Google brya
Geekbench ML Score
462
TensorFlow Lite CPU Inference Score
Geekbench ML 0.6.0 for Android AArch64
Result Information
| Upload Date | January 21 2024 09:16 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% |
370
69.3 IPS |
|
|
Image Classification (F16)
|
100% |
386
72.3 IPS |
|
|
Image Classification (I8)
|
97% |
141
26.4 IPS |
|
|
Image Segmentation (F32)
|
100% |
506
8.45 IPS |
|
|
Image Segmentation (F16)
|
100% |
539
9.00 IPS |
|
|
Image Segmentation (I8)
|
98% |
199
3.32 IPS |
|
|
Pose Estimation (F32)
|
100% |
588
0.71 IPS |
|
|
Pose Estimation (F16)
|
100% |
624
0.76 IPS |
|
|
Pose Estimation (I8)
|
100% |
589
0.71 IPS |
|
|
Object Detection (F32)
|
100% |
405
30.2 IPS |
|
|
Object Detection (F16)
|
100% |
402
30.0 IPS |
|
|
Object Detection (I8)
|
61% |
235
17.5 IPS |
|
|
Face Detection (F32)
|
100% |
850
10.1 IPS |
|
|
Face Detection (F16)
|
100% |
978
11.6 IPS |
|
|
Face Detection (I8)
|
86% |
319
3.79 IPS |
|
|
Depth Estimation (F32)
|
100% |
846
6.56 IPS |
|
|
Depth Estimation (F16)
|
100% |
854
6.62 IPS |
|
|
Depth Estimation (I8)
|
95% |
503
3.90 IPS |
|
|
Style Transfer (F32)
|
100% |
1200
1.58 IPS |
|
|
Style Transfer (F16)
|
100% |
1183
1.56 IPS |
|
|
Style Transfer (I8)
|
98% |
1169
1.54 IPS |
|
|
Image Super-Resolution (F32)
|
100% |
474
16.9 IPS |
|
|
Image Super-Resolution (F16)
|
100% |
499
17.8 IPS |
|
|
Image Super-Resolution (I8)
|
98% |
264
9.43 IPS |
|
|
Text Classification (F32)
|
100% |
409
588.5 IPS |
|
|
Text Classification (F16)
|
100% |
407
584.3 IPS |
|
|
Text Classification (I8)
|
92% |
80
114.6 IPS |
|
|
Machine Translation (F32)
|
100% |
631
11.6 IPS |
|
|
Machine Translation (F16)
|
100% |
661
12.2 IPS |
|
|
Machine Translation (I8)
|
64% |
181
3.32 IPS |
