User | eahyndman3 |
Upload Date | September 07 2024 03:48 PM |
Views | 14 |
AI Information | |
---|---|
Framework | Core ML |
Backend | Neural Engine |
Device | Apple A15 Bionic |
System Information | |
---|---|
Operating System | iOS 17.6.1 |
Model | iPhone 13 Pro |
Model ID | iPhone14,2 |
Motherboard | D63AP |
CPU Information | |
---|---|
Name | Apple A15 Bionic |
Topology | 1 Processor, 6 Cores |
Identifier | ARM |
Base Frequency | 3.23 GHz |
Cluster 1 | 2 Cores |
Cluster 2 | 4 Cores |
Memory Information | |
---|---|
Size | 5.50 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
1200
223.1 IPS |
|
Image Classification (HP)
|
100% |
4475
832.3 IPS |
|
Image Classification (Q)
|
96% |
5011
935.8 IPS |
|
Image Segmentation (SP)
|
100% |
666
10.8 IPS |
|
Image Segmentation (HP)
|
100% |
3952
64.1 IPS |
|
Image Segmentation (Q)
|
99% |
6748
109.4 IPS |
|
Pose Estimation (SP)
|
100% |
5779
6.74 IPS |
|
Pose Estimation (HP)
|
100% |
75190
87.7 IPS |
|
Pose Estimation (Q)
|
95% |
78170
91.6 IPS |
|
Object Detection (SP)
|
100% |
1212
96.1 IPS |
|
Object Detection (HP)
|
99% |
6866
546.2 IPS |
|
Object Detection (Q)
|
93% |
5977
476.9 IPS |
|
Face Detection (SP)
|
100% |
1909
22.7 IPS |
|
Face Detection (HP)
|
100% |
11003
130.7 IPS |
|
Face Detection (Q)
|
100% |
12932
153.7 IPS |
|
Depth Estimation (SP)
|
100% |
3738
28.8 IPS |
|
Depth Estimation (HP)
|
99% |
33684
259.5 IPS |
|
Depth Estimation (Q)
|
85% |
49413
386.1 IPS |
|
Style Transfer (SP)
|
100% |
10039
12.9 IPS |
|
Style Transfer (HP)
|
100% |
97940
125.9 IPS |
|
Style Transfer (Q)
|
95% |
105354
136.1 IPS |
|
Image Super-Resolution (SP)
|
100% |
3043
112.4 IPS |
|
Image Super-Resolution (HP)
|
100% |
14533
536.6 IPS |
|
Image Super-Resolution (Q)
|
99% |
16007
591.1 IPS |
|
Text Classification (SP)
|
100% |
1294
1.73 KIPS |
|
Text Classification (HP)
|
100% |
2522
3.37 KIPS |
|
Text Classification (Q)
|
93% |
2617
3.51 KIPS |
|
Machine Translation (SP)
|
100% |
1564
26.9 IPS |
|
Machine Translation (HP)
|
100% |
2149
37.0 IPS |
|
Machine Translation (Q)
|
98% |
2215
38.3 IPS |