Upload Date | September 17 2024 01:38 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% |
1333
247.9 IPS |
|
Image Classification (HP)
|
100% |
9084
1.69 KIPS |
|
Image Classification (Q)
|
96% |
10302
1.92 KIPS |
|
Image Segmentation (SP)
|
100% |
1246
20.2 IPS |
|
Image Segmentation (HP)
|
100% |
7166
116.2 IPS |
|
Image Segmentation (Q)
|
99% |
7900
128.1 IPS |
|
Pose Estimation (SP)
|
100% |
5710
6.66 IPS |
|
Pose Estimation (HP)
|
100% |
83251
97.1 IPS |
|
Pose Estimation (Q)
|
95% |
92960
109.0 IPS |
|
Object Detection (SP)
|
100% |
1396
110.7 IPS |
|
Object Detection (HP)
|
99% |
10699
851.1 IPS |
|
Object Detection (Q)
|
91% |
11021
880.6 IPS |
|
Face Detection (SP)
|
100% |
2750
32.7 IPS |
|
Face Detection (HP)
|
100% |
26040
309.4 IPS |
|
Face Detection (Q)
|
100% |
30677
364.5 IPS |
|
Depth Estimation (SP)
|
100% |
5287
40.7 IPS |
|
Depth Estimation (HP)
|
99% |
53042
408.7 IPS |
|
Depth Estimation (Q)
|
85% |
70452
550.5 IPS |
|
Style Transfer (SP)
|
100% |
16508
21.2 IPS |
|
Style Transfer (HP)
|
100% |
150901
194.0 IPS |
|
Style Transfer (Q)
|
96% |
149158
192.5 IPS |
|
Image Super-Resolution (SP)
|
100% |
3789
139.9 IPS |
|
Image Super-Resolution (HP)
|
100% |
26521
979.3 IPS |
|
Image Super-Resolution (Q)
|
99% |
27162
1.00 KIPS |
|
Text Classification (SP)
|
100% |
2409
3.22 KIPS |
|
Text Classification (HP)
|
100% |
2312
3.09 KIPS |
|
Text Classification (Q)
|
93% |
2368
3.18 KIPS |
|
Machine Translation (SP)
|
100% |
3435
59.2 IPS |
|
Machine Translation (HP)
|
100% |
2088
36.0 IPS |
|
Machine Translation (Q)
|
98% |
2068
35.7 IPS |