User | M91 |
Upload Date | December 11 2024 11:55 AM |
Views | 2 |
AI Information | |
---|---|
Framework | Core ML |
Backend | Neural Engine |
Device | Apple A17 Pro |
System Information | |
---|---|
Operating System | iOS 18.2 |
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% |
1666
309.8 IPS |
|
Image Classification (HP)
|
100% |
10855
2.02 KIPS |
|
Image Classification (Q)
|
97% |
15442
2.88 KIPS |
|
Image Segmentation (SP)
|
100% |
1594
25.8 IPS |
|
Image Segmentation (HP)
|
100% |
15840
256.8 IPS |
|
Image Segmentation (Q)
|
99% |
21032
340.9 IPS |
|
Pose Estimation (SP)
|
100% |
7346
8.57 IPS |
|
Pose Estimation (HP)
|
100% |
103874
121.2 IPS |
|
Pose Estimation (Q)
|
95% |
203790
238.9 IPS |
|
Object Detection (SP)
|
100% |
1767
140.1 IPS |
|
Object Detection (HP)
|
100% |
13925
1.10 KIPS |
|
Object Detection (Q)
|
91% |
19348
1.55 KIPS |
|
Face Detection (SP)
|
100% |
3193
37.9 IPS |
|
Face Detection (HP)
|
100% |
34120
405.4 IPS |
|
Face Detection (Q)
|
100% |
51082
607.0 IPS |
|
Depth Estimation (SP)
|
100% |
6828
52.6 IPS |
|
Depth Estimation (HP)
|
99% |
78639
605.9 IPS |
|
Depth Estimation (Q)
|
85% |
127923
1.00 KIPS |
|
Style Transfer (SP)
|
100% |
20259
26.0 IPS |
|
Style Transfer (HP)
|
100% |
201414
258.9 IPS |
|
Style Transfer (Q)
|
96% |
249843
322.4 IPS |
|
Image Super-Resolution (SP)
|
100% |
4734
174.8 IPS |
|
Image Super-Resolution (HP)
|
100% |
33882
1.25 KIPS |
|
Image Super-Resolution (Q)
|
99% |
57093
2.11 KIPS |
|
Text Classification (SP)
|
100% |
3196
4.27 KIPS |
|
Text Classification (HP)
|
100% |
3063
4.09 KIPS |
|
Text Classification (Q)
|
93% |
3091
4.15 KIPS |
|
Machine Translation (SP)
|
100% |
3152
54.3 IPS |
|
Machine Translation (HP)
|
100% |
6448
111.1 IPS |
|
Machine Translation (Q)
|
98% |
7233
125.0 IPS |