Upload Date | October 07 2024 07:26 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% |
1701
316.4 IPS |
|
Image Classification (HP)
|
100% |
11542
2.15 KIPS |
|
Image Classification (Q)
|
97% |
15186
2.83 KIPS |
|
Image Segmentation (SP)
|
100% |
1597
25.9 IPS |
|
Image Segmentation (HP)
|
100% |
15610
253.1 IPS |
|
Image Segmentation (Q)
|
99% |
20868
338.3 IPS |
|
Pose Estimation (SP)
|
100% |
7731
9.02 IPS |
|
Pose Estimation (HP)
|
100% |
107664
125.6 IPS |
|
Pose Estimation (Q)
|
95% |
204907
240.2 IPS |
|
Object Detection (SP)
|
100% |
1759
139.5 IPS |
|
Object Detection (HP)
|
100% |
14006
1.11 KIPS |
|
Object Detection (Q)
|
91% |
19343
1.55 KIPS |
|
Face Detection (SP)
|
100% |
3161
37.6 IPS |
|
Face Detection (HP)
|
100% |
35594
422.9 IPS |
|
Face Detection (Q)
|
100% |
50533
600.4 IPS |
|
Depth Estimation (SP)
|
100% |
6937
53.4 IPS |
|
Depth Estimation (HP)
|
99% |
79085
609.3 IPS |
|
Depth Estimation (Q)
|
85% |
127580
997.5 IPS |
|
Style Transfer (SP)
|
100% |
20494
26.3 IPS |
|
Style Transfer (HP)
|
100% |
203807
262.0 IPS |
|
Style Transfer (Q)
|
96% |
248018
320.1 IPS |
|
Image Super-Resolution (SP)
|
100% |
4831
178.4 IPS |
|
Image Super-Resolution (HP)
|
100% |
34332
1.27 KIPS |
|
Image Super-Resolution (Q)
|
99% |
56193
2.07 KIPS |
|
Text Classification (SP)
|
100% |
3197
4.27 KIPS |
|
Text Classification (HP)
|
100% |
3103
4.14 KIPS |
|
Text Classification (Q)
|
93% |
3222
4.32 KIPS |
|
Machine Translation (SP)
|
100% |
3091
53.2 IPS |
|
Machine Translation (HP)
|
100% |
6401
110.3 IPS |
|
Machine Translation (Q)
|
98% |
7334
126.7 IPS |