User | buliaoyin |
Upload Date | October 16 2024 04:48 AM |
Views | 7 |
AI Information | |
---|---|
Framework | Core ML |
Backend | Neural Engine |
Device | Apple A17 Pro |
System Information | |
---|---|
Operating System | iOS 18.0.1 |
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 | 7.51 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
1723
320.4 IPS |
|
Image Classification (HP)
|
100% |
10719
1.99 KIPS |
|
Image Classification (Q)
|
97% |
15206
2.84 KIPS |
|
Image Segmentation (SP)
|
100% |
1639
26.6 IPS |
|
Image Segmentation (HP)
|
100% |
12995
210.7 IPS |
|
Image Segmentation (Q)
|
99% |
15998
259.3 IPS |
|
Pose Estimation (SP)
|
100% |
8362
9.76 IPS |
|
Pose Estimation (HP)
|
100% |
106646
124.4 IPS |
|
Pose Estimation (Q)
|
95% |
204740
240.0 IPS |
|
Object Detection (SP)
|
100% |
1820
144.4 IPS |
|
Object Detection (HP)
|
100% |
13520
1.07 KIPS |
|
Object Detection (Q)
|
91% |
18862
1.51 KIPS |
|
Face Detection (SP)
|
100% |
3272
38.9 IPS |
|
Face Detection (HP)
|
100% |
34523
410.2 IPS |
|
Face Detection (Q)
|
100% |
51056
606.7 IPS |
|
Depth Estimation (SP)
|
100% |
7184
55.3 IPS |
|
Depth Estimation (HP)
|
99% |
79119
609.6 IPS |
|
Depth Estimation (Q)
|
85% |
127816
999.3 IPS |
|
Style Transfer (SP)
|
100% |
21550
27.7 IPS |
|
Style Transfer (HP)
|
100% |
204311
262.6 IPS |
|
Style Transfer (Q)
|
96% |
247238
319.0 IPS |
|
Image Super-Resolution (SP)
|
100% |
5113
188.8 IPS |
|
Image Super-Resolution (HP)
|
100% |
35592
1.31 KIPS |
|
Image Super-Resolution (Q)
|
99% |
55655
2.06 KIPS |
|
Text Classification (SP)
|
100% |
3201
4.27 KIPS |
|
Text Classification (HP)
|
100% |
3104
4.14 KIPS |
|
Text Classification (Q)
|
93% |
3125
4.19 KIPS |
|
Machine Translation (SP)
|
100% |
3139
54.1 IPS |
|
Machine Translation (HP)
|
100% |
6614
113.9 IPS |
|
Machine Translation (Q)
|
98% |
7106
122.8 IPS |