User | M91 |
Upload Date | January 29 2025 11:10 AM |
Views | 2 |
AI Information | |
---|---|
Framework | Core ML |
Backend | Neural Engine |
Device | Apple A17 Pro |
System Information | |
---|---|
Operating System | iOS 18.3 |
Model | iPhone 15 Pro |
Model ID | iPhone16,1 |
Motherboard | D83AP |
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 | 7.50 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
1695
315.2 IPS |
|
Image Classification (HP)
|
100% |
10817
2.01 KIPS |
|
Image Classification (Q)
|
97% |
15533
2.90 KIPS |
|
Image Segmentation (SP)
|
100% |
1604
26.0 IPS |
|
Image Segmentation (HP)
|
100% |
15922
258.1 IPS |
|
Image Segmentation (Q)
|
99% |
20704
335.6 IPS |
|
Pose Estimation (SP)
|
100% |
7457
8.70 IPS |
|
Pose Estimation (HP)
|
100% |
103232
120.5 IPS |
|
Pose Estimation (Q)
|
95% |
203382
238.4 IPS |
|
Object Detection (SP)
|
100% |
1768
140.2 IPS |
|
Object Detection (HP)
|
100% |
13862
1.10 KIPS |
|
Object Detection (Q)
|
91% |
19058
1.52 KIPS |
|
Face Detection (SP)
|
100% |
3165
37.6 IPS |
|
Face Detection (HP)
|
100% |
33951
403.4 IPS |
|
Face Detection (Q)
|
100% |
50333
598.1 IPS |
|
Depth Estimation (SP)
|
100% |
6772
52.2 IPS |
|
Depth Estimation (HP)
|
99% |
78139
602.0 IPS |
|
Depth Estimation (Q)
|
85% |
126834
991.6 IPS |
|
Style Transfer (SP)
|
100% |
19960
25.7 IPS |
|
Style Transfer (HP)
|
100% |
201225
258.7 IPS |
|
Style Transfer (Q)
|
96% |
251679
324.8 IPS |
|
Image Super-Resolution (SP)
|
100% |
4670
172.5 IPS |
|
Image Super-Resolution (HP)
|
100% |
33465
1.24 KIPS |
|
Image Super-Resolution (Q)
|
99% |
60671
2.24 KIPS |
|
Text Classification (SP)
|
100% |
3198
4.27 KIPS |
|
Text Classification (HP)
|
100% |
2360
3.15 KIPS |
|
Text Classification (Q)
|
93% |
2683
3.60 KIPS |
|
Machine Translation (SP)
|
100% |
3141
54.1 IPS |
|
Machine Translation (HP)
|
100% |
6417
110.5 IPS |
|
Machine Translation (Q)
|
98% |
7423
128.3 IPS |