Upload Date | January 06 2025 11:23 PM |
Views | 5 |
AI Information | |
---|---|
Framework | Core ML |
Backend | Neural Engine |
Device | Apple A16 Bionic |
System Information | |
---|---|
Operating System | iOS 18.2.1 |
Model | iPhone 14 Pro |
Model ID | iPhone15,2 |
Motherboard | D73AP |
CPU Information | |
---|---|
Name | Apple A16 Bionic |
Topology | 1 Processor, 6 Cores |
Identifier | ARM |
Base Frequency | 3.46 GHz |
Cluster 1 | 2 Cores |
Cluster 2 | 4 Cores |
Memory Information | |
---|---|
Size | 5.53 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
1431
266.2 IPS |
|
Image Classification (HP)
|
100% |
10508
1.95 KIPS |
|
Image Classification (Q)
|
97% |
12566
2.35 KIPS |
|
Image Segmentation (SP)
|
100% |
1439
23.3 IPS |
|
Image Segmentation (HP)
|
100% |
15056
244.1 IPS |
|
Image Segmentation (Q)
|
99% |
18007
291.9 IPS |
|
Pose Estimation (SP)
|
100% |
6863
8.01 IPS |
|
Pose Estimation (HP)
|
100% |
96113
112.1 IPS |
|
Pose Estimation (Q)
|
95% |
101765
119.3 IPS |
|
Object Detection (SP)
|
100% |
1587
125.9 IPS |
|
Object Detection (HP)
|
100% |
12921
1.02 KIPS |
|
Object Detection (Q)
|
91% |
14696
1.17 KIPS |
|
Face Detection (SP)
|
100% |
3110
37.0 IPS |
|
Face Detection (HP)
|
100% |
30323
360.3 IPS |
|
Face Detection (Q)
|
100% |
39437
468.6 IPS |
|
Depth Estimation (SP)
|
100% |
6164
47.5 IPS |
|
Depth Estimation (HP)
|
99% |
75141
578.9 IPS |
|
Depth Estimation (Q)
|
85% |
95743
748.6 IPS |
|
Style Transfer (SP)
|
100% |
18887
24.3 IPS |
|
Style Transfer (HP)
|
100% |
167217
215.0 IPS |
|
Style Transfer (Q)
|
96% |
171077
220.8 IPS |
|
Image Super-Resolution (SP)
|
100% |
4205
155.3 IPS |
|
Image Super-Resolution (HP)
|
100% |
32001
1.18 KIPS |
|
Image Super-Resolution (Q)
|
99% |
36751
1.36 KIPS |
|
Text Classification (SP)
|
100% |
2631
3.51 KIPS |
|
Text Classification (HP)
|
100% |
2238
2.99 KIPS |
|
Text Classification (Q)
|
93% |
2230
2.99 KIPS |
|
Machine Translation (SP)
|
100% |
3459
59.6 IPS |
|
Machine Translation (HP)
|
100% |
7131
122.8 IPS |
|
Machine Translation (Q)
|
98% |
8122
140.4 IPS |