User | M91 |
Upload Date | August 25 2024 11:42 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% |
1643
305.5 IPS |
|
Image Classification (HP)
|
100% |
10931
2.03 KIPS |
|
Image Classification (Q)
|
99% |
13147
2.45 KIPS |
|
Image Segmentation (SP)
|
100% |
1587
25.7 IPS |
|
Image Segmentation (HP)
|
100% |
10469
169.7 IPS |
|
Image Segmentation (Q)
|
100% |
10511
170.4 IPS |
|
Pose Estimation (SP)
|
100% |
7374
8.60 IPS |
|
Pose Estimation (HP)
|
100% |
102438
119.5 IPS |
|
Pose Estimation (Q)
|
94% |
197830
232.0 IPS |
|
Object Detection (SP)
|
100% |
1775
140.8 IPS |
|
Object Detection (HP)
|
100% |
13112
1.04 KIPS |
|
Object Detection (Q)
|
91% |
18656
1.49 KIPS |
|
Face Detection (SP)
|
100% |
3221
38.3 IPS |
|
Face Detection (HP)
|
100% |
21816
259.2 IPS |
|
Face Detection (Q)
|
100% |
35368
420.2 IPS |
|
Depth Estimation (SP)
|
100% |
6983
53.8 IPS |
|
Depth Estimation (HP)
|
99% |
65445
504.2 IPS |
|
Depth Estimation (Q)
|
97% |
74467
575.8 IPS |
|
Style Transfer (SP)
|
100% |
20286
26.1 IPS |
|
Style Transfer (HP)
|
100% |
138485
178.0 IPS |
|
Style Transfer (Q)
|
100% |
139457
179.3 IPS |
|
Image Super-Resolution (SP)
|
100% |
4750
175.4 IPS |
|
Image Super-Resolution (HP)
|
100% |
34602
1.28 KIPS |
|
Image Super-Resolution (Q)
|
98% |
55106
2.04 KIPS |
|
Text Classification (SP)
|
100% |
3185
4.25 KIPS |
|
Text Classification (HP)
|
100% |
2836
3.79 KIPS |
|
Text Classification (Q)
|
93% |
1887
2.53 KIPS |
|
Machine Translation (SP)
|
100% |
3149
54.3 IPS |
|
Machine Translation (HP)
|
100% |
6790
117.0 IPS |
|
Machine Translation (Q)
|
98% |
7210
124.6 IPS |