Upload Date | September 19 2024 03:27 AM |
Views | 1 |
AI Information | |
---|---|
Framework | Core ML |
Backend | Neural Engine |
Device | Apple A15 Bionic |
System Information | |
---|---|
Operating System | iOS 18.0 |
Model | iPhone SE (3rd generation) |
Model ID | iPhone14,6 |
Motherboard | D49AP |
CPU Information | |
---|---|
Name | Apple A15 Bionic |
Topology | 1 Processor, 6 Cores |
Identifier | ARM |
Base Frequency | 3.23 GHz |
Cluster 1 | 2 Cores |
Cluster 2 | 4 Cores |
Memory Information | |
---|---|
Size | 3.80 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
1360
253.0 IPS |
|
Image Classification (HP)
|
100% |
8410
1.56 KIPS |
|
Image Classification (Q)
|
96% |
9864
1.84 KIPS |
|
Image Segmentation (SP)
|
100% |
1348
21.8 IPS |
|
Image Segmentation (HP)
|
100% |
6872
111.4 IPS |
|
Image Segmentation (Q)
|
99% |
7662
124.2 IPS |
|
Pose Estimation (SP)
|
100% |
6481
7.56 IPS |
|
Pose Estimation (HP)
|
100% |
86361
100.8 IPS |
|
Pose Estimation (Q)
|
95% |
93958
110.1 IPS |
|
Object Detection (SP)
|
100% |
1452
115.2 IPS |
|
Object Detection (HP)
|
99% |
10507
835.8 IPS |
|
Object Detection (Q)
|
91% |
11445
914.5 IPS |
|
Face Detection (SP)
|
100% |
2801
33.3 IPS |
|
Face Detection (HP)
|
100% |
26804
318.5 IPS |
|
Face Detection (Q)
|
100% |
32015
380.4 IPS |
|
Depth Estimation (SP)
|
100% |
5496
42.3 IPS |
|
Depth Estimation (HP)
|
99% |
53146
409.5 IPS |
|
Depth Estimation (Q)
|
85% |
72290
564.9 IPS |
|
Style Transfer (SP)
|
100% |
17545
22.6 IPS |
|
Style Transfer (HP)
|
100% |
156907
201.7 IPS |
|
Style Transfer (Q)
|
96% |
155819
201.1 IPS |
|
Image Super-Resolution (SP)
|
100% |
3855
142.4 IPS |
|
Image Super-Resolution (HP)
|
100% |
26381
974.1 IPS |
|
Image Super-Resolution (Q)
|
99% |
28381
1.05 KIPS |
|
Text Classification (SP)
|
100% |
2401
3.20 KIPS |
|
Text Classification (HP)
|
100% |
2273
3.03 KIPS |
|
Text Classification (Q)
|
93% |
2276
3.05 KIPS |
|
Machine Translation (SP)
|
100% |
3482
60.0 IPS |
|
Machine Translation (HP)
|
100% |
2309
39.8 IPS |
|
Machine Translation (Q)
|
98% |
2262
39.1 IPS |