User | compaqdrew |
Upload Date | August 18 2024 10:54 PM |
Views | 6 |
AI Information | |
---|---|
Framework | Core ML |
Backend | Neural Engine |
Device | Apple A15 Bionic |
System Information | |
---|---|
Operating System | iOS 17.6.1 |
Model | iPhone 13 |
Model ID | iPhone14,5 |
Motherboard | D17AP |
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 | 3.54 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
949
176.6 IPS |
|
Image Classification (HP)
|
100% |
4193
779.7 IPS |
|
Image Classification (Q)
|
99% |
5138
958.3 IPS |
|
Image Segmentation (SP)
|
100% |
642
10.4 IPS |
|
Image Segmentation (HP)
|
100% |
3789
61.4 IPS |
|
Image Segmentation (Q)
|
100% |
3967
64.3 IPS |
|
Pose Estimation (SP)
|
100% |
5576
6.51 IPS |
|
Pose Estimation (HP)
|
100% |
74127
86.5 IPS |
|
Pose Estimation (Q)
|
94% |
65720
77.1 IPS |
|
Object Detection (SP)
|
100% |
969
76.9 IPS |
|
Object Detection (HP)
|
99% |
5586
444.4 IPS |
|
Object Detection (Q)
|
93% |
6408
511.3 IPS |
|
Face Detection (SP)
|
100% |
1678
19.9 IPS |
|
Face Detection (HP)
|
100% |
10576
125.7 IPS |
|
Face Detection (Q)
|
100% |
12098
143.8 IPS |
|
Depth Estimation (SP)
|
100% |
3182
24.5 IPS |
|
Depth Estimation (HP)
|
99% |
34442
265.4 IPS |
|
Depth Estimation (Q)
|
97% |
37063
286.6 IPS |
|
Style Transfer (SP)
|
100% |
9396
12.1 IPS |
|
Style Transfer (HP)
|
100% |
98979
127.2 IPS |
|
Style Transfer (Q)
|
100% |
105300
135.4 IPS |
|
Image Super-Resolution (SP)
|
100% |
2860
105.6 IPS |
|
Image Super-Resolution (HP)
|
100% |
13304
491.2 IPS |
|
Image Super-Resolution (Q)
|
98% |
15107
559.7 IPS |
|
Text Classification (SP)
|
100% |
1019
1.36 KIPS |
|
Text Classification (HP)
|
100% |
2534
3.38 KIPS |
|
Text Classification (Q)
|
93% |
2619
3.51 KIPS |
|
Machine Translation (SP)
|
100% |
1350
23.3 IPS |
|
Machine Translation (HP)
|
100% |
2095
36.1 IPS |
|
Machine Translation (Q)
|
98% |
2119
36.6 IPS |