Upload Date | September 17 2024 07:20 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% |
1709
317.9 IPS |
|
Image Classification (HP)
|
100% |
10727
1.99 KIPS |
|
Image Classification (Q)
|
97% |
14951
2.79 KIPS |
|
Image Segmentation (SP)
|
100% |
1624
26.3 IPS |
|
Image Segmentation (HP)
|
100% |
12828
208.0 IPS |
|
Image Segmentation (Q)
|
99% |
15883
257.5 IPS |
|
Pose Estimation (SP)
|
100% |
8106
9.46 IPS |
|
Pose Estimation (HP)
|
100% |
107613
125.6 IPS |
|
Pose Estimation (Q)
|
95% |
203105
238.1 IPS |
|
Object Detection (SP)
|
100% |
1792
142.2 IPS |
|
Object Detection (HP)
|
100% |
13871
1.10 KIPS |
|
Object Detection (Q)
|
91% |
18972
1.52 KIPS |
|
Face Detection (SP)
|
100% |
3172
37.7 IPS |
|
Face Detection (HP)
|
100% |
34455
409.4 IPS |
|
Face Detection (Q)
|
100% |
49089
583.3 IPS |
|
Depth Estimation (SP)
|
100% |
7085
54.6 IPS |
|
Depth Estimation (HP)
|
99% |
78526
605.0 IPS |
|
Depth Estimation (Q)
|
85% |
128511
1.00 KIPS |
|
Style Transfer (SP)
|
100% |
20892
26.9 IPS |
|
Style Transfer (HP)
|
100% |
138006
177.4 IPS |
|
Style Transfer (Q)
|
96% |
165076
213.0 IPS |
|
Image Super-Resolution (SP)
|
100% |
4960
183.1 IPS |
|
Image Super-Resolution (HP)
|
100% |
34100
1.26 KIPS |
|
Image Super-Resolution (Q)
|
99% |
57367
2.12 KIPS |
|
Text Classification (SP)
|
100% |
3179
4.24 KIPS |
|
Text Classification (HP)
|
100% |
3392
4.53 KIPS |
|
Text Classification (Q)
|
93% |
2918
3.92 KIPS |
|
Machine Translation (SP)
|
100% |
3121
53.8 IPS |
|
Machine Translation (HP)
|
100% |
6016
103.6 IPS |
|
Machine Translation (Q)
|
98% |
7466
129.0 IPS |