Firefly ITX-3588J
Geekbench ML Score
693
TensorFlow Lite GPU Inference Score
Geekbench ML 0.5.0 for Android AArch64
Result Information
| Upload Date | May 14 2022 10:11 AM |
| Views | 2 |
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 | GPU |
| Device | |
Inference Performance
| Workload | Accuracy | Score | |
|---|---|---|---|
|
Image Classification (F32)
|
100% |
433
46.4 IPS |
|
|
Image Classification (F16)
|
100% |
719
77.0 IPS |
|
|
Image Classification (I8)
|
81% |
699
74.9 IPS |
|
|
Image Segmentation (F32)
|
100% |
1026
6.34 IPS |
|
|
Image Segmentation (F16)
|
100% |
1693
10.5 IPS |
|
|
Image Segmentation (I8)
|
89% |
1527
9.43 IPS |
|
|
Pose Estimation (F32)
|
100% |
364
1.47 IPS |
|
|
Pose Estimation (F16)
|
100% |
906
3.67 IPS |
|
|
Pose Estimation (I8)
|
80% |
909
3.68 IPS |
|
|
Object Detection (F32)
|
100% |
346
12.2 IPS |
|
|
Object Detection (F16)
|
99% |
497
17.5 IPS |
|
|
Object Detection (I8)
|
54% |
489
17.2 IPS |
|
|
Face Detection (F32)
|
100% |
1091
12.5 IPS |
|
|
Face Detection (F16)
|
97% |
1822
20.9 IPS |
|
|
Face Detection (I8)
|
75% |
1543
17.7 IPS |
|
|
Text Classification (F32)
|
100% |
638
252.5 IPS |
|
|
Text Classification (F16)
|
98% |
923
365.1 IPS |
|
|
Machine Translation (F32)
|
100% |
187
28.8 IPS |
|
|
Machine Translation (F16)
|
100% |
192
29.5 IPS |
