User | M91 |
Upload Date | January 17 2025 09:01 PM |
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% |
1631
303.3 IPS |
|
Image Classification (HP)
|
100% |
11257
2.09 KIPS |
|
Image Classification (Q)
|
97% |
15145
2.83 KIPS |
|
Image Segmentation (SP)
|
100% |
1611
26.1 IPS |
|
Image Segmentation (HP)
|
100% |
15611
253.1 IPS |
|
Image Segmentation (Q)
|
99% |
20659
334.9 IPS |
|
Pose Estimation (SP)
|
100% |
6845
7.99 IPS |
|
Pose Estimation (HP)
|
100% |
99842
116.5 IPS |
|
Pose Estimation (Q)
|
95% |
202285
237.1 IPS |
|
Object Detection (SP)
|
100% |
1708
135.5 IPS |
|
Object Detection (HP)
|
100% |
13496
1.07 KIPS |
|
Object Detection (Q)
|
91% |
18023
1.44 KIPS |
|
Face Detection (SP)
|
100% |
3079
36.6 IPS |
|
Face Detection (HP)
|
100% |
34032
404.4 IPS |
|
Face Detection (Q)
|
100% |
50317
597.9 IPS |
|
Depth Estimation (SP)
|
100% |
6588
50.8 IPS |
|
Depth Estimation (HP)
|
99% |
78233
602.7 IPS |
|
Depth Estimation (Q)
|
85% |
124419
972.8 IPS |
|
Style Transfer (SP)
|
100% |
18802
24.2 IPS |
|
Style Transfer (HP)
|
100% |
197866
254.4 IPS |
|
Style Transfer (Q)
|
96% |
248727
321.0 IPS |
|
Image Super-Resolution (SP)
|
100% |
4431
163.6 IPS |
|
Image Super-Resolution (HP)
|
100% |
33635
1.24 KIPS |
|
Image Super-Resolution (Q)
|
99% |
58680
2.17 KIPS |
|
Text Classification (SP)
|
100% |
3086
4.12 KIPS |
|
Text Classification (HP)
|
100% |
2907
3.88 KIPS |
|
Text Classification (Q)
|
93% |
2897
3.89 KIPS |
|
Machine Translation (SP)
|
100% |
3181
54.8 IPS |
|
Machine Translation (HP)
|
100% |
6633
114.3 IPS |
|
Machine Translation (Q)
|
98% |
7778
134.4 IPS |