Upload Date | October 07 2024 07:49 PM |
Views | 1 |
AI Information | |
---|---|
Framework | Core ML |
Backend | Neural Engine |
Device | Apple A16 Bionic |
System Information | |
---|---|
Operating System | iOS 18.0.1 |
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% |
1440
267.7 IPS |
|
Image Classification (HP)
|
100% |
11145
2.07 KIPS |
|
Image Classification (Q)
|
97% |
13725
2.56 KIPS |
|
Image Segmentation (SP)
|
100% |
1445
23.4 IPS |
|
Image Segmentation (HP)
|
100% |
12222
198.1 IPS |
|
Image Segmentation (Q)
|
99% |
13822
224.1 IPS |
|
Pose Estimation (SP)
|
100% |
6555
7.65 IPS |
|
Pose Estimation (HP)
|
100% |
99325
115.9 IPS |
|
Pose Estimation (Q)
|
95% |
103933
121.8 IPS |
|
Object Detection (SP)
|
100% |
1549
122.9 IPS |
|
Object Detection (HP)
|
100% |
13055
1.04 KIPS |
|
Object Detection (Q)
|
91% |
15298
1.22 KIPS |
|
Face Detection (SP)
|
100% |
2886
34.3 IPS |
|
Face Detection (HP)
|
100% |
32512
386.3 IPS |
|
Face Detection (Q)
|
100% |
41271
490.4 IPS |
|
Depth Estimation (SP)
|
100% |
6122
47.2 IPS |
|
Depth Estimation (HP)
|
99% |
75506
581.7 IPS |
|
Depth Estimation (Q)
|
85% |
96579
755.1 IPS |
|
Style Transfer (SP)
|
100% |
19162
24.6 IPS |
|
Style Transfer (HP)
|
100% |
178381
229.3 IPS |
|
Style Transfer (Q)
|
96% |
171420
221.2 IPS |
|
Image Super-Resolution (SP)
|
100% |
4307
159.0 IPS |
|
Image Super-Resolution (HP)
|
100% |
33281
1.23 KIPS |
|
Image Super-Resolution (Q)
|
99% |
39129
1.44 KIPS |
|
Text Classification (SP)
|
100% |
2690
3.59 KIPS |
|
Text Classification (HP)
|
100% |
2495
3.33 KIPS |
|
Text Classification (Q)
|
93% |
2124
2.85 KIPS |
|
Machine Translation (SP)
|
100% |
3584
61.7 IPS |
|
Machine Translation (HP)
|
100% |
2440
42.0 IPS |
|
Machine Translation (Q)
|
98% |
2411
41.7 IPS |