Upload Date | January 26 2025 02:53 PM |
Views | 1 |
AI Information | |
---|---|
Framework | Core ML |
Backend | Neural Engine |
Device | Apple A16 Bionic |
System Information | |
---|---|
Operating System | iOS 18.2.1 |
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% |
1407
261.7 IPS |
|
Image Classification (HP)
|
100% |
10691
1.99 KIPS |
|
Image Classification (Q)
|
97% |
13135
2.45 KIPS |
|
Image Segmentation (SP)
|
100% |
1433
23.2 IPS |
|
Image Segmentation (HP)
|
100% |
13552
219.7 IPS |
|
Image Segmentation (Q)
|
99% |
17809
288.7 IPS |
|
Pose Estimation (SP)
|
100% |
6788
7.92 IPS |
|
Pose Estimation (HP)
|
100% |
98363
114.8 IPS |
|
Pose Estimation (Q)
|
95% |
101299
118.7 IPS |
|
Object Detection (SP)
|
100% |
1588
126.0 IPS |
|
Object Detection (HP)
|
100% |
12946
1.03 KIPS |
|
Object Detection (Q)
|
91% |
15158
1.21 KIPS |
|
Face Detection (SP)
|
100% |
3149
37.4 IPS |
|
Face Detection (HP)
|
100% |
30633
364.0 IPS |
|
Face Detection (Q)
|
100% |
40124
476.8 IPS |
|
Depth Estimation (SP)
|
100% |
6122
47.2 IPS |
|
Depth Estimation (HP)
|
99% |
74882
576.9 IPS |
|
Depth Estimation (Q)
|
85% |
94655
740.1 IPS |
|
Style Transfer (SP)
|
100% |
18871
24.3 IPS |
|
Style Transfer (HP)
|
100% |
168921
217.2 IPS |
|
Style Transfer (Q)
|
96% |
167979
216.8 IPS |
|
Image Super-Resolution (SP)
|
100% |
4214
155.6 IPS |
|
Image Super-Resolution (HP)
|
100% |
30727
1.13 KIPS |
|
Image Super-Resolution (Q)
|
99% |
36842
1.36 KIPS |
|
Text Classification (SP)
|
100% |
2616
3.49 KIPS |
|
Text Classification (HP)
|
100% |
2181
2.91 KIPS |
|
Text Classification (Q)
|
93% |
2218
2.98 KIPS |
|
Machine Translation (SP)
|
100% |
3450
59.4 IPS |
|
Machine Translation (HP)
|
100% |
7323
126.1 IPS |
|
Machine Translation (Q)
|
98% |
7756
134.0 IPS |