Upload Date | November 19 2024 08:34 PM |
Views | 1 |
AI Information | |
---|---|
Framework | Core ML |
Backend | Neural Engine |
Device | Apple A17 Pro |
System Information | |
---|---|
Operating System | iOS 18.1.1 |
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% |
1704
316.9 IPS |
|
Image Classification (HP)
|
100% |
11082
2.06 KIPS |
|
Image Classification (Q)
|
97% |
15379
2.87 KIPS |
|
Image Segmentation (SP)
|
100% |
1664
27.0 IPS |
|
Image Segmentation (HP)
|
100% |
15650
253.7 IPS |
|
Image Segmentation (Q)
|
99% |
20955
339.7 IPS |
|
Pose Estimation (SP)
|
100% |
7719
9.01 IPS |
|
Pose Estimation (HP)
|
100% |
105828
123.5 IPS |
|
Pose Estimation (Q)
|
95% |
204595
239.8 IPS |
|
Object Detection (SP)
|
100% |
1774
140.7 IPS |
|
Object Detection (HP)
|
100% |
13716
1.09 KIPS |
|
Object Detection (Q)
|
91% |
19026
1.52 KIPS |
|
Face Detection (SP)
|
100% |
3167
37.6 IPS |
|
Face Detection (HP)
|
100% |
34594
411.0 IPS |
|
Face Detection (Q)
|
100% |
51387
610.6 IPS |
|
Depth Estimation (SP)
|
100% |
7023
54.1 IPS |
|
Depth Estimation (HP)
|
99% |
78323
603.4 IPS |
|
Depth Estimation (Q)
|
85% |
128813
1.01 KIPS |
|
Style Transfer (SP)
|
100% |
20628
26.5 IPS |
|
Style Transfer (HP)
|
100% |
205038
263.6 IPS |
|
Style Transfer (Q)
|
96% |
251692
324.8 IPS |
|
Image Super-Resolution (SP)
|
100% |
4859
179.4 IPS |
|
Image Super-Resolution (HP)
|
100% |
34519
1.27 KIPS |
|
Image Super-Resolution (Q)
|
99% |
59007
2.18 KIPS |
|
Text Classification (SP)
|
100% |
3187
4.25 KIPS |
|
Text Classification (HP)
|
100% |
3325
4.44 KIPS |
|
Text Classification (Q)
|
93% |
3211
4.31 KIPS |
|
Machine Translation (SP)
|
100% |
3125
53.8 IPS |
|
Machine Translation (HP)
|
100% |
6193
106.7 IPS |
|
Machine Translation (Q)
|
98% |
7861
135.8 IPS |