User | pgfunny124 |
Upload Date | February 25 2025 07:31 PM |
Views | 6 |
AI Information | |
---|---|
Framework | Core ML |
Backend | Neural Engine |
Device | Apple A15 Bionic |
System Information | |
---|---|
Operating System | iOS 17.7.2 |
Model | iPhone 13 Pro |
Model ID | iPhone14,2 |
Motherboard | D63AP |
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 | 5.50 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
1193
221.9 IPS |
|
Image Classification (HP)
|
100% |
4362
811.1 IPS |
|
Image Classification (Q)
|
96% |
4944
923.3 IPS |
|
Image Segmentation (SP)
|
100% |
670
10.9 IPS |
|
Image Segmentation (HP)
|
100% |
3875
62.8 IPS |
|
Image Segmentation (Q)
|
99% |
5996
97.2 IPS |
|
Pose Estimation (SP)
|
100% |
5873
6.85 IPS |
|
Pose Estimation (HP)
|
100% |
71874
83.9 IPS |
|
Pose Estimation (Q)
|
95% |
75743
88.8 IPS |
|
Object Detection (SP)
|
100% |
1240
98.4 IPS |
|
Object Detection (HP)
|
99% |
5833
464.0 IPS |
|
Object Detection (Q)
|
93% |
7157
571.1 IPS |
|
Face Detection (SP)
|
100% |
1941
23.1 IPS |
|
Face Detection (HP)
|
100% |
10573
125.6 IPS |
|
Face Detection (Q)
|
100% |
12390
147.2 IPS |
|
Depth Estimation (SP)
|
100% |
3768
29.0 IPS |
|
Depth Estimation (HP)
|
99% |
34794
268.1 IPS |
|
Depth Estimation (Q)
|
85% |
45104
352.5 IPS |
|
Style Transfer (SP)
|
100% |
10303
13.2 IPS |
|
Style Transfer (HP)
|
100% |
103382
132.9 IPS |
|
Style Transfer (Q)
|
95% |
83012
107.2 IPS |
|
Image Super-Resolution (SP)
|
100% |
3086
114.0 IPS |
|
Image Super-Resolution (HP)
|
100% |
13673
504.9 IPS |
|
Image Super-Resolution (Q)
|
99% |
15501
572.4 IPS |
|
Text Classification (SP)
|
100% |
1286
1.72 KIPS |
|
Text Classification (HP)
|
100% |
3142
4.19 KIPS |
|
Text Classification (Q)
|
93% |
3130
4.20 KIPS |
|
Machine Translation (SP)
|
100% |
1558
26.8 IPS |
|
Machine Translation (HP)
|
100% |
2211
38.1 IPS |
|
Machine Translation (Q)
|
98% |
2177
37.6 IPS |