Upload Date | September 16 2024 10:07 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% |
1636
304.3 IPS |
|
Image Classification (HP)
|
100% |
11183
2.08 KIPS |
|
Image Classification (Q)
|
97% |
14984
2.80 KIPS |
|
Image Segmentation (SP)
|
100% |
1528
24.8 IPS |
|
Image Segmentation (HP)
|
100% |
12845
208.2 IPS |
|
Image Segmentation (Q)
|
99% |
15988
259.2 IPS |
|
Pose Estimation (SP)
|
100% |
7089
8.27 IPS |
|
Pose Estimation (HP)
|
100% |
98124
114.5 IPS |
|
Pose Estimation (Q)
|
95% |
197323
231.3 IPS |
|
Object Detection (SP)
|
100% |
1661
131.7 IPS |
|
Object Detection (HP)
|
100% |
13651
1.08 KIPS |
|
Object Detection (Q)
|
91% |
18988
1.52 KIPS |
|
Face Detection (SP)
|
100% |
2932
34.8 IPS |
|
Face Detection (HP)
|
100% |
34778
413.2 IPS |
|
Face Detection (Q)
|
100% |
49021
582.5 IPS |
|
Depth Estimation (SP)
|
100% |
6434
49.6 IPS |
|
Depth Estimation (HP)
|
99% |
78416
604.1 IPS |
|
Depth Estimation (Q)
|
85% |
127728
998.6 IPS |
|
Style Transfer (SP)
|
100% |
18562
23.9 IPS |
|
Style Transfer (HP)
|
100% |
137570
176.8 IPS |
|
Style Transfer (Q)
|
96% |
165621
213.7 IPS |
|
Image Super-Resolution (SP)
|
100% |
4352
160.7 IPS |
|
Image Super-Resolution (HP)
|
100% |
32867
1.21 KIPS |
|
Image Super-Resolution (Q)
|
99% |
54882
2.03 KIPS |
|
Text Classification (SP)
|
100% |
3165
4.22 KIPS |
|
Text Classification (HP)
|
100% |
2935
3.92 KIPS |
|
Text Classification (Q)
|
93% |
1922
2.58 KIPS |
|
Machine Translation (SP)
|
100% |
3067
52.8 IPS |
|
Machine Translation (HP)
|
100% |
6005
103.4 IPS |
|
Machine Translation (Q)
|
98% |
7178
124.0 IPS |