Upload Date | August 29 2024 08:50 AM |
Views | 1 |
System Information | |
---|---|
Operating System | Android 14 |
Model | Xiaomi Redmi Note 8 Pro |
Model ID | Xiaomi Redmi Note 8 Pro |
Motherboard | begonia |
CPU Information | |
---|---|
Name | ARM MT6785V/CC |
Topology | 1 Processor, 8 Cores |
Identifier | ARM implementer 65 architecture 8 variant 3 part 3339 revision 0 |
Base Frequency | 2.00 GHz |
Cluster 1 | 6 Cores @ 2.00 GHz |
Cluster 2 | 2 Cores @ 2.05 GHz |
Memory Information | |
---|---|
Size | 5.51 GB |
Inference Information | |
---|---|
Framework | TensorFlow Lite |
Backend | GPU |
Device | Default |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (F32)
|
100% |
36
6.69 IPS |
|
Image Classification (F16)
|
100% |
31
5.73 IPS |
|
Image Classification (I8)
|
97% |
30
5.64 IPS |
|
Image Segmentation (F32)
|
100% |
54
0.90 IPS |
|
Image Segmentation (F16)
|
100% |
47
0.79 IPS |
|
Image Segmentation (I8)
|
98% |
47
0.78 IPS |
|
Pose Estimation (F32)
|
100% |
31
0.04 IPS |
|
Pose Estimation (F16)
|
100% |
38
0.05 IPS |
|
Pose Estimation (I8)
|
100% |
39
0.05 IPS |
|
Object Detection (F32)
|
100% |
47
3.53 IPS |
|
Object Detection (F16)
|
100% |
39
2.90 IPS |
|
Object Detection (I8)
|
56% |
38
2.84 IPS |
|
Face Detection (F32)
|
100% |
157
1.86 IPS |
|
Face Detection (F16)
|
98% |
140
1.67 IPS |
|
Face Detection (I8)
|
86% |
135
1.61 IPS |
|
Depth Estimation (F32)
|
100% |
111
0.86 IPS |
|
Depth Estimation (F16)
|
100% |
86
0.67 IPS |
|
Depth Estimation (I8)
|
94% |
85
0.66 IPS |
|
Style Transfer (F32)
|
100% |
201
0.26 IPS |
|
Style Transfer (F16)
|
100% |
189
0.25 IPS |
|
Style Transfer (I8)
|
98% |
189
0.25 IPS |
|
Image Super-Resolution (F32)
|
100% |
63
2.27 IPS |
|
Image Super-Resolution (F16)
|
100% |
51
1.82 IPS |
|
Image Super-Resolution (I8)
|
98% |
51
1.81 IPS |
|
Text Classification (F32)
|
100% |
134
192.5 IPS |
|
Text Classification (F16)
|
100% |
134
192.1 IPS |
|
Text Classification (I8)
|
92% |
223
321.1 IPS |
|
Machine Translation (F32)
|
100% |
251
4.62 IPS |
|
Machine Translation (F16)
|
100% |
253
4.65 IPS |
|
Machine Translation (I8)
|
64% |
257
4.74 IPS |