Upload Date | December 26 2024 05:07 AM |
Views | 2 |
AI Information | |
---|---|
Framework | Core ML |
Backend | Neural Engine |
Device | Apple A16 Bionic |
System Information | |
---|---|
Operating System | iOS 18.2 |
Model | iPhone 14 Pro Max |
Model ID | iPhone15,3 |
Motherboard | D74AP |
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 | 5.51 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
1423
264.7 IPS |
|
Image Classification (HP)
|
100% |
9998
1.86 KIPS |
|
Image Classification (Q)
|
97% |
12541
2.34 KIPS |
|
Image Segmentation (SP)
|
100% |
1433
23.2 IPS |
|
Image Segmentation (HP)
|
100% |
13522
219.2 IPS |
|
Image Segmentation (Q)
|
99% |
18099
293.4 IPS |
|
Pose Estimation (SP)
|
100% |
6521
7.61 IPS |
|
Pose Estimation (HP)
|
100% |
96369
112.4 IPS |
|
Pose Estimation (Q)
|
95% |
101886
119.4 IPS |
|
Object Detection (SP)
|
100% |
1553
123.2 IPS |
|
Object Detection (HP)
|
100% |
13014
1.03 KIPS |
|
Object Detection (Q)
|
91% |
14970
1.20 KIPS |
|
Face Detection (SP)
|
100% |
2864
34.0 IPS |
|
Face Detection (HP)
|
100% |
30828
366.3 IPS |
|
Face Detection (Q)
|
100% |
40150
477.1 IPS |
|
Depth Estimation (SP)
|
100% |
6024
46.4 IPS |
|
Depth Estimation (HP)
|
99% |
74458
573.7 IPS |
|
Depth Estimation (Q)
|
85% |
95225
744.5 IPS |
|
Style Transfer (SP)
|
100% |
18323
23.6 IPS |
|
Style Transfer (HP)
|
100% |
165987
213.4 IPS |
|
Style Transfer (Q)
|
96% |
169095
218.2 IPS |
|
Image Super-Resolution (SP)
|
100% |
4195
154.9 IPS |
|
Image Super-Resolution (HP)
|
100% |
32170
1.19 KIPS |
|
Image Super-Resolution (Q)
|
99% |
38222
1.41 KIPS |
|
Text Classification (SP)
|
100% |
2666
3.56 KIPS |
|
Text Classification (HP)
|
100% |
1798
2.40 KIPS |
|
Text Classification (Q)
|
93% |
2516
3.38 KIPS |
|
Machine Translation (SP)
|
100% |
3429
59.1 IPS |
|
Machine Translation (HP)
|
100% |
7105
122.4 IPS |
|
Machine Translation (Q)
|
98% |
7887
136.3 IPS |