Xiaomi Redmi 7A
Geekbench ML Score
17
TensorFlow Lite GPU Inference Score
Geekbench ML 0.6.0 for Android AArch64
Result Information
| Upload Date | May 08 2024 11:43 AM |
| Views | 1 |
System Information
| System Information | |
|---|---|
| Operating System | Android 14 |
| Model | Xiaomi Redmi 7A |
| Model ID | Xiaomi Redmi 7A |
| Motherboard | msm8937 |
| Governor | schedutil |
| CPU Information | |
|---|---|
| Name | ARM Qualcomm |
| Topology | 1 Processor, 8 Cores |
| Identifier | ARM implementer 65 architecture 8 variant 0 part 3331 revision 4 |
| Base Frequency | 2.02 GHz |
| Cluster 1 | 4 Cores @ 1.46 GHz |
| Cluster 2 | 4 Cores @ 2.02 GHz |
| Memory Information | |
|---|---|
| Size | 1.78 GB |
| Inference Information | |
|---|---|
| Framework | TensorFlow Lite |
| Backend | GPU |
| Device | Default |
Inference Performance
| Workload | Accuracy | Score | |
|---|---|---|---|
|
Image Classification (F32)
|
100% |
19
3.64 IPS |
|
|
Image Classification (F16)
|
100% |
26
4.91 IPS |
|
|
Image Classification (I8)
|
97% |
26
4.95 IPS |
|
|
Image Segmentation (F32)
|
100% |
23
0.38 IPS |
|
|
Image Segmentation (F16)
|
100% |
30
0.51 IPS |
|
|
Image Segmentation (I8)
|
98% |
30
0.50 IPS |
|
|
Pose Estimation (F32)
|
0
|
||
|
Pose Estimation (F16)
|
0
|
||
|
Pose Estimation (I8)
|
0
|
||
|
Object Detection (F32)
|
100% |
17
1.25 IPS |
|
|
Object Detection (F16)
|
100% |
22
1.64 IPS |
|
|
Object Detection (I8)
|
62% |
23
1.69 IPS |
|
|
Face Detection (F32)
|
100% |
51
0.61 IPS |
|
|
Face Detection (F16)
|
97% |
66
0.79 IPS |
|
|
Face Detection (I8)
|
87% |
67
0.79 IPS |
|
|
Depth Estimation (F32)
|
100% |
42
0.33 IPS |
|
|
Depth Estimation (F16)
|
100% |
54
0.42 IPS |
|
|
Depth Estimation (I8)
|
95% |
53
0.41 IPS |
|
|
Style Transfer (F32)
|
0
|
||
|
Style Transfer (F16)
|
0
|
||
|
Style Transfer (I8)
|
0
|
||
|
Image Super-Resolution (F32)
|
100% |
23
0.84 IPS |
|
|
Image Super-Resolution (F16)
|
100% |
31
1.09 IPS |
|
|
Image Super-Resolution (I8)
|
98% |
30
1.08 IPS |
|
|
Text Classification (F32)
|
100% |
29
41.2 IPS |
|
|
Text Classification (F16)
|
100% |
29
41.2 IPS |
|
|
Text Classification (I8)
|
92% |
43
61.1 IPS |
|
|
Machine Translation (F32)
|
100% |
60
1.10 IPS |
|
|
Machine Translation (F16)
|
100% |
59
1.08 IPS |
|
|
Machine Translation (I8)
|
64% |
59
1.09 IPS |
