Upload Date | May 07 2024 02:11 AM |
Views | 1 |
System Information | |
---|---|
Operating System | Android 14 |
Model | vivo I2208 |
Model ID | vivo I2208 |
Motherboard | holi |
Governor | schedutil |
CPU Information | |
---|---|
Name | ARM Qualcomm |
Topology | 1 Processor, 8 Cores |
Identifier | ARM implementer 65 architecture 8 variant 1 part 3393 revision 1 |
Base Frequency | 1.80 GHz |
Cluster 1 | 6 Cores @ 1.80 GHz |
Cluster 2 | 2 Cores @ 2.02 GHz |
Memory Information | |
---|---|
Size | 5.32 GB |
Inference Information | |
---|---|
Framework | TensorFlow Lite |
Backend | CPU |
Device | Default |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (F32)
|
100% |
106
19.7 IPS |
|
Image Classification (F16)
|
100% |
191
35.7 IPS |
|
Image Classification (I8)
|
97% |
500
93.6 IPS |
|
Image Segmentation (F32)
|
100% |
273
4.57 IPS |
|
Image Segmentation (F16)
|
100% |
284
4.74 IPS |
|
Image Segmentation (I8)
|
98% |
391
6.54 IPS |
|
Pose Estimation (F32)
|
100% |
351
0.42 IPS |
|
Pose Estimation (F16)
|
100% |
336
0.41 IPS |
|
Pose Estimation (I8)
|
100% |
1894
2.29 IPS |
|
Object Detection (F32)
|
100% |
205
15.3 IPS |
|
Object Detection (F16)
|
100% |
210
15.6 IPS |
|
Object Detection (I8)
|
61% |
548
40.9 IPS |
|
Face Detection (F32)
|
100% |
433
5.15 IPS |
|
Face Detection (F16)
|
100% |
431
5.12 IPS |
|
Face Detection (I8)
|
86% |
1080
12.8 IPS |
|
Depth Estimation (F32)
|
100% |
416
3.22 IPS |
|
Depth Estimation (F16)
|
100% |
428
3.32 IPS |
|
Depth Estimation (I8)
|
95% |
1095
8.49 IPS |
|
Style Transfer (F32)
|
100% |
699
0.92 IPS |
|
Style Transfer (F16)
|
100% |
676
0.89 IPS |
|
Style Transfer (I8)
|
98% |
1640
2.16 IPS |
|
Image Super-Resolution (F32)
|
100% |
251
8.96 IPS |
|
Image Super-Resolution (F16)
|
100% |
249
8.88 IPS |
|
Image Super-Resolution (I8)
|
98% |
812
29.0 IPS |
|
Text Classification (F32)
|
100% |
226
324.5 IPS |
|
Text Classification (F16)
|
100% |
210
301.2 IPS |
|
Text Classification (I8)
|
92% |
182
261.4 IPS |
|
Machine Translation (F32)
|
100% |
474
8.72 IPS |
|
Machine Translation (F16)
|
100% |
448
8.24 IPS |
|
Machine Translation (I8)
|
64% |
205
3.78 IPS |