User | y0n9le |
Upload Date | April 20 2025 11:01 PM |
Views | 4 |
AI Information | |
---|---|
Framework | TensorFlow Lite |
Backend | GPU |
Device | Qualcomm Snapdragon 835 |
System Information | |
---|---|
Operating System | Android 15 |
Model | Xiaomi MI 6 |
Model ID | Xiaomi MI 6 |
Motherboard | msm8998 |
Governor | interactive |
CPU Information | |
---|---|
Name | Qualcomm Qualcomm |
Topology | 1 Processor, 8 Cores |
Identifier | ARM implementer 81 architecture 8 variant 10 part 2048 revision 1 |
Base Frequency | 1.90 GHz |
Cluster 1 | 4 Cores @ 1.90 GHz |
Cluster 2 | 4 Cores @ 2.46 GHz |
Memory Information | |
---|---|
Size | 5.59 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
137
25.4 IPS |
|
Image Classification (HP)
|
100% |
257
47.7 IPS |
|
Image Classification (Q)
|
97% |
255
47.5 IPS |
|
Image Segmentation (SP)
|
100% |
188
3.05 IPS |
|
Image Segmentation (HP)
|
100% |
263
4.27 IPS |
|
Image Segmentation (Q)
|
98% |
261
4.24 IPS |
|
Pose Estimation (SP)
|
100% |
164
0.19 IPS |
|
Pose Estimation (HP)
|
100% |
428
0.50 IPS |
|
Pose Estimation (Q)
|
95% |
414
0.48 IPS |
|
Object Detection (SP)
|
100% |
104
8.23 IPS |
|
Object Detection (HP)
|
100% |
175
13.9 IPS |
|
Object Detection (Q)
|
89% |
179
14.3 IPS |
|
Face Detection (SP)
|
100% |
320
3.80 IPS |
|
Face Detection (HP)
|
100% |
506
6.01 IPS |
|
Face Detection (Q)
|
97% |
648
7.73 IPS |
|
Depth Estimation (SP)
|
100% |
255
1.96 IPS |
|
Depth Estimation (HP)
|
99% |
558
4.31 IPS |
|
Depth Estimation (Q)
|
62% |
455
4.31 IPS |
|
Style Transfer (SP)
|
100% |
503
0.65 IPS |
|
Style Transfer (HP)
|
100% |
960
1.23 IPS |
|
Style Transfer (Q)
|
98% |
1268
1.63 IPS |
|
Image Super-Resolution (SP)
|
100% |
104
3.85 IPS |
|
Image Super-Resolution (HP)
|
100% |
261
9.64 IPS |
|
Image Super-Resolution (Q)
|
97% |
192
7.12 IPS |
|
Text Classification (SP)
|
100% |
62
83.3 IPS |
|
Text Classification (HP)
|
100% |
62
83.4 IPS |
|
Text Classification (Q)
|
91% |
80
107.8 IPS |
|
Machine Translation (SP)
|
100% |
111
1.91 IPS |
|
Machine Translation (HP)
|
100% |
112
1.93 IPS |
|
Machine Translation (Q)
|
57% |
85
2.08 IPS |