Upload Date | November 17 2024 08:53 PM |
Views | 1 |
AI Information | |
---|---|
Framework | Core ML |
Backend | Neural Engine |
Device | Apple A15 Bionic |
System Information | |
---|---|
Operating System | iOS 18.1 |
Model | iPhone 13 mini |
Model ID | iPhone14,4 |
Motherboard | D16AP |
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 | 3.59 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
1348
250.6 IPS |
|
Image Classification (HP)
|
100% |
9446
1.76 KIPS |
|
Image Classification (Q)
|
96% |
9913
1.85 KIPS |
|
Image Segmentation (SP)
|
100% |
1343
21.8 IPS |
|
Image Segmentation (HP)
|
100% |
12705
206.0 IPS |
|
Image Segmentation (Q)
|
99% |
13783
223.4 IPS |
|
Pose Estimation (SP)
|
100% |
5842
6.82 IPS |
|
Pose Estimation (HP)
|
100% |
81165
94.7 IPS |
|
Pose Estimation (Q)
|
95% |
89199
104.5 IPS |
|
Object Detection (SP)
|
100% |
1454
115.3 IPS |
|
Object Detection (HP)
|
99% |
10878
865.3 IPS |
|
Object Detection (Q)
|
91% |
11737
937.8 IPS |
|
Face Detection (SP)
|
100% |
2830
33.6 IPS |
|
Face Detection (HP)
|
100% |
25113
298.4 IPS |
|
Face Detection (Q)
|
100% |
31741
377.1 IPS |
|
Depth Estimation (SP)
|
100% |
5408
41.7 IPS |
|
Depth Estimation (HP)
|
99% |
53456
411.8 IPS |
|
Depth Estimation (Q)
|
85% |
71658
560.0 IPS |
|
Style Transfer (SP)
|
100% |
16548
21.3 IPS |
|
Style Transfer (HP)
|
100% |
153790
197.7 IPS |
|
Style Transfer (Q)
|
96% |
154572
199.5 IPS |
|
Image Super-Resolution (SP)
|
100% |
3842
141.9 IPS |
|
Image Super-Resolution (HP)
|
100% |
25914
956.9 IPS |
|
Image Super-Resolution (Q)
|
99% |
28046
1.04 KIPS |
|
Text Classification (SP)
|
100% |
2420
3.23 KIPS |
|
Text Classification (HP)
|
100% |
2225
2.97 KIPS |
|
Text Classification (Q)
|
93% |
2283
3.06 KIPS |
|
Machine Translation (SP)
|
100% |
3441
59.3 IPS |
|
Machine Translation (HP)
|
100% |
4601
79.2 IPS |
|
Machine Translation (Q)
|
98% |
5537
95.7 IPS |