User | dr904 |
Upload Date | July 23 2025 10:05 AM |
Views | 4 |
AI Information | |
---|---|
Framework | Core ML |
Backend | Neural Engine |
Device | Apple A18 Pro |
System Information | |
---|---|
Operating System | iOS 18.5 |
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 | 7.47 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
2086
387.9 IPS |
|
Image Classification (HP)
|
100% |
15613
2.90 KIPS |
|
Image Classification (Q)
|
97% |
20704
3.86 KIPS |
|
Image Segmentation (SP)
|
100% |
1995
32.3 IPS |
|
Image Segmentation (HP)
|
100% |
18337
297.3 IPS |
|
Image Segmentation (Q)
|
99% |
24064
390.1 IPS |
|
Pose Estimation (SP)
|
100% |
9138
10.7 IPS |
|
Pose Estimation (HP)
|
100% |
148448
173.2 IPS |
|
Pose Estimation (Q)
|
95% |
291839
342.1 IPS |
|
Object Detection (SP)
|
100% |
2337
185.3 IPS |
|
Object Detection (HP)
|
100% |
16225
1.29 KIPS |
|
Object Detection (Q)
|
91% |
22661
1.81 KIPS |
|
Face Detection (SP)
|
100% |
3961
47.1 IPS |
|
Face Detection (HP)
|
100% |
40185
477.5 IPS |
|
Face Detection (Q)
|
100% |
57092
678.4 IPS |
|
Depth Estimation (SP)
|
100% |
8164
62.9 IPS |
|
Depth Estimation (HP)
|
99% |
95360
734.7 IPS |
|
Depth Estimation (Q)
|
85% |
159633
1.25 KIPS |
|
Style Transfer (SP)
|
100% |
20053
25.8 IPS |
|
Style Transfer (HP)
|
100% |
246245
316.6 IPS |
|
Style Transfer (Q)
|
96% |
302504
390.4 IPS |
|
Image Super-Resolution (SP)
|
100% |
5381
198.7 IPS |
|
Image Super-Resolution (HP)
|
100% |
51011
1.88 KIPS |
|
Image Super-Resolution (Q)
|
99% |
84298
3.11 KIPS |
|
Text Classification (SP)
|
100% |
3399
4.54 KIPS |
|
Text Classification (HP)
|
100% |
5008
6.68 KIPS |
|
Text Classification (Q)
|
93% |
5218
7.00 KIPS |
|
Machine Translation (SP)
|
100% |
4290
73.9 IPS |
|
Machine Translation (HP)
|
100% |
10297
177.4 IPS |
|
Machine Translation (Q)
|
98% |
11410
197.2 IPS |