Google brya
Geekbench ML Score
455
TensorFlow Lite CPU Inference Score
Geekbench ML 0.6.0 for Android AArch64
Result Information
| Upload Date | January 24 2024 12:20 AM |
| Views | 1 |
System Information
| System Information | |
|---|---|
| Operating System | Android 13 |
| Model | Google brya |
| Model ID | Google brya |
| Motherboard | redrix |
| CPU Information | |
|---|---|
| Name | placeholder |
| Topology | 1 Processor, 12 Cores |
| Identifier | ARM implementer 78 architecture 8 variant 2 part 0 revision 1 |
| Base Frequency | 0 MHz |
| Cluster 1 | 12 Cores |
| Memory Information | |
|---|---|
| Size | 6.33 GB |
| Inference Information | |
|---|---|
| Framework | TensorFlow Lite |
| Backend | CPU |
| Device | Default |
Inference Performance
| Workload | Accuracy | Score | |
|---|---|---|---|
|
Image Classification (F32)
|
100% |
376
70.3 IPS |
|
|
Image Classification (F16)
|
100% |
380
71.2 IPS |
|
|
Image Classification (I8)
|
97% |
155
28.9 IPS |
|
|
Image Segmentation (F32)
|
100% |
490
8.18 IPS |
|
|
Image Segmentation (F16)
|
100% |
414
6.92 IPS |
|
|
Image Segmentation (I8)
|
98% |
192
3.20 IPS |
|
|
Pose Estimation (F32)
|
100% |
640
0.78 IPS |
|
|
Pose Estimation (F16)
|
100% |
558
0.68 IPS |
|
|
Pose Estimation (I8)
|
100% |
606
0.73 IPS |
|
|
Object Detection (F32)
|
100% |
398
29.7 IPS |
|
|
Object Detection (F16)
|
100% |
382
28.6 IPS |
|
|
Object Detection (I8)
|
61% |
219
16.3 IPS |
|
|
Face Detection (F32)
|
100% |
960
11.4 IPS |
|
|
Face Detection (F16)
|
100% |
967
11.5 IPS |
|
|
Face Detection (I8)
|
86% |
318
3.78 IPS |
|
|
Depth Estimation (F32)
|
100% |
899
6.97 IPS |
|
|
Depth Estimation (F16)
|
100% |
803
6.22 IPS |
|
|
Depth Estimation (I8)
|
95% |
513
3.98 IPS |
|
|
Style Transfer (F32)
|
100% |
1198
1.58 IPS |
|
|
Style Transfer (F16)
|
100% |
1186
1.56 IPS |
|
|
Style Transfer (I8)
|
98% |
1180
1.55 IPS |
|
|
Image Super-Resolution (F32)
|
100% |
454
16.2 IPS |
|
|
Image Super-Resolution (F16)
|
100% |
492
17.6 IPS |
|
|
Image Super-Resolution (I8)
|
98% |
267
9.55 IPS |
|
|
Text Classification (F32)
|
100% |
401
576.2 IPS |
|
|
Text Classification (F16)
|
100% |
405
582.5 IPS |
|
|
Text Classification (I8)
|
92% |
82
118.3 IPS |
|
|
Machine Translation (F32)
|
100% |
610
11.2 IPS |
|
|
Machine Translation (F16)
|
100% |
568
10.5 IPS |
|
|
Machine Translation (I8)
|
64% |
176
3.24 IPS |
