Google octopus
Geekbench AI Score
14
Single Precision Score
14
Half Precision Score
8
Quantized Score
Geekbench AI 1.1.0 for Android AArch64
Result Information
| User | shimonocyou |
| Upload Date | October 20 2024 08:29 AM |
| Views | 10 |
System Information
| AI Information | |
|---|---|
| Framework | TensorFlow Lite |
| Backend | GPU |
| Device | placeholder |
| System Information | |
|---|---|
| Operating System | Android 13 |
| Model | Google octopus |
| Model ID | Google octopus |
| Motherboard | phaser360 |
| CPU Information | |
|---|---|
| Name | placeholder |
| Topology | 1 Processor, 4 Cores |
| Identifier | ARM implementer 78 architecture 8 variant 2 part 0 revision 1 |
| Base Frequency | 0 MHz |
| Cluster 1 | 4 Cores |
| Memory Information | |
|---|---|
| Size | 3.12 GB |
AI Performance
| Workload | Accuracy | Score | |
|---|---|---|---|
|
Image Classification (SP)
|
0% |
0
726.0 IPS |
|
|
Image Classification (HP)
|
0% |
0
841.8 IPS |
|
|
Image Classification (Q)
|
0% |
0
736.6 IPS |
|
|
Image Segmentation (SP)
|
73% |
6740
116.5 IPS |
|
|
Image Segmentation (HP)
|
73% |
6756
116.7 IPS |
|
|
Image Segmentation (Q)
|
73% |
538
9.30 IPS |
|
|
Pose Estimation (SP)
|
0% |
0
321.5 IPS |
|
|
Pose Estimation (HP)
|
0% |
0
322.8 IPS |
|
|
Pose Estimation (Q)
|
0% |
0
129.1 IPS |
|
|
Object Detection (SP)
|
0% |
0
269.9 IPS |
|
|
Object Detection (HP)
|
0% |
0
360.1 IPS |
|
|
Object Detection (Q)
|
0% |
0
284.8 IPS |
|
|
Face Detection (SP)
|
0% |
0
132.7 IPS |
|
|
Face Detection (HP)
|
0% |
0
148.0 IPS |
|
|
Face Detection (Q)
|
0% |
0
54.5 IPS |
|
|
Depth Estimation (SP)
|
0% |
0
383.0 IPS |
|
|
Depth Estimation (HP)
|
0% |
0
406.3 IPS |
|
|
Depth Estimation (Q)
|
0% |
0
407.9 IPS |
|
|
Style Transfer (SP)
|
32% |
40334
505.9 IPS |
|
|
Style Transfer (HP)
|
32% |
39420
494.4 IPS |
|
|
Style Transfer (Q)
|
32% |
9515
118.7 IPS |
|
|
Image Super-Resolution (SP)
|
1% |
0
892.4 IPS |
|
|
Image Super-Resolution (HP)
|
1% |
0
886.5 IPS |
|
|
Image Super-Resolution (Q)
|
1% |
0
209.0 IPS |
|
|
Text Classification (SP)
|
100% |
32
43.4 IPS |
|
|
Text Classification (HP)
|
100% |
33
44.7 IPS |
|
|
Text Classification (Q)
|
91% |
18
24.8 IPS |
|
|
Machine Translation (SP)
|
100% |
65
1.12 IPS |
|
|
Machine Translation (HP)
|
100% |
65
1.12 IPS |
|
|
Machine Translation (Q)
|
57% |
22
0.53 IPS |
