Upload Date | September 16 2024 10:38 AM |
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% |
1633
303.7 IPS |
|
Image Classification (HP)
|
100% |
10677
1.99 KIPS |
|
Image Classification (Q)
|
97% |
15183
2.83 KIPS |
|
Image Segmentation (SP)
|
100% |
1571
25.5 IPS |
|
Image Segmentation (HP)
|
100% |
12850
208.3 IPS |
|
Image Segmentation (Q)
|
99% |
16078
260.6 IPS |
|
Pose Estimation (SP)
|
100% |
7197
8.40 IPS |
|
Pose Estimation (HP)
|
100% |
100601
117.4 IPS |
|
Pose Estimation (Q)
|
95% |
202731
237.6 IPS |
|
Object Detection (SP)
|
100% |
1717
136.2 IPS |
|
Object Detection (HP)
|
100% |
13859
1.10 KIPS |
|
Object Detection (Q)
|
91% |
19217
1.54 KIPS |
|
Face Detection (SP)
|
100% |
3096
36.8 IPS |
|
Face Detection (HP)
|
100% |
33449
397.4 IPS |
|
Face Detection (Q)
|
100% |
49969
593.7 IPS |
|
Depth Estimation (SP)
|
100% |
6688
51.5 IPS |
|
Depth Estimation (HP)
|
99% |
78619
605.7 IPS |
|
Depth Estimation (Q)
|
85% |
126771
991.2 IPS |
|
Style Transfer (SP)
|
100% |
19823
25.5 IPS |
|
Style Transfer (HP)
|
100% |
138155
177.6 IPS |
|
Style Transfer (Q)
|
96% |
164852
212.7 IPS |
|
Image Super-Resolution (SP)
|
100% |
4710
173.9 IPS |
|
Image Super-Resolution (HP)
|
100% |
34130
1.26 KIPS |
|
Image Super-Resolution (Q)
|
99% |
58396
2.16 KIPS |
|
Text Classification (SP)
|
100% |
3160
4.22 KIPS |
|
Text Classification (HP)
|
100% |
2065
2.76 KIPS |
|
Text Classification (Q)
|
93% |
1982
2.66 KIPS |
|
Machine Translation (SP)
|
100% |
3092
53.3 IPS |
|
Machine Translation (HP)
|
100% |
6097
105.0 IPS |
|
Machine Translation (Q)
|
98% |
7285
125.9 IPS |