User | sunjw8888 |
Upload Date | August 16 2024 02:44 AM |
Views | 3 |
AI Information | |
---|---|
Framework | Core ML |
Backend | Neural Engine |
Device | Apple A17 Pro |
System Information | |
---|---|
Operating System | iOS 17.6.1 |
Model | iPhone 15 Pro |
Model ID | iPhone16,1 |
Motherboard | D83AP |
CPU Information | |
---|---|
Name | Apple A17 Pro |
Topology | 1 Processor, 6 Cores |
Identifier | ARM |
Base Frequency | 3.78 GHz |
Cluster 1 | 2 Cores |
Cluster 2 | 4 Cores |
Memory Information | |
---|---|
Size | 7.47 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
1472
273.7 IPS |
|
Image Classification (HP)
|
100% |
6287
1.17 KIPS |
|
Image Classification (Q)
|
99% |
6863
1.28 KIPS |
|
Image Segmentation (SP)
|
100% |
825
13.4 IPS |
|
Image Segmentation (HP)
|
100% |
5216
84.6 IPS |
|
Image Segmentation (Q)
|
100% |
5205
84.4 IPS |
|
Pose Estimation (SP)
|
100% |
7651
8.93 IPS |
|
Pose Estimation (HP)
|
100% |
88012
102.7 IPS |
|
Pose Estimation (Q)
|
94% |
129878
152.3 IPS |
|
Object Detection (SP)
|
100% |
1444
114.5 IPS |
|
Object Detection (HP)
|
100% |
8174
648.3 IPS |
|
Object Detection (Q)
|
93% |
9210
734.8 IPS |
|
Face Detection (SP)
|
100% |
2221
26.4 IPS |
|
Face Detection (HP)
|
100% |
11184
132.9 IPS |
|
Face Detection (Q)
|
100% |
13495
160.4 IPS |
|
Depth Estimation (SP)
|
100% |
4600
35.4 IPS |
|
Depth Estimation (HP)
|
99% |
42988
331.2 IPS |
|
Depth Estimation (Q)
|
97% |
48373
374.0 IPS |
|
Style Transfer (SP)
|
100% |
12092
15.5 IPS |
|
Style Transfer (HP)
|
100% |
128288
164.9 IPS |
|
Style Transfer (Q)
|
100% |
128218
164.8 IPS |
|
Image Super-Resolution (SP)
|
100% |
3747
138.3 IPS |
|
Image Super-Resolution (HP)
|
100% |
18393
679.2 IPS |
|
Image Super-Resolution (Q)
|
98% |
26572
984.5 IPS |
|
Text Classification (SP)
|
100% |
1806
2.41 KIPS |
|
Text Classification (HP)
|
71% |
4133
5.94 KIPS |
|
Text Classification (Q)
|
69% |
4025
5.90 KIPS |
|
Machine Translation (SP)
|
100% |
1881
32.4 IPS |
|
Machine Translation (HP)
|
100% |
2316
39.9 IPS |
|
Machine Translation (Q)
|
98% |
2343
40.5 IPS |