Upload Date | September 16 2024 01:39 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% |
1613
300.0 IPS |
|
Image Classification (HP)
|
100% |
10744
2.00 KIPS |
|
Image Classification (Q)
|
97% |
15449
2.88 KIPS |
|
Image Segmentation (SP)
|
100% |
1601
26.0 IPS |
|
Image Segmentation (HP)
|
100% |
12809
207.6 IPS |
|
Image Segmentation (Q)
|
99% |
15929
258.2 IPS |
|
Pose Estimation (SP)
|
100% |
7457
8.70 IPS |
|
Pose Estimation (HP)
|
100% |
103942
121.3 IPS |
|
Pose Estimation (Q)
|
95% |
204959
240.2 IPS |
|
Object Detection (SP)
|
100% |
1758
139.4 IPS |
|
Object Detection (HP)
|
100% |
13539
1.07 KIPS |
|
Object Detection (Q)
|
91% |
19057
1.52 KIPS |
|
Face Detection (SP)
|
100% |
3133
37.2 IPS |
|
Face Detection (HP)
|
100% |
33353
396.3 IPS |
|
Face Detection (Q)
|
100% |
48920
581.3 IPS |
|
Depth Estimation (SP)
|
100% |
6847
52.8 IPS |
|
Depth Estimation (HP)
|
99% |
78679
606.2 IPS |
|
Depth Estimation (Q)
|
85% |
127608
997.7 IPS |
|
Style Transfer (SP)
|
100% |
20140
25.9 IPS |
|
Style Transfer (HP)
|
100% |
206189
265.1 IPS |
|
Style Transfer (Q)
|
96% |
245637
317.0 IPS |
|
Image Super-Resolution (SP)
|
100% |
4730
174.6 IPS |
|
Image Super-Resolution (HP)
|
100% |
33795
1.25 KIPS |
|
Image Super-Resolution (Q)
|
99% |
56461
2.08 KIPS |
|
Text Classification (SP)
|
100% |
3264
4.36 KIPS |
|
Text Classification (HP)
|
100% |
3069
4.10 KIPS |
|
Text Classification (Q)
|
93% |
3098
4.16 KIPS |
|
Machine Translation (SP)
|
100% |
3239
55.8 IPS |
|
Machine Translation (HP)
|
100% |
6074
104.6 IPS |
|
Machine Translation (Q)
|
98% |
7544
130.4 IPS |