User | MicheleGB |
Upload Date | December 18 2024 01:51 PM |
Views | 8 |
AI Information | |
---|---|
Framework | Core ML |
Backend | Neural Engine |
Device | Apple A14 Bionic |
System Information | |
---|---|
Operating System | iOS 17.7.2 |
Model | iPhone 12 Pro |
Model ID | iPhone13,3 |
Motherboard | D53pAP |
CPU Information | |
---|---|
Name | Apple A14 Bionic |
Topology | 1 Processor, 6 Cores |
Identifier | ARM |
Base Frequency | 2.99 GHz |
Cluster 1 | 2 Cores |
Cluster 2 | 4 Cores |
Memory Information | |
---|---|
Size | 5.54 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
925
172.1 IPS |
|
Image Classification (HP)
|
100% |
4585
852.6 IPS |
|
Image Classification (Q)
|
96% |
4608
860.6 IPS |
|
Image Segmentation (SP)
|
100% |
580
9.39 IPS |
|
Image Segmentation (HP)
|
100% |
3677
59.6 IPS |
|
Image Segmentation (Q)
|
99% |
439
7.12 IPS |
|
Pose Estimation (SP)
|
100% |
4495
5.24 IPS |
|
Pose Estimation (HP)
|
100% |
60560
70.7 IPS |
|
Pose Estimation (Q)
|
95% |
58349
68.4 IPS |
|
Object Detection (SP)
|
100% |
947
75.1 IPS |
|
Object Detection (HP)
|
99% |
5405
430.0 IPS |
|
Object Detection (Q)
|
93% |
5290
422.1 IPS |
|
Face Detection (SP)
|
100% |
1577
18.7 IPS |
|
Face Detection (HP)
|
100% |
11401
135.5 IPS |
|
Face Detection (Q)
|
100% |
10415
123.7 IPS |
|
Depth Estimation (SP)
|
100% |
3072
23.7 IPS |
|
Depth Estimation (HP)
|
99% |
34645
266.9 IPS |
|
Depth Estimation (Q)
|
85% |
42667
333.4 IPS |
|
Style Transfer (SP)
|
100% |
8426
10.8 IPS |
|
Style Transfer (HP)
|
100% |
93124
119.7 IPS |
|
Style Transfer (Q)
|
96% |
101282
130.7 IPS |
|
Image Super-Resolution (SP)
|
100% |
1901
70.2 IPS |
|
Image Super-Resolution (HP)
|
100% |
13714
506.4 IPS |
|
Image Super-Resolution (Q)
|
99% |
17548
648.0 IPS |
|
Text Classification (SP)
|
100% |
1144
1.53 KIPS |
|
Text Classification (HP)
|
100% |
3181
4.25 KIPS |
|
Text Classification (Q)
|
93% |
3592
4.82 KIPS |
|
Machine Translation (SP)
|
100% |
1131
19.5 IPS |
|
Machine Translation (HP)
|
100% |
1841
31.7 IPS |
|
Machine Translation (Q)
|
98% |
1804
31.2 IPS |