Upload Date | August 19 2024 06:58 AM |
Views | 1 |
System Information | |
---|---|
Operating System | Android 14 |
Model | Qualcomm msmnile_gvmq for arm64 |
Model ID | Qualcomm msmnile_gvmq for arm64 |
Motherboard | msmnile |
Governor | schedutil |
CPU Information | |
---|---|
Name | ARM ARMv8 |
Topology | 1 Processor, 8 Cores |
Identifier | ARM implementer 65 architecture 8 variant 0 part 3403 revision 0 |
Base Frequency | 2.59 GHz |
Cluster 1 | 4 Cores @ 2.25 GHz |
Cluster 2 | 4 Cores @ 2.59 GHz |
Memory Information | |
---|---|
Size | 24.56 GB |
Inference Information | |
---|---|
Framework | TensorFlow Lite |
Backend | GPU |
Device |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (F32)
|
13% |
2359
252.8 IPS |
|
Image Classification (F16)
|
3% |
3037
325.5 IPS |
|
Image Classification (I8)
|
1% |
2836
303.9 IPS |
|
Image Segmentation (F32)
|
100% |
5488
33.9 IPS |
|
Image Segmentation (F16)
|
100% |
9234
57.0 IPS |
|
Image Segmentation (I8)
|
89% |
9436
58.3 IPS |
|
Pose Estimation (F32)
|
40% |
2725
11.0 IPS |
|
Pose Estimation (F16)
|
27% |
5203
21.1 IPS |
|
Pose Estimation (I8)
|
80% |
5209
21.1 IPS |
|
Object Detection (F32)
|
97% |
911
32.0 IPS |
|
Object Detection (F16)
|
96% |
1074
37.7 IPS |
|
Object Detection (I8)
|
50% |
1062
37.3 IPS |
|
Face Detection (F32)
|
66% |
3392
39.0 IPS |
|
Face Detection (F16)
|
67% |
5597
64.3 IPS |
|
Face Detection (I8)
|
71% |
5154
59.2 IPS |
|
Text Classification (F32)
|
46% |
715
282.9 IPS |
|
Text Classification (F16)
|
46% |
746
295.0 IPS |
|
Machine Translation (F32)
|
100% |
698
107.5 IPS |
|
Machine Translation (F16)
|
100% |
701
108.0 IPS |