User | winzee |
Upload Date | December 10 2024 12:08 AM |
Views | 3 |
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% |
1432
266.3 IPS |
|
Image Classification (HP)
|
100% |
10338
1.92 KIPS |
|
Image Classification (Q)
|
97% |
12792
2.39 KIPS |
|
Image Segmentation (SP)
|
100% |
1437
23.3 IPS |
|
Image Segmentation (HP)
|
100% |
13695
222.0 IPS |
|
Image Segmentation (Q)
|
99% |
18011
292.0 IPS |
|
Pose Estimation (SP)
|
100% |
7110
8.30 IPS |
|
Pose Estimation (HP)
|
100% |
97009
113.2 IPS |
|
Pose Estimation (Q)
|
95% |
101737
119.2 IPS |
|
Object Detection (SP)
|
100% |
1590
126.1 IPS |
|
Object Detection (HP)
|
100% |
12879
1.02 KIPS |
|
Object Detection (Q)
|
91% |
14837
1.19 KIPS |
|
Face Detection (SP)
|
100% |
3111
37.0 IPS |
|
Face Detection (HP)
|
100% |
30784
365.8 IPS |
|
Face Detection (Q)
|
100% |
39746
472.3 IPS |
|
Depth Estimation (SP)
|
100% |
6160
47.5 IPS |
|
Depth Estimation (HP)
|
99% |
75142
578.9 IPS |
|
Depth Estimation (Q)
|
85% |
96071
751.1 IPS |
|
Style Transfer (SP)
|
100% |
18949
24.4 IPS |
|
Style Transfer (HP)
|
100% |
168886
217.1 IPS |
|
Style Transfer (Q)
|
96% |
168008
216.8 IPS |
|
Image Super-Resolution (SP)
|
100% |
4225
156.0 IPS |
|
Image Super-Resolution (HP)
|
100% |
31779
1.17 KIPS |
|
Image Super-Resolution (Q)
|
99% |
38072
1.41 KIPS |
|
Text Classification (SP)
|
100% |
2612
3.49 KIPS |
|
Text Classification (HP)
|
100% |
2285
3.05 KIPS |
|
Text Classification (Q)
|
93% |
2461
3.30 KIPS |
|
Machine Translation (SP)
|
100% |
3437
59.2 IPS |
|
Machine Translation (HP)
|
100% |
7223
124.4 IPS |
|
Machine Translation (Q)
|
98% |
7922
136.9 IPS |