User | sichunlam |
Upload Date | August 15 2024 05:53 PM |
Views | 4 |
AI Information | |
---|---|
Framework | Core ML |
Backend | GPU |
Device | Apple A15 Bionic |
System Information | |
---|---|
Operating System | iOS 17.6.1 |
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% |
716
133.1 IPS |
|
Image Classification (HP)
|
100% |
599
111.4 IPS |
|
Image Classification (Q)
|
99% |
554
103.4 IPS |
|
Image Segmentation (SP)
|
100% |
1929
31.3 IPS |
|
Image Segmentation (HP)
|
100% |
1944
31.5 IPS |
|
Image Segmentation (Q)
|
100% |
1973
32.0 IPS |
|
Pose Estimation (SP)
|
100% |
9088
10.6 IPS |
|
Pose Estimation (HP)
|
100% |
9911
11.6 IPS |
|
Pose Estimation (Q)
|
96% |
8926
10.5 IPS |
|
Object Detection (SP)
|
100% |
966
76.6 IPS |
|
Object Detection (HP)
|
100% |
943
74.8 IPS |
|
Object Detection (Q)
|
92% |
1282
102.3 IPS |
|
Face Detection (SP)
|
100% |
3140
37.3 IPS |
|
Face Detection (HP)
|
100% |
4769
56.7 IPS |
|
Face Detection (Q)
|
100% |
3138
37.3 IPS |
|
Depth Estimation (SP)
|
100% |
7118
54.8 IPS |
|
Depth Estimation (HP)
|
99% |
6521
50.2 IPS |
|
Depth Estimation (Q)
|
97% |
7770
60.1 IPS |
|
Style Transfer (SP)
|
100% |
16427
21.1 IPS |
|
Style Transfer (HP)
|
100% |
18958
24.4 IPS |
|
Style Transfer (Q)
|
100% |
18968
24.4 IPS |
|
Image Super-Resolution (SP)
|
100% |
2754
101.7 IPS |
|
Image Super-Resolution (HP)
|
100% |
2937
108.4 IPS |
|
Image Super-Resolution (Q)
|
98% |
2275
84.3 IPS |
|
Text Classification (SP)
|
100% |
360
480.4 IPS |
|
Text Classification (HP)
|
100% |
353
471.6 IPS |
|
Text Classification (Q)
|
93% |
202
271.3 IPS |
|
Machine Translation (SP)
|
100% |
549
9.45 IPS |
|
Machine Translation (HP)
|
100% |
659
11.4 IPS |
|
Machine Translation (Q)
|
98% |
646
11.2 IPS |