User | pestana58 |
Upload Date | January 04 2025 05:38 PM |
Views | 3 |
AI Information | |
---|---|
Framework | TensorFlow Lite |
Backend | GPU |
Device | Qualcomm Snapdragon 732G |
System Information | |
---|---|
Operating System | Android 12 |
Model | Xiaomi Redmi Note 10 Pro |
Model ID | Xiaomi M2101K6G |
Motherboard | sweet |
Governor | schedutil |
CPU Information | |
---|---|
Name | Qualcomm Qualcomm |
Topology | 1 Processor, 8 Cores |
Identifier | ARM implementer 81 architecture 8 variant 13 part 2052 revision 14 |
Base Frequency | 1.80 GHz |
Cluster 1 | 6 Cores @ 1.80 GHz |
Cluster 2 | 2 Cores @ 2.30 GHz |
Memory Information | |
---|---|
Size | 7.39 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
106
19.8 IPS |
|
Image Classification (HP)
|
100% |
169
31.4 IPS |
|
Image Classification (Q)
|
97% |
172
32.2 IPS |
|
Image Segmentation (SP)
|
100% |
126
2.05 IPS |
|
Image Segmentation (HP)
|
100% |
237
3.85 IPS |
|
Image Segmentation (Q)
|
98% |
218
3.55 IPS |
|
Pose Estimation (SP)
|
100% |
211
0.25 IPS |
|
Pose Estimation (HP)
|
100% |
280
0.33 IPS |
|
Pose Estimation (Q)
|
95% |
288
0.34 IPS |
|
Object Detection (SP)
|
100% |
92
7.28 IPS |
|
Object Detection (HP)
|
100% |
133
10.6 IPS |
|
Object Detection (Q)
|
89% |
136
10.9 IPS |
|
Face Detection (SP)
|
100% |
245
2.91 IPS |
|
Face Detection (HP)
|
100% |
430
5.11 IPS |
|
Face Detection (Q)
|
97% |
436
5.20 IPS |
|
Depth Estimation (SP)
|
100% |
255
1.97 IPS |
|
Depth Estimation (HP)
|
99% |
427
3.30 IPS |
|
Depth Estimation (Q)
|
62% |
351
3.33 IPS |
|
Style Transfer (SP)
|
100% |
501
0.64 IPS |
|
Style Transfer (HP)
|
100% |
1068
1.37 IPS |
|
Style Transfer (Q)
|
98% |
1062
1.37 IPS |
|
Image Super-Resolution (SP)
|
100% |
126
4.65 IPS |
|
Image Super-Resolution (HP)
|
100% |
156
5.75 IPS |
|
Image Super-Resolution (Q)
|
97% |
165
6.13 IPS |
|
Text Classification (SP)
|
100% |
112
148.9 IPS |
|
Text Classification (HP)
|
100% |
112
149.0 IPS |
|
Text Classification (Q)
|
91% |
180
241.6 IPS |
|
Machine Translation (SP)
|
100% |
191
3.29 IPS |
|
Machine Translation (HP)
|
100% |
194
3.33 IPS |
|
Machine Translation (Q)
|
57% |
155
3.78 IPS |