Upload Date | July 19 2024 04:10 AM |
Views | 1 |
System Information | |
---|---|
Operating System | Android 13 |
Model | SHARP SHG05 |
Model ID | SHARP SHG05 |
Motherboard | Chara |
Governor | schedutil |
CPU Information | |
---|---|
Name | ARM Qualcomm |
Topology | 1 Processor, 8 Cores |
Identifier | ARM implementer 65 architecture 8 variant 1 part 3341 revision 0 |
Base Frequency | 1.71 GHz |
Cluster 1 | 6 Cores @ 1.71 GHz |
Cluster 2 | 2 Cores @ 2.07 GHz |
Memory Information | |
---|---|
Size | 3.39 GB |
Inference Information | |
---|---|
Framework | TensorFlow Lite |
Backend | CPU |
Device | Default |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (F32)
|
100% |
192
35.9 IPS |
|
Image Classification (F16)
|
100% |
198
37.1 IPS |
|
Image Classification (I8)
|
97% |
436
81.5 IPS |
|
Image Segmentation (F32)
|
100% |
271
4.52 IPS |
|
Image Segmentation (F16)
|
100% |
269
4.49 IPS |
|
Image Segmentation (I8)
|
98% |
362
6.05 IPS |
|
Pose Estimation (F32)
|
100% |
371
0.45 IPS |
|
Pose Estimation (F16)
|
100% |
377
0.46 IPS |
|
Pose Estimation (I8)
|
100% |
1327
1.61 IPS |
|
Object Detection (F32)
|
100% |
213
15.9 IPS |
|
Object Detection (F16)
|
100% |
216
16.1 IPS |
|
Object Detection (I8)
|
61% |
500
37.4 IPS |
|
Face Detection (F32)
|
100% |
428
5.09 IPS |
|
Face Detection (F16)
|
100% |
430
5.11 IPS |
|
Face Detection (I8)
|
86% |
1055
12.5 IPS |
|
Depth Estimation (F32)
|
100% |
393
3.05 IPS |
|
Depth Estimation (F16)
|
100% |
407
3.15 IPS |
|
Depth Estimation (I8)
|
95% |
975
7.56 IPS |
|
Style Transfer (F32)
|
100% |
625
0.82 IPS |
|
Style Transfer (F16)
|
100% |
620
0.82 IPS |
|
Style Transfer (I8)
|
98% |
1530
2.01 IPS |
|
Image Super-Resolution (F32)
|
100% |
200
7.14 IPS |
|
Image Super-Resolution (F16)
|
100% |
227
8.10 IPS |
|
Image Super-Resolution (I8)
|
98% |
731
26.1 IPS |
|
Text Classification (F32)
|
100% |
225
323.2 IPS |
|
Text Classification (F16)
|
100% |
234
336.5 IPS |
|
Text Classification (I8)
|
92% |
198
284.3 IPS |
|
Machine Translation (F32)
|
100% |
473
8.70 IPS |
|
Machine Translation (F16)
|
100% |
468
8.61 IPS |
|
Machine Translation (I8)
|
64% |
158
2.91 IPS |