NVIDIA SHIELD Android TV
Geekbench ML Score
108
TensorFlow Lite NNAPI Inference Score
Geekbench ML 0.5.0 for Android AArch64
Result Information
| Upload Date | October 23 2021 10:37 PM |
| Views | 1 |
System Information
| System Information | |
|---|---|
| Operating System | Android 9 |
| Model | NVIDIA SHIELD Android TV |
| Model ID | NVIDIA SHIELD Android TV |
| Motherboard | darcy |
| Governor | schedutil |
| CPU Information | |
|---|---|
| Name | ARM ARMv8 |
| Topology | 1 Processor, 4 Cores |
| Identifier | ARM implementer 65 architecture 8 variant 1 part 3335 revision 1 |
| Base Frequency | 2.01 GHz |
| Cluster 1 | 4 Cores @ 2.01 GHz |
| Memory Information | |
|---|---|
| Size | 2.88 GB |
| Inference Information | |
|---|---|
| Framework | TensorFlow Lite |
| Backend | NNAPI |
| Device | |
Inference Performance
| Workload | Accuracy | Score | |
|---|---|---|---|
|
Image Classification (F32)
|
100% |
121
12.9 IPS |
|
|
Image Classification (F16)
|
100% |
122
13.1 IPS |
|
|
Image Classification (I8)
|
81% |
168
18.0 IPS |
|
|
Image Segmentation (F32)
|
100% |
151
0.94 IPS |
|
|
Image Segmentation (F16)
|
100% |
153
0.95 IPS |
|
|
Image Segmentation (I8)
|
89% |
221
1.37 IPS |
|
|
Pose Estimation (F32)
|
100% |
50
0.20 IPS |
|
|
Pose Estimation (F16)
|
100% |
49
0.20 IPS |
|
|
Pose Estimation (I8)
|
80% |
78
0.32 IPS |
|
|
Object Detection (F32)
|
100% |
143
5.03 IPS |
|
|
Object Detection (F16)
|
100% |
143
5.02 IPS |
|
|
Object Detection (I8)
|
52% |
243
8.53 IPS |
|
|
Face Detection (F32)
|
100% |
159
1.83 IPS |
|
|
Face Detection (F16)
|
100% |
160
1.83 IPS |
|
|
Face Detection (I8)
|
75% |
182
2.10 IPS |
|
|
Text Classification (F32)
|
100% |
39
15.6 IPS |
|
|
Text Classification (F16)
|
100% |
40
15.7 IPS |
|
|
Machine Translation (F32)
|
100% |
75
11.5 IPS |
|
|
Machine Translation (F16)
|
100% |
73
11.3 IPS |
