Upload Date | January 06 2025 08:24 PM |
Views | 1 |
AI Information | |
---|---|
Framework | Core ML |
Backend | Neural Engine |
Device | Apple A17 Pro |
System Information | |
---|---|
Operating System | iOS 18.2 |
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% |
1691
314.6 IPS |
|
Image Classification (HP)
|
100% |
11513
2.14 KIPS |
|
Image Classification (Q)
|
97% |
15501
2.89 KIPS |
|
Image Segmentation (SP)
|
100% |
1598
25.9 IPS |
|
Image Segmentation (HP)
|
100% |
15686
254.3 IPS |
|
Image Segmentation (Q)
|
99% |
20882
338.5 IPS |
|
Pose Estimation (SP)
|
100% |
8221
9.59 IPS |
|
Pose Estimation (HP)
|
100% |
106936
124.8 IPS |
|
Pose Estimation (Q)
|
95% |
205458
240.8 IPS |
|
Object Detection (SP)
|
100% |
1789
141.9 IPS |
|
Object Detection (HP)
|
100% |
13561
1.08 KIPS |
|
Object Detection (Q)
|
91% |
18810
1.50 KIPS |
|
Face Detection (SP)
|
100% |
3116
37.0 IPS |
|
Face Detection (HP)
|
100% |
33054
392.8 IPS |
|
Face Detection (Q)
|
100% |
50275
597.4 IPS |
|
Depth Estimation (SP)
|
100% |
7106
54.7 IPS |
|
Depth Estimation (HP)
|
99% |
78331
603.5 IPS |
|
Depth Estimation (Q)
|
85% |
127320
995.4 IPS |
|
Style Transfer (SP)
|
100% |
21478
27.6 IPS |
|
Style Transfer (HP)
|
100% |
202622
260.5 IPS |
|
Style Transfer (Q)
|
96% |
245051
316.2 IPS |
|
Image Super-Resolution (SP)
|
100% |
5127
189.3 IPS |
|
Image Super-Resolution (HP)
|
100% |
33948
1.25 KIPS |
|
Image Super-Resolution (Q)
|
99% |
54356
2.01 KIPS |
|
Text Classification (SP)
|
100% |
3204
4.28 KIPS |
|
Text Classification (HP)
|
100% |
3174
4.24 KIPS |
|
Text Classification (Q)
|
93% |
3337
4.48 KIPS |
|
Machine Translation (SP)
|
100% |
3101
53.4 IPS |
|
Machine Translation (HP)
|
100% |
6178
106.4 IPS |
|
Machine Translation (Q)
|
98% |
7405
128.0 IPS |