User | Paddie37 |
Upload Date | October 02 2024 01:58 PM |
Views | 4 |
AI Information | |
---|---|
Framework | Core ML |
Backend | Neural Engine |
Device | Apple A16 Bionic |
System Information | |
---|---|
Operating System | iOS 18.1 |
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% |
1416
263.3 IPS |
|
Image Classification (HP)
|
100% |
10086
1.88 KIPS |
|
Image Classification (Q)
|
97% |
12469
2.33 KIPS |
|
Image Segmentation (SP)
|
100% |
1457
23.6 IPS |
|
Image Segmentation (HP)
|
100% |
13638
221.1 IPS |
|
Image Segmentation (Q)
|
99% |
18611
301.7 IPS |
|
Pose Estimation (SP)
|
100% |
5301
6.19 IPS |
|
Pose Estimation (HP)
|
100% |
86564
101.0 IPS |
|
Pose Estimation (Q)
|
95% |
100348
117.6 IPS |
|
Object Detection (SP)
|
100% |
1303
103.4 IPS |
|
Object Detection (HP)
|
100% |
12427
985.8 IPS |
|
Object Detection (Q)
|
91% |
14992
1.20 KIPS |
|
Face Detection (SP)
|
100% |
2982
35.4 IPS |
|
Face Detection (HP)
|
100% |
31551
374.9 IPS |
|
Face Detection (Q)
|
100% |
39146
465.1 IPS |
|
Depth Estimation (SP)
|
100% |
5340
41.1 IPS |
|
Depth Estimation (HP)
|
99% |
69025
531.8 IPS |
|
Depth Estimation (Q)
|
85% |
94520
739.0 IPS |
|
Style Transfer (SP)
|
100% |
17158
22.1 IPS |
|
Style Transfer (HP)
|
100% |
171629
220.6 IPS |
|
Style Transfer (Q)
|
96% |
174049
224.6 IPS |
|
Image Super-Resolution (SP)
|
100% |
3693
136.4 IPS |
|
Image Super-Resolution (HP)
|
100% |
29399
1.09 KIPS |
|
Image Super-Resolution (Q)
|
99% |
35739
1.32 KIPS |
|
Text Classification (SP)
|
100% |
2554
3.41 KIPS |
|
Text Classification (HP)
|
100% |
2662
3.55 KIPS |
|
Text Classification (Q)
|
93% |
2156
2.89 KIPS |
|
Machine Translation (SP)
|
100% |
3340
57.5 IPS |
|
Machine Translation (HP)
|
100% |
2007
34.6 IPS |
|
Machine Translation (Q)
|
98% |
1964
33.9 IPS |