Upload Date | September 17 2024 08:37 PM |
Views | 1 |
AI Information | |
---|---|
Framework | Core ML |
Backend | Neural Engine |
Device | Apple A17 Pro |
System Information | |
---|---|
Operating System | iOS 18.1 |
Model | iPhone 15 Pro Max |
Model ID | iPhone16,2 |
Motherboard | D84AP |
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 | 7.48 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
1630
303.0 IPS |
|
Image Classification (HP)
|
100% |
11021
2.05 KIPS |
|
Image Classification (Q)
|
97% |
14783
2.76 KIPS |
|
Image Segmentation (SP)
|
100% |
1597
25.9 IPS |
|
Image Segmentation (HP)
|
100% |
12860
208.5 IPS |
|
Image Segmentation (Q)
|
99% |
16094
260.9 IPS |
|
Pose Estimation (SP)
|
100% |
7415
8.65 IPS |
|
Pose Estimation (HP)
|
100% |
105463
123.1 IPS |
|
Pose Estimation (Q)
|
95% |
203182
238.1 IPS |
|
Object Detection (SP)
|
100% |
1762
139.8 IPS |
|
Object Detection (HP)
|
100% |
13863
1.10 KIPS |
|
Object Detection (Q)
|
91% |
18955
1.51 KIPS |
|
Face Detection (SP)
|
100% |
3159
37.5 IPS |
|
Face Detection (HP)
|
100% |
33587
399.1 IPS |
|
Face Detection (Q)
|
100% |
49360
586.5 IPS |
|
Depth Estimation (SP)
|
100% |
6957
53.6 IPS |
|
Depth Estimation (HP)
|
99% |
78693
606.3 IPS |
|
Depth Estimation (Q)
|
85% |
128767
1.01 KIPS |
|
Style Transfer (SP)
|
100% |
20270
26.1 IPS |
|
Style Transfer (HP)
|
100% |
202822
260.7 IPS |
|
Style Transfer (Q)
|
96% |
248926
321.2 IPS |
|
Image Super-Resolution (SP)
|
100% |
4724
174.4 IPS |
|
Image Super-Resolution (HP)
|
100% |
34321
1.27 KIPS |
|
Image Super-Resolution (Q)
|
99% |
55055
2.03 KIPS |
|
Text Classification (SP)
|
100% |
3199
4.27 KIPS |
|
Text Classification (HP)
|
100% |
2755
3.68 KIPS |
|
Text Classification (Q)
|
93% |
1861
2.50 KIPS |
|
Machine Translation (SP)
|
100% |
3094
53.3 IPS |
|
Machine Translation (HP)
|
100% |
6490
111.8 IPS |
|
Machine Translation (Q)
|
98% |
7110
122.9 IPS |