User | Ktest |
Upload Date | August 15 2024 07:41 PM |
Views | 4 |
AI Information | |
---|---|
Framework | Core ML |
Backend | Neural Engine |
Device | Apple A17 Pro |
System Information | |
---|---|
Operating System | iOS 17.6.1 |
Model | iPhone 15 Pro |
Model ID | iPhone16,1 |
Motherboard | D83AP |
CPU Information | |
---|---|
Name | Apple A17 Pro |
Topology | 1 Processor, 6 Cores |
Identifier | ARM |
Base Frequency | 3.78 GHz |
Cluster 1 | 2 Cores |
Cluster 2 | 4 Cores |
Memory Information | |
---|---|
Size | 7.47 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
1360
252.8 IPS |
|
Image Classification (HP)
|
100% |
6210
1.15 KIPS |
|
Image Classification (Q)
|
99% |
7220
1.35 KIPS |
|
Image Segmentation (SP)
|
100% |
794
12.9 IPS |
|
Image Segmentation (HP)
|
100% |
5118
83.0 IPS |
|
Image Segmentation (Q)
|
100% |
5500
89.2 IPS |
|
Pose Estimation (SP)
|
100% |
7493
8.74 IPS |
|
Pose Estimation (HP)
|
100% |
89646
104.6 IPS |
|
Pose Estimation (Q)
|
94% |
150923
177.0 IPS |
|
Object Detection (SP)
|
100% |
1412
112.0 IPS |
|
Object Detection (HP)
|
100% |
8678
688.3 IPS |
|
Object Detection (Q)
|
93% |
9489
757.1 IPS |
|
Face Detection (SP)
|
100% |
2142
25.4 IPS |
|
Face Detection (HP)
|
100% |
11788
140.1 IPS |
|
Face Detection (Q)
|
100% |
12158
144.5 IPS |
|
Depth Estimation (SP)
|
100% |
4065
31.3 IPS |
|
Depth Estimation (HP)
|
99% |
47135
363.2 IPS |
|
Depth Estimation (Q)
|
97% |
48587
375.7 IPS |
|
Style Transfer (SP)
|
100% |
7230
9.29 IPS |
|
Style Transfer (HP)
|
100% |
124728
160.3 IPS |
|
Style Transfer (Q)
|
100% |
126305
162.4 IPS |
|
Image Super-Resolution (SP)
|
100% |
3255
120.2 IPS |
|
Image Super-Resolution (HP)
|
100% |
18224
672.9 IPS |
|
Image Super-Resolution (Q)
|
98% |
28493
1.06 KIPS |
|
Text Classification (SP)
|
100% |
1098
1.47 KIPS |
|
Text Classification (HP)
|
71% |
5008
7.20 KIPS |
|
Text Classification (Q)
|
69% |
5179
7.59 KIPS |
|
Machine Translation (SP)
|
100% |
1325
22.8 IPS |
|
Machine Translation (HP)
|
100% |
1816
31.3 IPS |
|
Machine Translation (Q)
|
98% |
2448
42.3 IPS |