Upload Date | November 21 2024 08:13 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% |
1692
314.7 IPS |
|
Image Classification (HP)
|
100% |
10983
2.04 KIPS |
|
Image Classification (Q)
|
97% |
14760
2.75 KIPS |
|
Image Segmentation (SP)
|
100% |
1595
25.9 IPS |
|
Image Segmentation (HP)
|
100% |
15862
257.1 IPS |
|
Image Segmentation (Q)
|
99% |
20527
332.8 IPS |
|
Pose Estimation (SP)
|
100% |
7657
8.93 IPS |
|
Pose Estimation (HP)
|
100% |
103328
120.6 IPS |
|
Pose Estimation (Q)
|
95% |
203419
238.4 IPS |
|
Object Detection (SP)
|
100% |
1772
140.6 IPS |
|
Object Detection (HP)
|
100% |
13931
1.11 KIPS |
|
Object Detection (Q)
|
91% |
19103
1.53 KIPS |
|
Face Detection (SP)
|
100% |
3080
36.6 IPS |
|
Face Detection (HP)
|
100% |
34305
407.6 IPS |
|
Face Detection (Q)
|
100% |
50533
600.4 IPS |
|
Depth Estimation (SP)
|
100% |
6982
53.8 IPS |
|
Depth Estimation (HP)
|
99% |
78468
604.6 IPS |
|
Depth Estimation (Q)
|
85% |
127001
992.9 IPS |
|
Style Transfer (SP)
|
100% |
20414
26.2 IPS |
|
Style Transfer (HP)
|
100% |
200935
258.3 IPS |
|
Style Transfer (Q)
|
96% |
248740
321.0 IPS |
|
Image Super-Resolution (SP)
|
100% |
4806
177.5 IPS |
|
Image Super-Resolution (HP)
|
100% |
34455
1.27 KIPS |
|
Image Super-Resolution (Q)
|
99% |
62739
2.32 KIPS |
|
Text Classification (SP)
|
100% |
3188
4.26 KIPS |
|
Text Classification (HP)
|
100% |
2714
3.62 KIPS |
|
Text Classification (Q)
|
93% |
3033
4.07 KIPS |
|
Machine Translation (SP)
|
100% |
3151
54.3 IPS |
|
Machine Translation (HP)
|
100% |
6579
113.3 IPS |
|
Machine Translation (Q)
|
98% |
7834
135.4 IPS |