Punkt MC02
Geekbench ML Score
464
TensorFlow Lite CPU Inference Score
Geekbench ML 0.6.0 for Android AArch64
Result Information
| Upload Date | August 21 2024 09:45 AM |
| Views | 1 |
System Information
| System Information | |
|---|---|
| Operating System | Android 13 |
| Model | Punkt MC02 |
| Model ID | Punkt MC02 |
| Motherboard | k6877v1_64_k419 |
| CPU Information | |
|---|---|
| Name | ARM MT6877V/ZA |
| Topology | 1 Processor, 8 Cores |
| Identifier | ARM implementer 65 architecture 8 variant 1 part 3393 revision 0 |
| Base Frequency | 2.00 GHz |
| Cluster 1 | 6 Cores @ 2.00 GHz |
| Cluster 2 | 2 Cores @ 2.40 GHz |
| Memory Information | |
|---|---|
| Size | 5.54 GB |
| Inference Information | |
|---|---|
| Framework | TensorFlow Lite |
| Backend | CPU |
| Device | Default |
Inference Performance
| Workload | Accuracy | Score | |
|---|---|---|---|
|
Image Classification (F32)
|
100% |
225
42.2 IPS |
|
|
Image Classification (F16)
|
100% |
230
43.1 IPS |
|
|
Image Classification (I8)
|
97% |
399
74.6 IPS |
|
|
Image Segmentation (F32)
|
100% |
316
5.27 IPS |
|
|
Image Segmentation (F16)
|
100% |
315
5.27 IPS |
|
|
Image Segmentation (I8)
|
98% |
542
9.06 IPS |
|
|
Pose Estimation (F32)
|
100% |
457
0.55 IPS |
|
|
Pose Estimation (F16)
|
100% |
451
0.55 IPS |
|
|
Pose Estimation (I8)
|
100% |
1955
2.37 IPS |
|
|
Object Detection (F32)
|
100% |
226
16.9 IPS |
|
|
Object Detection (F16)
|
100% |
226
16.9 IPS |
|
|
Object Detection (I8)
|
61% |
451
33.6 IPS |
|
|
Face Detection (F32)
|
100% |
490
5.82 IPS |
|
|
Face Detection (F16)
|
100% |
490
5.83 IPS |
|
|
Face Detection (I8)
|
86% |
1099
13.1 IPS |
|
|
Depth Estimation (F32)
|
100% |
483
3.75 IPS |
|
|
Depth Estimation (F16)
|
100% |
483
3.74 IPS |
|
|
Depth Estimation (I8)
|
95% |
1097
8.51 IPS |
|
|
Style Transfer (F32)
|
100% |
802
1.06 IPS |
|
|
Style Transfer (F16)
|
100% |
801
1.05 IPS |
|
|
Style Transfer (I8)
|
98% |
2194
2.89 IPS |
|
|
Image Super-Resolution (F32)
|
100% |
278
9.92 IPS |
|
|
Image Super-Resolution (F16)
|
100% |
279
9.98 IPS |
|
|
Image Super-Resolution (I8)
|
98% |
785
28.0 IPS |
|
|
Text Classification (F32)
|
100% |
278
399.8 IPS |
|
|
Text Classification (F16)
|
100% |
281
404.0 IPS |
|
|
Text Classification (I8)
|
92% |
241
346.6 IPS |
|
|
Machine Translation (F32)
|
100% |
533
9.80 IPS |
|
|
Machine Translation (F16)
|
100% |
517
9.52 IPS |
|
|
Machine Translation (I8)
|
64% |
329
6.06 IPS |
