Upload Date | January 06 2025 10:52 AM |
Views | 1 |
AI Information | |
---|---|
Framework | Core ML |
Backend | Neural Engine |
Device | Apple A15 Bionic |
System Information | |
---|---|
Operating System | iOS 18.2 |
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% |
1365
253.8 IPS |
|
Image Classification (HP)
|
100% |
8401
1.56 KIPS |
|
Image Classification (Q)
|
96% |
9061
1.69 KIPS |
|
Image Segmentation (SP)
|
100% |
1342
21.8 IPS |
|
Image Segmentation (HP)
|
100% |
12305
199.5 IPS |
|
Image Segmentation (Q)
|
99% |
14312
232.0 IPS |
|
Pose Estimation (SP)
|
100% |
6518
7.61 IPS |
|
Pose Estimation (HP)
|
100% |
85042
99.2 IPS |
|
Pose Estimation (Q)
|
95% |
94325
110.6 IPS |
|
Object Detection (SP)
|
100% |
1479
117.3 IPS |
|
Object Detection (HP)
|
99% |
10414
828.4 IPS |
|
Object Detection (Q)
|
91% |
11768
940.3 IPS |
|
Face Detection (SP)
|
100% |
2792
33.2 IPS |
|
Face Detection (HP)
|
100% |
25420
302.0 IPS |
|
Face Detection (Q)
|
100% |
31394
373.0 IPS |
|
Depth Estimation (SP)
|
100% |
5475
42.2 IPS |
|
Depth Estimation (HP)
|
99% |
53576
412.8 IPS |
|
Depth Estimation (Q)
|
85% |
69881
546.1 IPS |
|
Style Transfer (SP)
|
100% |
17719
22.8 IPS |
|
Style Transfer (HP)
|
100% |
150039
192.9 IPS |
|
Style Transfer (Q)
|
96% |
153416
198.0 IPS |
|
Image Super-Resolution (SP)
|
100% |
3957
146.1 IPS |
|
Image Super-Resolution (HP)
|
100% |
27078
999.9 IPS |
|
Image Super-Resolution (Q)
|
99% |
27342
1.01 KIPS |
|
Text Classification (SP)
|
100% |
2435
3.25 KIPS |
|
Text Classification (HP)
|
100% |
1632
2.18 KIPS |
|
Text Classification (Q)
|
93% |
2383
3.20 KIPS |
|
Machine Translation (SP)
|
100% |
3506
60.4 IPS |
|
Machine Translation (HP)
|
100% |
6321
108.9 IPS |
|
Machine Translation (Q)
|
98% |
7251
125.3 IPS |