Upload Date | September 17 2024 02:29 AM |
Views | 1 |
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% |
1714
318.8 IPS |
|
Image Classification (HP)
|
100% |
11338
2.11 KIPS |
|
Image Classification (Q)
|
97% |
15020
2.80 KIPS |
|
Image Segmentation (SP)
|
100% |
1615
26.2 IPS |
|
Image Segmentation (HP)
|
100% |
12883
208.8 IPS |
|
Image Segmentation (Q)
|
99% |
15988
259.2 IPS |
|
Pose Estimation (SP)
|
100% |
8005
9.34 IPS |
|
Pose Estimation (HP)
|
100% |
106094
123.8 IPS |
|
Pose Estimation (Q)
|
95% |
203759
238.8 IPS |
|
Object Detection (SP)
|
100% |
1809
143.5 IPS |
|
Object Detection (HP)
|
100% |
13838
1.10 KIPS |
|
Object Detection (Q)
|
91% |
19379
1.55 KIPS |
|
Face Detection (SP)
|
100% |
3193
37.9 IPS |
|
Face Detection (HP)
|
100% |
33601
399.3 IPS |
|
Face Detection (Q)
|
100% |
49183
584.4 IPS |
|
Depth Estimation (SP)
|
100% |
7165
55.2 IPS |
|
Depth Estimation (HP)
|
99% |
78857
607.5 IPS |
|
Depth Estimation (Q)
|
85% |
127103
993.8 IPS |
|
Style Transfer (SP)
|
100% |
21480
27.6 IPS |
|
Style Transfer (HP)
|
100% |
205238
263.8 IPS |
|
Style Transfer (Q)
|
96% |
247882
319.9 IPS |
|
Image Super-Resolution (SP)
|
100% |
4970
183.5 IPS |
|
Image Super-Resolution (HP)
|
100% |
34576
1.28 KIPS |
|
Image Super-Resolution (Q)
|
99% |
58196
2.15 KIPS |
|
Text Classification (SP)
|
100% |
3228
4.31 KIPS |
|
Text Classification (HP)
|
100% |
2774
3.70 KIPS |
|
Text Classification (Q)
|
93% |
1995
2.68 KIPS |
|
Machine Translation (SP)
|
100% |
3114
53.6 IPS |
|
Machine Translation (HP)
|
100% |
6077
104.7 IPS |
|
Machine Translation (Q)
|
98% |
7282
125.8 IPS |