Realme 3
Geekbench ML Score
133
TensorFlow Lite CPU Inference Score
Geekbench ML 0.5.0 for Android AArch64
Result Information
| Upload Date | May 16 2023 10:01 AM |
| Views | 1 |
System Information
| System Information | |
|---|---|
| Operating System | Android 10 |
| Model | Realme 3 |
| Model ID | Realme RMX1821 |
| Motherboard | RM6771_18601 |
| CPU Information | |
|---|---|
| Name | ARM MT6771V/W |
| Topology | 1 Processor, 8 Cores |
| Identifier | ARM implementer 65 architecture 8 variant 0 part 3337 revision 2 |
| Base Frequency | 1.99 GHz |
| Cluster 1 | 8 Cores @ 1.99 GHz |
| Memory Information | |
|---|---|
| Size | 2.67 GB |
| Inference Information | |
|---|---|
| Framework | TensorFlow Lite |
| Backend | CPU |
Inference Performance
| Workload | Accuracy | Score | |
|---|---|---|---|
|
Image Classification (F32)
|
100% |
67
7.13 IPS |
|
|
Image Classification (F16)
|
100% |
66
7.05 IPS |
|
|
Image Classification (I8)
|
81% |
312
33.4 IPS |
|
|
Image Segmentation (F32)
|
100% |
164
1.01 IPS |
|
|
Image Segmentation (F16)
|
100% |
179
1.10 IPS |
|
|
Image Segmentation (I8)
|
89% |
534
3.30 IPS |
|
|
Pose Estimation (F32)
|
100% |
73
0.29 IPS |
|
|
Pose Estimation (F16)
|
100% |
78
0.31 IPS |
|
|
Pose Estimation (I8)
|
80% |
132
0.53 IPS |
|
|
Object Detection (F32)
|
100% |
106
3.71 IPS |
|
|
Object Detection (F16)
|
100% |
106
3.71 IPS |
|
|
Object Detection (I8)
|
52% |
281
9.86 IPS |
|
|
Face Detection (F32)
|
100% |
136
1.56 IPS |
|
|
Face Detection (F16)
|
100% |
135
1.55 IPS |
|
|
Face Detection (I8)
|
75% |
385
4.42 IPS |
|
|
Text Classification (F32)
|
100% |
110
43.5 IPS |
|
|
Text Classification (F16)
|
100% |
109
43.2 IPS |
|
|
Machine Translation (F32)
|
100% |
75
11.5 IPS |
|
|
Machine Translation (F16)
|
100% |
73
11.3 IPS |
