0 |
| Base Frequency | 1.80 GHz |
| Cluster 1 | 4 Cores @ 1.80 GHz |
| Cluster 2 | 3 Cores @ 2.42 GHz |
| Cluster 3 | 1 Core @ 2.84 GHz |
| Memory Information | |
|---|---|
| Size | 11.38 GB |
| Inference Information | |
|---|---|
| Framework | TensorFlow Lite |
| Backend | GPU |
| Device | |
Inference Performance
| Workload | Accuracy | Score | |
|---|---|---|---|
|
Image Classification (F32)
|
100% |
954
102.2 IPS |
|
|
Image Classification (F16)
|
100% |
1551
166.2 IPS |
|
|
Image Classification (I8)
|
80% |
1426
152.8 IPS |
|
|
Image Segmentation (F32)
|
100% |
2527
15.6 IPS |
|
|
Image Segmentation (F16)
|
100% |
4206
26.0 IPS |
|
|
Image Segmentation (I8)
|
89% |
3961
24.5 IPS |
|
|
Pose Estimation (F32)
|
100% |
1302
5.27 IPS |
|
|
Pose Estimation (F16)
|
100% |
2227
9.01 IPS |
|
|
Pose Estimation (I8)
|
80% |
2218
8.97 IPS |
|
|
Object Detection (F32)
|
100% |
681
23.9 IPS |
|
|
Object Detection (F16)
|
99% |
657
23.1 IPS |
|
|
Object Detection (I8)
|
53% |
613
21.5 IPS |
|
|
Face Detection (F32)
|
100% |
1787
20.5 IPS |
|
|
Face Detection (F16)
|
97% |
3049
35.0 IPS |
|
|
Face Detection (I8)
|
76% |
2733
31.4 IPS |
|
|
Text Classification (F32)
|
100% |
485
191.8 IPS |
|
|
Text Classification (F16)
|
98% |
527
208.3 IPS |
|
|
Machine Translation (F32)
|
100% |
551
84.9 IPS |
|
|
Machine Translation (F16)
|
100% |
552
85.1 IPS |
