Google brya
Geekbench ML Score
454
TensorFlow Lite CPU Inference Score
Geekbench ML 0.6.0 for Android AArch64
Result Information
| Upload Date | April 26 2024 05:50 PM |
| Views | 1 |
System Information
| System Information | |
|---|---|
| Operating System | Android 13 |
| Model | Google brya |
| Model ID | Google brya |
| Motherboard | kano |
| 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% |
91
17.1 IPS |
|
|
Image Classification (F16)
|
100% |
201
37.7 IPS |
|
|
Image Classification (I8)
|
97% |
122
22.8 IPS |
|
|
Image Segmentation (F32)
|
100% |
508
8.49 IPS |
|
|
Image Segmentation (F16)
|
100% |
557
9.30 IPS |
|
|
Image Segmentation (I8)
|
98% |
213
3.56 IPS |
|
|
Pose Estimation (F32)
|
100% |
613
0.74 IPS |
|
|
Pose Estimation (F16)
|
100% |
719
0.87 IPS |
|
|
Pose Estimation (I8)
|
100% |
605
0.73 IPS |
|
|
Object Detection (F32)
|
100% |
392
29.3 IPS |
|
|
Object Detection (F16)
|
100% |
455
34.0 IPS |
|
|
Object Detection (I8)
|
61% |
238
17.8 IPS |
|
|
Face Detection (F32)
|
100% |
998
11.9 IPS |
|
|
Face Detection (F16)
|
100% |
1003
11.9 IPS |
|
|
Face Detection (I8)
|
86% |
325
3.86 IPS |
|
|
Depth Estimation (F32)
|
100% |
976
7.57 IPS |
|
|
Depth Estimation (F16)
|
100% |
962
7.46 IPS |
|
|
Depth Estimation (I8)
|
95% |
525
4.07 IPS |
|
|
Style Transfer (F32)
|
100% |
1143
1.50 IPS |
|
|
Style Transfer (F16)
|
100% |
1394
1.83 IPS |
|
|
Style Transfer (I8)
|
98% |
1410
1.85 IPS |
|
|
Image Super-Resolution (F32)
|
100% |
531
18.9 IPS |
|
|
Image Super-Resolution (F16)
|
100% |
538
19.2 IPS |
|
|
Image Super-Resolution (I8)
|
98% |
281
10.0 IPS |
|
|
Text Classification (F32)
|
100% |
459
659.6 IPS |
|
|
Text Classification (F16)
|
100% |
415
596.8 IPS |
|
|
Text Classification (I8)
|
92% |
92
132.4 IPS |
|
|
Machine Translation (F32)
|
100% |
581
10.7 IPS |
|
|
Machine Translation (F16)
|
100% |
621
11.4 IPS |
|
|
Machine Translation (I8)
|
64% |
190
3.50 IPS |
