Google brya
Geekbench ML Score
452
TensorFlow Lite CPU Inference Score
Geekbench ML 0.6.0 for Android AArch64
Result Information
| Upload Date | January 24 2024 12:12 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% |
392
73.3 IPS |
|
|
Image Classification (F16)
|
100% |
380
71.2 IPS |
|
|
Image Classification (I8)
|
97% |
145
27.1 IPS |
|
|
Image Segmentation (F32)
|
100% |
448
7.48 IPS |
|
|
Image Segmentation (F16)
|
100% |
453
7.56 IPS |
|
|
Image Segmentation (I8)
|
98% |
191
3.20 IPS |
|
|
Pose Estimation (F32)
|
100% |
631
0.76 IPS |
|
|
Pose Estimation (F16)
|
100% |
616
0.75 IPS |
|
|
Pose Estimation (I8)
|
100% |
519
0.63 IPS |
|
|
Object Detection (F32)
|
100% |
378
28.3 IPS |
|
|
Object Detection (F16)
|
100% |
386
28.8 IPS |
|
|
Object Detection (I8)
|
61% |
233
17.4 IPS |
|
|
Face Detection (F32)
|
100% |
951
11.3 IPS |
|
|
Face Detection (F16)
|
100% |
943
11.2 IPS |
|
|
Face Detection (I8)
|
86% |
314
3.74 IPS |
|
|
Depth Estimation (F32)
|
100% |
882
6.84 IPS |
|
|
Depth Estimation (F16)
|
100% |
808
6.27 IPS |
|
|
Depth Estimation (I8)
|
95% |
488
3.78 IPS |
|
|
Style Transfer (F32)
|
100% |
1187
1.56 IPS |
|
|
Style Transfer (F16)
|
100% |
1184
1.56 IPS |
|
|
Style Transfer (I8)
|
98% |
1247
1.64 IPS |
|
|
Image Super-Resolution (F32)
|
100% |
396
14.1 IPS |
|
|
Image Super-Resolution (F16)
|
100% |
450
16.1 IPS |
|
|
Image Super-Resolution (I8)
|
98% |
270
9.64 IPS |
|
|
Text Classification (F32)
|
100% |
406
583.5 IPS |
|
|
Text Classification (F16)
|
100% |
416
597.2 IPS |
|
|
Text Classification (I8)
|
92% |
82
117.8 IPS |
|
|
Machine Translation (F32)
|
100% |
626
11.5 IPS |
|
|
Machine Translation (F16)
|
100% |
648
11.9 IPS |
|
|
Machine Translation (I8)
|
64% |
176
3.24 IPS |
