Upload Date | September 18 2024 07:40 PM |
Views | 2 |
AI Information | |
---|---|
Framework | Core ML |
Backend | Neural Engine |
Device | Apple A16 Bionic |
System Information | |
---|---|
Operating System | iOS 18.0 |
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% |
1446
268.9 IPS |
|
Image Classification (HP)
|
100% |
10197
1.90 KIPS |
|
Image Classification (Q)
|
97% |
12258
2.29 KIPS |
|
Image Segmentation (SP)
|
100% |
1451
23.5 IPS |
|
Image Segmentation (HP)
|
100% |
11939
193.5 IPS |
|
Image Segmentation (Q)
|
99% |
14126
229.0 IPS |
|
Pose Estimation (SP)
|
100% |
6623
7.73 IPS |
|
Pose Estimation (HP)
|
100% |
95229
111.1 IPS |
|
Pose Estimation (Q)
|
95% |
101808
119.3 IPS |
|
Object Detection (SP)
|
100% |
1583
125.6 IPS |
|
Object Detection (HP)
|
100% |
12942
1.03 KIPS |
|
Object Detection (Q)
|
91% |
14476
1.16 KIPS |
|
Face Detection (SP)
|
100% |
2987
35.5 IPS |
|
Face Detection (HP)
|
100% |
30536
362.8 IPS |
|
Face Detection (Q)
|
100% |
38739
460.3 IPS |
|
Depth Estimation (SP)
|
100% |
6184
47.6 IPS |
|
Depth Estimation (HP)
|
99% |
74237
572.0 IPS |
|
Depth Estimation (Q)
|
85% |
96262
752.6 IPS |
|
Style Transfer (SP)
|
100% |
18314
23.5 IPS |
|
Style Transfer (HP)
|
100% |
168194
216.2 IPS |
|
Style Transfer (Q)
|
96% |
171714
221.6 IPS |
|
Image Super-Resolution (SP)
|
100% |
4116
152.0 IPS |
|
Image Super-Resolution (HP)
|
100% |
31411
1.16 KIPS |
|
Image Super-Resolution (Q)
|
99% |
36361
1.34 KIPS |
|
Text Classification (SP)
|
100% |
2626
3.51 KIPS |
|
Text Classification (HP)
|
100% |
2213
2.95 KIPS |
|
Text Classification (Q)
|
93% |
2354
3.16 KIPS |
|
Machine Translation (SP)
|
100% |
3428
59.0 IPS |
|
Machine Translation (HP)
|
100% |
2323
40.0 IPS |
|
Machine Translation (Q)
|
98% |
2270
39.2 IPS |