Upload Date | July 19 2024 01:02 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% |
179
33.4 IPS |
|
Image Classification (F16)
|
100% |
186
34.7 IPS |
|
Image Classification (I8)
|
97% |
428
80.1 IPS |
|
Image Segmentation (F32)
|
100% |
262
4.38 IPS |
|
Image Segmentation (F16)
|
100% |
266
4.44 IPS |
|
Image Segmentation (I8)
|
98% |
362
6.05 IPS |
|
Pose Estimation (F32)
|
100% |
368
0.45 IPS |
|
Pose Estimation (F16)
|
100% |
345
0.42 IPS |
|
Pose Estimation (I8)
|
100% |
1202
1.46 IPS |
|
Object Detection (F32)
|
100% |
208
15.5 IPS |
|
Object Detection (F16)
|
100% |
209
15.6 IPS |
|
Object Detection (I8)
|
61% |
470
35.1 IPS |
|
Face Detection (F32)
|
100% |
420
5.00 IPS |
|
Face Detection (F16)
|
100% |
249
2.97 IPS |
|
Face Detection (I8)
|
86% |
371
4.41 IPS |
|
Depth Estimation (F32)
|
100% |
409
3.17 IPS |
|
Depth Estimation (F16)
|
100% |
238
1.85 IPS |
|
Depth Estimation (I8)
|
95% |
333
2.58 IPS |
|
Style Transfer (F32)
|
100% |
599
0.79 IPS |
|
Style Transfer (F16)
|
100% |
590
0.78 IPS |
|
Style Transfer (I8)
|
98% |
1637
2.15 IPS |
|
Image Super-Resolution (F32)
|
100% |
210
7.49 IPS |
|
Image Super-Resolution (F16)
|
100% |
231
8.26 IPS |
|
Image Super-Resolution (I8)
|
98% |
583
20.8 IPS |
|
Text Classification (F32)
|
100% |
239
343.2 IPS |
|
Text Classification (F16)
|
100% |
226
325.2 IPS |
|
Text Classification (I8)
|
92% |
196
281.0 IPS |
|
Machine Translation (F32)
|
100% |
483
8.89 IPS |
|
Machine Translation (F16)
|
100% |
463
8.53 IPS |
|
Machine Translation (I8)
|
64% |
164
3.01 IPS |