Upload Date | December 30 2024 09:38 PM |
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% |
10474
1.95 KIPS |
|
Image Classification (Q)
|
97% |
11874
2.22 KIPS |
|
Image Segmentation (SP)
|
100% |
1408
22.8 IPS |
|
Image Segmentation (HP)
|
100% |
14396
233.4 IPS |
|
Image Segmentation (Q)
|
99% |
17643
286.0 IPS |
|
Pose Estimation (SP)
|
100% |
7094
8.28 IPS |
|
Pose Estimation (HP)
|
100% |
100207
116.9 IPS |
|
Pose Estimation (Q)
|
95% |
101488
118.9 IPS |
|
Object Detection (SP)
|
100% |
1562
123.9 IPS |
|
Object Detection (HP)
|
100% |
12882
1.02 KIPS |
|
Object Detection (Q)
|
91% |
14984
1.20 KIPS |
|
Face Detection (SP)
|
100% |
2899
34.4 IPS |
|
Face Detection (HP)
|
100% |
28472
338.3 IPS |
|
Face Detection (Q)
|
100% |
37227
442.3 IPS |
|
Depth Estimation (SP)
|
100% |
6116
47.1 IPS |
|
Depth Estimation (HP)
|
99% |
75311
580.2 IPS |
|
Depth Estimation (Q)
|
85% |
95980
750.4 IPS |
|
Style Transfer (SP)
|
100% |
18980
24.4 IPS |
|
Style Transfer (HP)
|
100% |
176083
226.4 IPS |
|
Style Transfer (Q)
|
96% |
169228
218.4 IPS |
|
Image Super-Resolution (SP)
|
100% |
4253
157.0 IPS |
|
Image Super-Resolution (HP)
|
100% |
32557
1.20 KIPS |
|
Image Super-Resolution (Q)
|
99% |
38446
1.42 KIPS |
|
Text Classification (SP)
|
100% |
2628
3.51 KIPS |
|
Text Classification (HP)
|
100% |
1988
2.65 KIPS |
|
Text Classification (Q)
|
93% |
1830
2.46 KIPS |
|
Machine Translation (SP)
|
100% |
3328
57.3 IPS |
|
Machine Translation (HP)
|
100% |
6991
120.4 IPS |
|
Machine Translation (Q)
|
98% |
7645
132.1 IPS |