Upload Date | November 09 2024 06:15 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% |
1710
318.0 IPS |
|
Image Classification (HP)
|
100% |
11324
2.11 KIPS |
|
Image Classification (Q)
|
97% |
14518
2.71 KIPS |
|
Image Segmentation (SP)
|
100% |
1608
26.1 IPS |
|
Image Segmentation (HP)
|
100% |
15635
253.5 IPS |
|
Image Segmentation (Q)
|
99% |
20962
339.8 IPS |
|
Pose Estimation (SP)
|
100% |
8381
9.78 IPS |
|
Pose Estimation (HP)
|
100% |
106493
124.3 IPS |
|
Pose Estimation (Q)
|
95% |
204956
240.2 IPS |
|
Object Detection (SP)
|
100% |
1816
144.0 IPS |
|
Object Detection (HP)
|
100% |
13872
1.10 KIPS |
|
Object Detection (Q)
|
91% |
19296
1.54 KIPS |
|
Face Detection (SP)
|
100% |
3226
38.3 IPS |
|
Face Detection (HP)
|
100% |
33925
403.1 IPS |
|
Face Detection (Q)
|
100% |
50091
595.2 IPS |
|
Depth Estimation (SP)
|
100% |
7236
55.7 IPS |
|
Depth Estimation (HP)
|
99% |
78842
607.4 IPS |
|
Depth Estimation (Q)
|
85% |
127548
997.2 IPS |
|
Style Transfer (SP)
|
100% |
21600
27.8 IPS |
|
Style Transfer (HP)
|
100% |
201952
259.6 IPS |
|
Style Transfer (Q)
|
96% |
246804
318.5 IPS |
|
Image Super-Resolution (SP)
|
100% |
5127
189.3 IPS |
|
Image Super-Resolution (HP)
|
100% |
34917
1.29 KIPS |
|
Image Super-Resolution (Q)
|
99% |
59439
2.19 KIPS |
|
Text Classification (SP)
|
100% |
3201
4.27 KIPS |
|
Text Classification (HP)
|
100% |
3340
4.46 KIPS |
|
Text Classification (Q)
|
93% |
2514
3.37 KIPS |
|
Machine Translation (SP)
|
100% |
3107
53.5 IPS |
|
Machine Translation (HP)
|
100% |
6203
106.9 IPS |
|
Machine Translation (Q)
|
98% |
7310
126.3 IPS |