User | nadozza |
Upload Date | September 28 2024 01:11 AM |
Views | 5 |
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% |
1684
313.1 IPS |
|
Image Classification (HP)
|
100% |
10892
2.03 KIPS |
|
Image Classification (Q)
|
97% |
14938
2.79 KIPS |
|
Image Segmentation (SP)
|
100% |
1597
25.9 IPS |
|
Image Segmentation (HP)
|
100% |
15775
255.7 IPS |
|
Image Segmentation (Q)
|
99% |
20693
335.4 IPS |
|
Pose Estimation (SP)
|
100% |
8385
9.78 IPS |
|
Pose Estimation (HP)
|
100% |
107097
125.0 IPS |
|
Pose Estimation (Q)
|
95% |
203282
238.3 IPS |
|
Object Detection (SP)
|
100% |
1807
143.3 IPS |
|
Object Detection (HP)
|
100% |
13874
1.10 KIPS |
|
Object Detection (Q)
|
91% |
18916
1.51 KIPS |
|
Face Detection (SP)
|
100% |
3191
37.9 IPS |
|
Face Detection (HP)
|
100% |
34546
410.5 IPS |
|
Face Detection (Q)
|
100% |
50766
603.2 IPS |
|
Depth Estimation (SP)
|
100% |
7274
56.0 IPS |
|
Depth Estimation (HP)
|
99% |
78599
605.6 IPS |
|
Depth Estimation (Q)
|
85% |
127036
993.2 IPS |
|
Style Transfer (SP)
|
100% |
21177
27.2 IPS |
|
Style Transfer (HP)
|
100% |
202242
260.0 IPS |
|
Style Transfer (Q)
|
96% |
247813
319.8 IPS |
|
Image Super-Resolution (SP)
|
100% |
5124
189.2 IPS |
|
Image Super-Resolution (HP)
|
100% |
33681
1.24 KIPS |
|
Image Super-Resolution (Q)
|
99% |
57270
2.11 KIPS |
|
Text Classification (SP)
|
100% |
3204
4.28 KIPS |
|
Text Classification (HP)
|
100% |
1870
2.50 KIPS |
|
Text Classification (Q)
|
93% |
1847
2.48 KIPS |
|
Machine Translation (SP)
|
100% |
3088
53.2 IPS |
|
Machine Translation (HP)
|
100% |
6493
111.8 IPS |
|
Machine Translation (Q)
|
98% |
7297
126.1 IPS |