User | M91 |
Upload Date | September 17 2024 10:59 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 |
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 | 7.51 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
1639
304.7 IPS |
|
Image Classification (HP)
|
100% |
11069
2.06 KIPS |
|
Image Classification (Q)
|
97% |
15342
2.86 KIPS |
|
Image Segmentation (SP)
|
100% |
1590
25.8 IPS |
|
Image Segmentation (HP)
|
100% |
12953
210.0 IPS |
|
Image Segmentation (Q)
|
99% |
16105
261.1 IPS |
|
Pose Estimation (SP)
|
100% |
7364
8.59 IPS |
|
Pose Estimation (HP)
|
100% |
104377
121.8 IPS |
|
Pose Estimation (Q)
|
95% |
204232
239.4 IPS |
|
Object Detection (SP)
|
100% |
1768
140.2 IPS |
|
Object Detection (HP)
|
100% |
13859
1.10 KIPS |
|
Object Detection (Q)
|
91% |
19061
1.52 KIPS |
|
Face Detection (SP)
|
100% |
3217
38.2 IPS |
|
Face Detection (HP)
|
100% |
33461
397.6 IPS |
|
Face Detection (Q)
|
100% |
49374
586.7 IPS |
|
Depth Estimation (SP)
|
100% |
6936
53.4 IPS |
|
Depth Estimation (HP)
|
99% |
78446
604.4 IPS |
|
Depth Estimation (Q)
|
85% |
126658
990.3 IPS |
|
Style Transfer (SP)
|
100% |
20562
26.4 IPS |
|
Style Transfer (HP)
|
100% |
138196
177.7 IPS |
|
Style Transfer (Q)
|
96% |
167663
216.4 IPS |
|
Image Super-Resolution (SP)
|
100% |
4833
178.4 IPS |
|
Image Super-Resolution (HP)
|
100% |
34189
1.26 KIPS |
|
Image Super-Resolution (Q)
|
99% |
55588
2.05 KIPS |
|
Text Classification (SP)
|
100% |
3178
4.24 KIPS |
|
Text Classification (HP)
|
100% |
2729
3.64 KIPS |
|
Text Classification (Q)
|
93% |
1941
2.61 KIPS |
|
Machine Translation (SP)
|
100% |
3136
54.0 IPS |
|
Machine Translation (HP)
|
100% |
6106
105.2 IPS |
|
Machine Translation (Q)
|
98% |
7321
126.5 IPS |