User | Fine_HIMEMIYA |
Upload Date | December 06 2024 06:24 AM |
Views | 4 |
AI Information | |
---|---|
Framework | Core ML |
Backend | Neural Engine |
Device | Apple A18 Pro |
System Information | |
---|---|
Operating System | iOS 18.1.1 |
Model | iPhone 16 Pro |
Model ID | iPhone17,1 |
Motherboard | D93AP |
CPU Information | |
---|---|
Name | Apple A18 Pro |
Topology | 1 Processor, 6 Cores |
Identifier | ARM |
Base Frequency | 4.04 GHz |
Cluster 1 | 2 Cores |
Cluster 2 | 4 Cores |
Memory Information | |
---|---|
Size | 7.49 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
2019
375.5 IPS |
|
Image Classification (HP)
|
100% |
15238
2.83 KIPS |
|
Image Classification (Q)
|
97% |
20177
3.77 KIPS |
|
Image Segmentation (SP)
|
100% |
1980
32.1 IPS |
|
Image Segmentation (HP)
|
100% |
18347
297.4 IPS |
|
Image Segmentation (Q)
|
99% |
24187
392.1 IPS |
|
Pose Estimation (SP)
|
100% |
9128
10.7 IPS |
|
Pose Estimation (HP)
|
100% |
153932
179.6 IPS |
|
Pose Estimation (Q)
|
95% |
294937
345.7 IPS |
|
Object Detection (SP)
|
100% |
2158
171.2 IPS |
|
Object Detection (HP)
|
100% |
16406
1.30 KIPS |
|
Object Detection (Q)
|
91% |
23192
1.85 KIPS |
|
Face Detection (SP)
|
100% |
3677
43.7 IPS |
|
Face Detection (HP)
|
100% |
41854
497.3 IPS |
|
Face Detection (Q)
|
100% |
57539
683.7 IPS |
|
Depth Estimation (SP)
|
100% |
7936
61.1 IPS |
|
Depth Estimation (HP)
|
99% |
95972
739.4 IPS |
|
Depth Estimation (Q)
|
85% |
163345
1.28 KIPS |
|
Style Transfer (SP)
|
100% |
24326
31.3 IPS |
|
Style Transfer (HP)
|
100% |
244857
314.8 IPS |
|
Style Transfer (Q)
|
96% |
304468
392.9 IPS |
|
Image Super-Resolution (SP)
|
100% |
5807
214.4 IPS |
|
Image Super-Resolution (HP)
|
100% |
50724
1.87 KIPS |
|
Image Super-Resolution (Q)
|
99% |
87416
3.23 KIPS |
|
Text Classification (SP)
|
100% |
3434
4.58 KIPS |
|
Text Classification (HP)
|
100% |
4797
6.40 KIPS |
|
Text Classification (Q)
|
93% |
5077
6.81 KIPS |
|
Machine Translation (SP)
|
100% |
3808
65.6 IPS |
|
Machine Translation (HP)
|
100% |
9484
163.4 IPS |
|
Machine Translation (Q)
|
98% |
11574
200.0 IPS |