Upload Date | September 18 2024 05:05 PM |
Views | 2 |
AI Information | |
---|---|
Framework | Core ML |
Backend | Neural Engine |
Device | Apple A17 Pro |
System Information | |
---|---|
Operating System | iOS 18.0 |
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% |
1704
317.0 IPS |
|
Image Classification (HP)
|
100% |
11744
2.18 KIPS |
|
Image Classification (Q)
|
97% |
15484
2.89 KIPS |
|
Image Segmentation (SP)
|
100% |
1633
26.5 IPS |
|
Image Segmentation (HP)
|
100% |
12887
208.9 IPS |
|
Image Segmentation (Q)
|
99% |
15926
258.2 IPS |
|
Pose Estimation (SP)
|
100% |
7968
9.30 IPS |
|
Pose Estimation (HP)
|
100% |
107165
125.0 IPS |
|
Pose Estimation (Q)
|
95% |
202887
237.8 IPS |
|
Object Detection (SP)
|
100% |
1768
140.2 IPS |
|
Object Detection (HP)
|
100% |
13588
1.08 KIPS |
|
Object Detection (Q)
|
91% |
20687
1.65 KIPS |
|
Face Detection (SP)
|
100% |
3120
37.1 IPS |
|
Face Detection (HP)
|
100% |
34347
408.1 IPS |
|
Face Detection (Q)
|
100% |
49096
583.4 IPS |
|
Depth Estimation (SP)
|
100% |
6976
53.7 IPS |
|
Depth Estimation (HP)
|
99% |
78800
607.1 IPS |
|
Depth Estimation (Q)
|
85% |
126663
990.3 IPS |
|
Style Transfer (SP)
|
100% |
20936
26.9 IPS |
|
Style Transfer (HP)
|
100% |
205063
263.6 IPS |
|
Style Transfer (Q)
|
96% |
245666
317.0 IPS |
|
Image Super-Resolution (SP)
|
100% |
4872
179.9 IPS |
|
Image Super-Resolution (HP)
|
100% |
34216
1.26 KIPS |
|
Image Super-Resolution (Q)
|
99% |
59027
2.18 KIPS |
|
Text Classification (SP)
|
100% |
3196
4.27 KIPS |
|
Text Classification (HP)
|
100% |
3201
4.27 KIPS |
|
Text Classification (Q)
|
93% |
3200
4.29 KIPS |
|
Machine Translation (SP)
|
100% |
3092
53.3 IPS |
|
Machine Translation (HP)
|
100% |
6137
105.7 IPS |
|
Machine Translation (Q)
|
98% |
7267
125.6 IPS |