User | frank_m_h_jaeger |
Upload Date | August 18 2024 04:35 PM |
Views | 16 |
AI Information | |
---|---|
Framework | Core ML |
Backend | Neural Engine |
Device | Apple A13 Bionic |
System Information | |
---|---|
Operating System | iOS 17.6.1 |
Model | iPhone SE (2nd generation) |
Model ID | iPhone12,8 |
Motherboard | D79AP |
CPU Information | |
---|---|
Name | Apple A13 Bionic |
Topology | 1 Processor, 6 Cores |
Identifier | ARM |
Base Frequency | 2.66 GHz |
Cluster 1 | 2 Cores |
Cluster 2 | 4 Cores |
Memory Information | |
---|---|
Size | 2.89 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
543
100.9 IPS |
|
Image Classification (HP)
|
100% |
2735
508.7 IPS |
|
Image Classification (Q)
|
99% |
2783
519.1 IPS |
|
Image Segmentation (SP)
|
100% |
442
7.16 IPS |
|
Image Segmentation (HP)
|
100% |
501
8.13 IPS |
|
Image Segmentation (Q)
|
100% |
512
8.30 IPS |
|
Pose Estimation (SP)
|
100% |
3360
3.92 IPS |
|
Pose Estimation (HP)
|
100% |
28098
32.8 IPS |
|
Pose Estimation (Q)
|
95% |
3246
3.80 IPS |
|
Object Detection (SP)
|
100% |
573
45.4 IPS |
|
Object Detection (HP)
|
100% |
2476
196.4 IPS |
|
Object Detection (Q)
|
94% |
268
21.3 IPS |
|
Face Detection (SP)
|
100% |
1110
13.2 IPS |
|
Face Detection (HP)
|
100% |
6891
81.9 IPS |
|
Face Detection (Q)
|
100% |
420
4.99 IPS |
|
Depth Estimation (SP)
|
100% |
2026
15.6 IPS |
|
Depth Estimation (HP)
|
99% |
23200
178.7 IPS |
|
Depth Estimation (Q)
|
97% |
22942
177.4 IPS |
|
Style Transfer (SP)
|
100% |
5744
7.38 IPS |
|
Style Transfer (HP)
|
100% |
11361
14.6 IPS |
|
Style Transfer (Q)
|
100% |
11368
14.6 IPS |
|
Image Super-Resolution (SP)
|
100% |
1597
59.0 IPS |
|
Image Super-Resolution (HP)
|
100% |
3984
147.1 IPS |
|
Image Super-Resolution (Q)
|
98% |
545
20.2 IPS |
|
Text Classification (SP)
|
100% |
726
969.1 IPS |
|
Text Classification (HP)
|
100% |
423
565.3 IPS |
|
Text Classification (Q)
|
93% |
423
567.4 IPS |
|
Machine Translation (SP)
|
100% |
751
12.9 IPS |
|
Machine Translation (HP)
|
100% |
975
16.8 IPS |
|
Machine Translation (Q)
|
98% |
962
16.6 IPS |