Firefly ITX-3588J
Geekbench ML Score
173
TensorFlow Lite NNAPI Inference Score
Geekbench ML 0.5.0 for Android AArch64
Result Information
| Upload Date | May 16 2022 12:21 PM |
| Views | 1 |
System Information
| System Information | |
|---|---|
| Operating System | Android 12 |
| Model | Firefly ITX-3588J |
| Model ID | Firefly ITX-3588J |
| Motherboard | rk30sdk |
| Governor | schedutil |
| CPU Information | |
|---|---|
| Name | ARM ARMv8 |
| Topology | 1 Processor, 8 Cores |
| Identifier | ARM implementer 65 architecture 8 variant 4 part 3339 revision 0 |
| Base Frequency | 1.80 GHz |
| Cluster 1 | 4 Cores @ 1.80 GHz |
| Cluster 2 | 4 Cores @ 2.40 GHz |
| Memory Information | |
|---|---|
| Size | 3.37 GB |
| Inference Information | |
|---|---|
| Framework | TensorFlow Lite |
| Backend | NNAPI |
| Device | |
Inference Performance
| Workload | Accuracy | Score | |
|---|---|---|---|
|
Image Classification (F32)
|
100% |
66
7.12 IPS |
|
|
Image Classification (F16)
|
100% |
68
7.27 IPS |
|
|
Image Classification (I8)
|
81% |
194
20.8 IPS |
|
|
Image Segmentation (F32)
|
100% |
247
1.52 IPS |
|
|
Image Segmentation (F16)
|
100% |
229
1.42 IPS |
|
|
Image Segmentation (I8)
|
89% |
352
2.17 IPS |
|
|
Pose Estimation (F32)
|
100% |
173
0.70 IPS |
|
|
Pose Estimation (F16)
|
100% |
171
0.69 IPS |
|
|
Pose Estimation (I8)
|
80% |
57
0.23 IPS |
|
|
Object Detection (F32)
|
100% |
84
2.96 IPS |
|
|
Object Detection (F16)
|
100% |
83
2.90 IPS |
|
|
Object Detection (I8)
|
52% |
232
8.14 IPS |
|
|
Face Detection (F32)
|
100% |
195
2.24 IPS |
|
|
Face Detection (F16)
|
100% |
207
2.38 IPS |
|
|
Face Detection (I8)
|
75% |
254
2.92 IPS |
|
|
Text Classification (F32)
|
100% |
437
172.8 IPS |
|
|
Text Classification (F16)
|
100% |
430
170.2 IPS |
|
|
Machine Translation (F32)
|
100% |
193
29.8 IPS |
|
|
Machine Translation (F16)
|
100% |
203
31.3 IPS |
