Upload Date | January 04 2025 03:14 AM |
Views | 1 |
AI Information | |
---|---|
Framework | Core ML |
Backend | Neural Engine |
Device | Apple A16 Bionic |
System Information | |
---|---|
Operating System | iOS 18.2 |
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% |
1397
259.8 IPS |
|
Image Classification (HP)
|
100% |
10077
1.87 KIPS |
|
Image Classification (Q)
|
97% |
11888
2.22 KIPS |
|
Image Segmentation (SP)
|
100% |
1406
22.8 IPS |
|
Image Segmentation (HP)
|
100% |
14089
228.4 IPS |
|
Image Segmentation (Q)
|
99% |
18263
296.1 IPS |
|
Pose Estimation (SP)
|
100% |
6966
8.13 IPS |
|
Pose Estimation (HP)
|
100% |
96693
112.8 IPS |
|
Pose Estimation (Q)
|
95% |
100421
117.7 IPS |
|
Object Detection (SP)
|
100% |
1546
122.6 IPS |
|
Object Detection (HP)
|
100% |
12956
1.03 KIPS |
|
Object Detection (Q)
|
91% |
15097
1.21 KIPS |
|
Face Detection (SP)
|
100% |
2799
33.3 IPS |
|
Face Detection (HP)
|
100% |
29211
347.1 IPS |
|
Face Detection (Q)
|
100% |
39311
467.1 IPS |
|
Depth Estimation (SP)
|
100% |
6097
47.0 IPS |
|
Depth Estimation (HP)
|
99% |
74766
576.0 IPS |
|
Depth Estimation (Q)
|
85% |
95027
743.0 IPS |
|
Style Transfer (SP)
|
100% |
19044
24.5 IPS |
|
Style Transfer (HP)
|
100% |
166819
214.4 IPS |
|
Style Transfer (Q)
|
96% |
169174
218.3 IPS |
|
Image Super-Resolution (SP)
|
100% |
4230
156.2 IPS |
|
Image Super-Resolution (HP)
|
100% |
33024
1.22 KIPS |
|
Image Super-Resolution (Q)
|
99% |
36901
1.36 KIPS |
|
Text Classification (SP)
|
100% |
2628
3.51 KIPS |
|
Text Classification (HP)
|
100% |
1785
2.38 KIPS |
|
Text Classification (Q)
|
93% |
2482
3.33 KIPS |
|
Machine Translation (SP)
|
100% |
3280
56.5 IPS |
|
Machine Translation (HP)
|
100% |
7148
123.1 IPS |
|
Machine Translation (Q)
|
98% |
7876
136.1 IPS |