Upload Date | September 17 2024 08:36 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% |
1652
307.2 IPS |
|
Image Classification (HP)
|
100% |
11656
2.17 KIPS |
|
Image Classification (Q)
|
97% |
14800
2.76 KIPS |
|
Image Segmentation (SP)
|
100% |
1622
26.3 IPS |
|
Image Segmentation (HP)
|
100% |
12888
208.9 IPS |
|
Image Segmentation (Q)
|
99% |
16030
259.9 IPS |
|
Pose Estimation (SP)
|
100% |
7674
8.95 IPS |
|
Pose Estimation (HP)
|
100% |
106110
123.8 IPS |
|
Pose Estimation (Q)
|
95% |
202734
237.6 IPS |
|
Object Detection (SP)
|
100% |
1778
141.0 IPS |
|
Object Detection (HP)
|
100% |
13805
1.10 KIPS |
|
Object Detection (Q)
|
91% |
18907
1.51 KIPS |
|
Face Detection (SP)
|
100% |
3185
37.8 IPS |
|
Face Detection (HP)
|
100% |
33765
401.2 IPS |
|
Face Detection (Q)
|
100% |
49435
587.4 IPS |
|
Depth Estimation (SP)
|
100% |
7060
54.4 IPS |
|
Depth Estimation (HP)
|
99% |
78573
605.4 IPS |
|
Depth Estimation (Q)
|
85% |
128548
1.01 KIPS |
|
Style Transfer (SP)
|
100% |
20610
26.5 IPS |
|
Style Transfer (HP)
|
100% |
203507
261.6 IPS |
|
Style Transfer (Q)
|
96% |
246196
317.7 IPS |
|
Image Super-Resolution (SP)
|
100% |
4760
175.8 IPS |
|
Image Super-Resolution (HP)
|
100% |
34313
1.27 KIPS |
|
Image Super-Resolution (Q)
|
99% |
54828
2.02 KIPS |
|
Text Classification (SP)
|
100% |
3230
4.31 KIPS |
|
Text Classification (HP)
|
100% |
2736
3.65 KIPS |
|
Text Classification (Q)
|
93% |
1787
2.40 KIPS |
|
Machine Translation (SP)
|
100% |
3133
54.0 IPS |
|
Machine Translation (HP)
|
100% |
6115
105.3 IPS |
|
Machine Translation (Q)
|
98% |
7185
124.2 IPS |