Google brya
Geekbench ML Score
457
TensorFlow Lite CPU Inference Score
Geekbench ML 0.6.0 for Android AArch64
Result Information
| Upload Date | January 23 2024 11:32 PM |
| 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% |
383
71.8 IPS |
|
|
Image Classification (F16)
|
100% |
388
72.7 IPS |
|
|
Image Classification (I8)
|
97% |
168
31.4 IPS |
|
|
Image Segmentation (F32)
|
100% |
466
7.78 IPS |
|
|
Image Segmentation (F16)
|
100% |
475
7.93 IPS |
|
|
Image Segmentation (I8)
|
98% |
188
3.14 IPS |
|
|
Pose Estimation (F32)
|
100% |
576
0.70 IPS |
|
|
Pose Estimation (F16)
|
100% |
587
0.71 IPS |
|
|
Pose Estimation (I8)
|
100% |
551
0.67 IPS |
|
|
Object Detection (F32)
|
100% |
395
29.5 IPS |
|
|
Object Detection (F16)
|
100% |
391
29.2 IPS |
|
|
Object Detection (I8)
|
61% |
229
17.1 IPS |
|
|
Face Detection (F32)
|
100% |
954
11.3 IPS |
|
|
Face Detection (F16)
|
100% |
900
10.7 IPS |
|
|
Face Detection (I8)
|
86% |
315
3.75 IPS |
|
|
Depth Estimation (F32)
|
100% |
767
5.95 IPS |
|
|
Depth Estimation (F16)
|
100% |
838
6.50 IPS |
|
|
Depth Estimation (I8)
|
95% |
512
3.97 IPS |
|
|
Style Transfer (F32)
|
100% |
1190
1.57 IPS |
|
|
Style Transfer (F16)
|
100% |
1188
1.56 IPS |
|
|
Style Transfer (I8)
|
98% |
1168
1.54 IPS |
|
|
Image Super-Resolution (F32)
|
100% |
481
17.2 IPS |
|
|
Image Super-Resolution (F16)
|
100% |
500
17.9 IPS |
|
|
Image Super-Resolution (I8)
|
98% |
264
9.44 IPS |
|
|
Text Classification (F32)
|
100% |
384
552.0 IPS |
|
|
Text Classification (F16)
|
100% |
415
596.8 IPS |
|
|
Text Classification (I8)
|
92% |
90
129.9 IPS |
|
|
Machine Translation (F32)
|
100% |
613
11.3 IPS |
|
|
Machine Translation (F16)
|
100% |
646
11.9 IPS |
|
|
Machine Translation (I8)
|
64% |
177
3.25 IPS |
