Upload Date | September 14 2024 09:34 PM |
Views | 10 |
AI Information | |
---|---|
Framework | Core ML |
Backend | Neural Engine |
Device | Apple A16 Bionic |
System Information | |
---|---|
Operating System | iOS 18.0 |
Model | iPhone 15 |
Model ID | iPhone15,4 |
Motherboard | D37AP |
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 | 5.56 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
1420
264.1 IPS |
|
Image Classification (HP)
|
100% |
9685
1.80 KIPS |
|
Image Classification (Q)
|
97% |
12263
2.29 KIPS |
|
Image Segmentation (SP)
|
100% |
1478
24.0 IPS |
|
Image Segmentation (HP)
|
100% |
11379
184.5 IPS |
|
Image Segmentation (Q)
|
99% |
13527
219.3 IPS |
|
Pose Estimation (SP)
|
100% |
6780
7.91 IPS |
|
Pose Estimation (HP)
|
100% |
95682
111.6 IPS |
|
Pose Estimation (Q)
|
95% |
103622
121.5 IPS |
|
Object Detection (SP)
|
100% |
1600
126.9 IPS |
|
Object Detection (HP)
|
100% |
13078
1.04 KIPS |
|
Object Detection (Q)
|
91% |
14956
1.20 KIPS |
|
Face Detection (SP)
|
100% |
3374
40.1 IPS |
|
Face Detection (HP)
|
100% |
31053
369.0 IPS |
|
Face Detection (Q)
|
100% |
38993
463.3 IPS |
|
Depth Estimation (SP)
|
100% |
6163
47.5 IPS |
|
Depth Estimation (HP)
|
99% |
75336
580.4 IPS |
|
Depth Estimation (Q)
|
85% |
96820
757.0 IPS |
|
Style Transfer (SP)
|
100% |
18393
23.6 IPS |
|
Style Transfer (HP)
|
100% |
173960
223.6 IPS |
|
Style Transfer (Q)
|
96% |
172411
222.5 IPS |
|
Image Super-Resolution (SP)
|
100% |
4104
151.5 IPS |
|
Image Super-Resolution (HP)
|
100% |
33020
1.22 KIPS |
|
Image Super-Resolution (Q)
|
99% |
38220
1.41 KIPS |
|
Text Classification (SP)
|
100% |
2598
3.47 KIPS |
|
Text Classification (HP)
|
100% |
2162
2.89 KIPS |
|
Text Classification (Q)
|
93% |
2289
3.07 KIPS |
|
Machine Translation (SP)
|
100% |
3393
58.4 IPS |
|
Machine Translation (HP)
|
100% |
2358
40.6 IPS |
|
Machine Translation (Q)
|
98% |
2301
39.8 IPS |