Upload Date | December 22 2024 09:00 PM |
Views | 2 |
AI Information | |
---|---|
Framework | Core ML |
Backend | Neural Engine |
Device | Apple A16 Bionic |
System Information | |
---|---|
Operating System | iOS 18.3 |
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% |
1432
266.3 IPS |
|
Image Classification (HP)
|
100% |
8664
1.61 KIPS |
|
Image Classification (Q)
|
97% |
10471
1.95 KIPS |
|
Image Segmentation (SP)
|
100% |
1435
23.3 IPS |
|
Image Segmentation (HP)
|
100% |
13293
215.5 IPS |
|
Image Segmentation (Q)
|
99% |
17147
278.0 IPS |
|
Pose Estimation (SP)
|
100% |
6782
7.91 IPS |
|
Pose Estimation (HP)
|
100% |
98634
115.1 IPS |
|
Pose Estimation (Q)
|
95% |
101446
118.9 IPS |
|
Object Detection (SP)
|
100% |
1574
124.9 IPS |
|
Object Detection (HP)
|
100% |
12322
977.4 IPS |
|
Object Detection (Q)
|
91% |
14112
1.13 KIPS |
|
Face Detection (SP)
|
100% |
3091
36.7 IPS |
|
Face Detection (HP)
|
100% |
30575
363.3 IPS |
|
Face Detection (Q)
|
100% |
39197
465.7 IPS |
|
Depth Estimation (SP)
|
100% |
6214
47.9 IPS |
|
Depth Estimation (HP)
|
99% |
73571
566.8 IPS |
|
Depth Estimation (Q)
|
85% |
80451
629.0 IPS |
|
Style Transfer (SP)
|
100% |
18987
24.4 IPS |
|
Style Transfer (HP)
|
100% |
167253
215.0 IPS |
|
Style Transfer (Q)
|
96% |
170879
220.5 IPS |
|
Image Super-Resolution (SP)
|
100% |
4236
156.4 IPS |
|
Image Super-Resolution (HP)
|
100% |
27205
1.00 KIPS |
|
Image Super-Resolution (Q)
|
99% |
36664
1.35 KIPS |
|
Text Classification (SP)
|
100% |
2504
3.34 KIPS |
|
Text Classification (HP)
|
100% |
2173
2.90 KIPS |
|
Text Classification (Q)
|
93% |
2205
2.96 KIPS |
|
Machine Translation (SP)
|
100% |
3266
56.3 IPS |
|
Machine Translation (HP)
|
100% |
6734
116.0 IPS |
|
Machine Translation (Q)
|
98% |
7397
127.8 IPS |