Upload Date | September 14 2024 04:25 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% |
1638
304.6 IPS |
|
Image Classification (HP)
|
100% |
11043
2.05 KIPS |
|
Image Classification (Q)
|
97% |
15305
2.86 KIPS |
|
Image Segmentation (SP)
|
100% |
1696
27.5 IPS |
|
Image Segmentation (HP)
|
100% |
12829
208.0 IPS |
|
Image Segmentation (Q)
|
99% |
15863
257.1 IPS |
|
Pose Estimation (SP)
|
100% |
7777
9.07 IPS |
|
Pose Estimation (HP)
|
100% |
105893
123.6 IPS |
|
Pose Estimation (Q)
|
95% |
202832
237.7 IPS |
|
Object Detection (SP)
|
100% |
1799
142.7 IPS |
|
Object Detection (HP)
|
100% |
13865
1.10 KIPS |
|
Object Detection (Q)
|
91% |
19160
1.53 KIPS |
|
Face Detection (SP)
|
100% |
3203
38.1 IPS |
|
Face Detection (HP)
|
100% |
33477
397.8 IPS |
|
Face Detection (Q)
|
100% |
48839
580.3 IPS |
|
Depth Estimation (SP)
|
100% |
7163
55.2 IPS |
|
Depth Estimation (HP)
|
99% |
78514
604.9 IPS |
|
Depth Estimation (Q)
|
85% |
125563
981.7 IPS |
|
Style Transfer (SP)
|
100% |
20961
26.9 IPS |
|
Style Transfer (HP)
|
100% |
138145
177.6 IPS |
|
Style Transfer (Q)
|
96% |
167159
215.7 IPS |
|
Image Super-Resolution (SP)
|
100% |
4928
182.0 IPS |
|
Image Super-Resolution (HP)
|
100% |
33911
1.25 KIPS |
|
Image Super-Resolution (Q)
|
99% |
53631
1.98 KIPS |
|
Text Classification (SP)
|
100% |
3194
4.26 KIPS |
|
Text Classification (HP)
|
100% |
2745
3.66 KIPS |
|
Text Classification (Q)
|
93% |
1832
2.46 KIPS |
|
Machine Translation (SP)
|
100% |
3118
53.7 IPS |
|
Machine Translation (HP)
|
100% |
6002
103.4 IPS |
|
Machine Translation (Q)
|
98% |
7154
123.6 IPS |