Upload Date | January 02 2025 11:01 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% |
1427
265.3 IPS |
|
Image Classification (HP)
|
100% |
10911
2.03 KIPS |
|
Image Classification (Q)
|
97% |
12650
2.36 KIPS |
|
Image Segmentation (SP)
|
100% |
1496
24.2 IPS |
|
Image Segmentation (HP)
|
100% |
13678
221.7 IPS |
|
Image Segmentation (Q)
|
99% |
18524
300.3 IPS |
|
Pose Estimation (SP)
|
100% |
6583
7.68 IPS |
|
Pose Estimation (HP)
|
100% |
96659
112.8 IPS |
|
Pose Estimation (Q)
|
95% |
101385
118.8 IPS |
|
Object Detection (SP)
|
100% |
1584
125.6 IPS |
|
Object Detection (HP)
|
100% |
12922
1.02 KIPS |
|
Object Detection (Q)
|
91% |
15041
1.20 KIPS |
|
Face Detection (SP)
|
100% |
3077
36.6 IPS |
|
Face Detection (HP)
|
100% |
30869
366.8 IPS |
|
Face Detection (Q)
|
100% |
39858
473.6 IPS |
|
Depth Estimation (SP)
|
100% |
6122
47.2 IPS |
|
Depth Estimation (HP)
|
99% |
74825
576.5 IPS |
|
Depth Estimation (Q)
|
85% |
95529
746.9 IPS |
|
Style Transfer (SP)
|
100% |
18809
24.2 IPS |
|
Style Transfer (HP)
|
100% |
170331
219.0 IPS |
|
Style Transfer (Q)
|
96% |
169732
219.0 IPS |
|
Image Super-Resolution (SP)
|
100% |
4178
154.3 IPS |
|
Image Super-Resolution (HP)
|
100% |
31759
1.17 KIPS |
|
Image Super-Resolution (Q)
|
99% |
37173
1.37 KIPS |
|
Text Classification (SP)
|
100% |
2637
3.52 KIPS |
|
Text Classification (HP)
|
100% |
1853
2.47 KIPS |
|
Text Classification (Q)
|
93% |
2481
3.33 KIPS |
|
Machine Translation (SP)
|
100% |
3438
59.2 IPS |
|
Machine Translation (HP)
|
100% |
7206
124.1 IPS |
|
Machine Translation (Q)
|
98% |
7980
137.9 IPS |