Upload Date | July 18 2024 04:00 PM |
Views | 1 |
System Information | |
---|---|
Operating System | Android 13 |
Model | Xiaomi 11T Pro |
Model ID | Xiaomi 2107113SG |
Motherboard | vili |
Governor | schedutil |
CPU Information | |
---|---|
Name | ARM Odin |
Topology | 1 Processor, 8 Cores |
Identifier | ARM implementer 65 architecture 8 variant 1 part 3396 revision 0 |
Base Frequency | 1.80 GHz |
Cluster 1 | 4 Cores @ 1.80 GHz |
Cluster 2 | 3 Cores @ 2.42 GHz |
Cluster 3 | 1 Core @ 2.84 GHz |
Memory Information | |
---|---|
Size | 7.05 GB |
Inference Information | |
---|---|
Framework | TensorFlow Lite |
Backend | GPU |
Device | Default |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (F32)
|
100% |
413
77.2 IPS |
|
Image Classification (F16)
|
100% |
409
76.5 IPS |
|
Image Classification (I8)
|
97% |
382
71.6 IPS |
|
Image Segmentation (F32)
|
100% |
591
9.87 IPS |
|
Image Segmentation (F16)
|
100% |
727
12.1 IPS |
|
Image Segmentation (I8)
|
98% |
685
11.4 IPS |
|
Pose Estimation (F32)
|
100% |
711
0.86 IPS |
|
Pose Estimation (F16)
|
100% |
395
0.48 IPS |
|
Pose Estimation (I8)
|
100% |
402
0.49 IPS |
|
Object Detection (F32)
|
100% |
193
14.4 IPS |
|
Object Detection (F16)
|
100% |
200
14.9 IPS |
|
Object Detection (I8)
|
62% |
193
14.4 IPS |
|
Face Detection (F32)
|
100% |
1208
14.4 IPS |
|
Face Detection (F16)
|
97% |
1227
14.6 IPS |
|
Face Detection (I8)
|
87% |
1368
16.3 IPS |
|
Depth Estimation (F32)
|
100% |
1005
7.79 IPS |
|
Depth Estimation (F16)
|
100% |
1268
9.84 IPS |
|
Depth Estimation (I8)
|
95% |
1227
9.52 IPS |
|
Style Transfer (F32)
|
100% |
2073
2.73 IPS |
|
Style Transfer (F16)
|
100% |
3284
4.32 IPS |
|
Style Transfer (I8)
|
98% |
3277
4.31 IPS |
|
Image Super-Resolution (F32)
|
100% |
404
14.4 IPS |
|
Image Super-Resolution (F16)
|
100% |
477
17.0 IPS |
|
Image Super-Resolution (I8)
|
98% |
503
18.0 IPS |
|
Text Classification (F32)
|
100% |
182
261.9 IPS |
|
Text Classification (F16)
|
100% |
179
257.5 IPS |
|
Text Classification (I8)
|
92% |
301
432.5 IPS |
|
Machine Translation (F32)
|
100% |
333
6.13 IPS |
|
Machine Translation (F16)
|
100% |
249
4.58 IPS |
|
Machine Translation (I8)
|
64% |
294
5.42 IPS |