Upload Date | July 06 2024 10:14 PM |
Views | 1 |
System Information | |
---|---|
Operating System | Android 13 |
Model | reeder S19 Max Pro S |
Model ID | reeder S19 Max Pro S |
Motherboard | ums9230_1h10 |
Governor | schedutil |
CPU Information | |
---|---|
Name | ARM Unisoc |
Topology | 1 Processor, 8 Cores |
Identifier | ARM implementer 65 architecture 8 variant 3 part 3338 revision 1 |
Base Frequency | 1.61 GHz |
Cluster 1 | 8 Cores @ 1.61 GHz |
Memory Information | |
---|---|
Size | 7.59 GB |
Inference Information | |
---|---|
Framework | TensorFlow Lite |
Backend | CPU |
Device | Default |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (F32)
|
100% |
140
26.2 IPS |
|
Image Classification (F16)
|
100% |
141
26.3 IPS |
|
Image Classification (I8)
|
97% |
234
43.7 IPS |
|
Image Segmentation (F32)
|
100% |
206
3.44 IPS |
|
Image Segmentation (F16)
|
100% |
207
3.47 IPS |
|
Image Segmentation (I8)
|
98% |
253
4.23 IPS |
|
Pose Estimation (F32)
|
100% |
282
0.34 IPS |
|
Pose Estimation (F16)
|
100% |
275
0.33 IPS |
|
Pose Estimation (I8)
|
100% |
1302
1.58 IPS |
|
Object Detection (F32)
|
100% |
159
11.8 IPS |
|
Object Detection (F16)
|
100% |
157
11.7 IPS |
|
Object Detection (I8)
|
61% |
306
22.8 IPS |
|
Face Detection (F32)
|
100% |
336
4.00 IPS |
|
Face Detection (F16)
|
100% |
334
3.97 IPS |
|
Face Detection (I8)
|
86% |
709
8.43 IPS |
|
Depth Estimation (F32)
|
100% |
308
2.39 IPS |
|
Depth Estimation (F16)
|
100% |
306
2.38 IPS |
|
Depth Estimation (I8)
|
95% |
654
5.07 IPS |
|
Style Transfer (F32)
|
100% |
464
0.61 IPS |
|
Style Transfer (F16)
|
100% |
459
0.60 IPS |
|
Style Transfer (I8)
|
98% |
1376
1.81 IPS |
|
Image Super-Resolution (F32)
|
100% |
193
6.89 IPS |
|
Image Super-Resolution (F16)
|
100% |
188
6.71 IPS |
|
Image Super-Resolution (I8)
|
98% |
593
21.2 IPS |
|
Text Classification (F32)
|
100% |
179
256.8 IPS |
|
Text Classification (F16)
|
100% |
175
251.1 IPS |
|
Text Classification (I8)
|
92% |
142
204.3 IPS |
|
Machine Translation (F32)
|
100% |
321
5.91 IPS |
|
Machine Translation (F16)
|
100% |
311
5.73 IPS |
|
Machine Translation (I8)
|
64% |
169
3.11 IPS |