Upload Date | December 25 2024 06:08 PM |
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% |
1394
259.3 IPS |
|
Image Classification (HP)
|
100% |
10455
1.94 KIPS |
|
Image Classification (Q)
|
97% |
13065
2.44 KIPS |
|
Image Segmentation (SP)
|
100% |
1434
23.3 IPS |
|
Image Segmentation (HP)
|
100% |
14533
235.6 IPS |
|
Image Segmentation (Q)
|
99% |
18141
294.1 IPS |
|
Pose Estimation (SP)
|
100% |
6967
8.13 IPS |
|
Pose Estimation (HP)
|
100% |
94065
109.8 IPS |
|
Pose Estimation (Q)
|
95% |
102639
120.3 IPS |
|
Object Detection (SP)
|
100% |
1590
126.1 IPS |
|
Object Detection (HP)
|
100% |
12931
1.03 KIPS |
|
Object Detection (Q)
|
91% |
14873
1.19 KIPS |
|
Face Detection (SP)
|
100% |
3074
36.5 IPS |
|
Face Detection (HP)
|
100% |
29760
353.6 IPS |
|
Face Detection (Q)
|
100% |
40097
476.4 IPS |
|
Depth Estimation (SP)
|
100% |
6157
47.4 IPS |
|
Depth Estimation (HP)
|
99% |
76183
586.9 IPS |
|
Depth Estimation (Q)
|
85% |
94832
741.4 IPS |
|
Style Transfer (SP)
|
100% |
18781
24.1 IPS |
|
Style Transfer (HP)
|
100% |
164494
211.5 IPS |
|
Style Transfer (Q)
|
96% |
175299
226.2 IPS |
|
Image Super-Resolution (SP)
|
100% |
4323
159.6 IPS |
|
Image Super-Resolution (HP)
|
100% |
32986
1.22 KIPS |
|
Image Super-Resolution (Q)
|
99% |
36720
1.36 KIPS |
|
Text Classification (SP)
|
100% |
2617
3.49 KIPS |
|
Text Classification (HP)
|
100% |
2444
3.26 KIPS |
|
Text Classification (Q)
|
93% |
2221
2.98 KIPS |
|
Machine Translation (SP)
|
100% |
3522
60.7 IPS |
|
Machine Translation (HP)
|
100% |
7261
125.1 IPS |
|
Machine Translation (Q)
|
98% |
7624
131.8 IPS |