Google dedede
Geekbench ML Score
88
TensorFlow Lite CPU Inference Score
Geekbench ML 0.5.0 for Android AArch64
Result Information
| Upload Date | February 22 2023 09:34 AM |
| Views | 1 |
System Information
| System Information | |
|---|---|
| Operating System | Android 11 |
| Model | Google dedede |
| Model ID | Google dedede |
| Motherboard | cret |
| CPU Information | |
|---|---|
| Name | placeholder |
| Topology | 1 Processor, 2 Cores |
| Identifier | ARM implementer 78 architecture 8 variant 2 part 0 revision 1 |
| Base Frequency | 0 MHz |
| Cluster 1 | 2 Cores @ 0.00 Hz |
| Memory Information | |
|---|---|
| Size | 2.69 GB |
| Inference Information | |
|---|---|
| Framework | TensorFlow Lite |
| Backend | CPU |
Inference Performance
| Workload | Accuracy | Score | |
|---|---|---|---|
|
Image Classification (F32)
|
100% |
95
10.2 IPS |
|
|
Image Classification (F16)
|
100% |
94
10.1 IPS |
|
|
Image Classification (I8)
|
81% |
63
6.75 IPS |
|
|
Image Segmentation (F32)
|
100% |
130
0.81 IPS |
|
|
Image Segmentation (F16)
|
100% |
126
0.78 IPS |
|
|
Image Segmentation (I8)
|
89% |
112
0.69 IPS |
|
|
Pose Estimation (F32)
|
100% |
30
0.12 IPS |
|
|
Pose Estimation (F16)
|
100% |
29
0.12 IPS |
|
|
Pose Estimation (I8)
|
80% |
21
0.08 IPS |
|
|
Object Detection (F32)
|
100% |
101
3.55 IPS |
|
|
Object Detection (F16)
|
100% |
105
3.68 IPS |
|
|
Object Detection (I8)
|
52% |
76
2.66 IPS |
|
|
Face Detection (F32)
|
100% |
122
1.40 IPS |
|
|
Face Detection (F16)
|
100% |
110
1.26 IPS |
|
|
Face Detection (I8)
|
75% |
58
0.66 IPS |
|
|
Text Classification (F32)
|
100% |
113
44.8 IPS |
|
|
Text Classification (F16)
|
100% |
127
50.0 IPS |
|
|
Machine Translation (F32)
|
100% |
241
37.1 IPS |
|
|
Machine Translation (F16)
|
100% |
240
37.0 IPS |
