User | buliaoyin |
Upload Date | September 27 2024 07:40 AM |
Views | 4 |
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% |
1485
276.2 IPS |
|
Image Classification (HP)
|
100% |
6232
1.16 KIPS |
|
Image Classification (Q)
|
97% |
7560
1.41 KIPS |
|
Image Segmentation (SP)
|
100% |
822
13.3 IPS |
|
Image Segmentation (HP)
|
100% |
5232
84.8 IPS |
|
Image Segmentation (Q)
|
99% |
9989
161.9 IPS |
|
Pose Estimation (SP)
|
100% |
7735
9.03 IPS |
|
Pose Estimation (HP)
|
100% |
87961
102.6 IPS |
|
Pose Estimation (Q)
|
95% |
152461
178.7 IPS |
|
Object Detection (SP)
|
100% |
1499
118.9 IPS |
|
Object Detection (HP)
|
100% |
8167
647.8 IPS |
|
Object Detection (Q)
|
93% |
9994
797.5 IPS |
|
Face Detection (SP)
|
100% |
2319
27.6 IPS |
|
Face Detection (HP)
|
100% |
11176
132.8 IPS |
|
Face Detection (Q)
|
100% |
13289
157.9 IPS |
|
Depth Estimation (SP)
|
100% |
4830
37.2 IPS |
|
Depth Estimation (HP)
|
99% |
43116
332.2 IPS |
|
Depth Estimation (Q)
|
85% |
58540
457.7 IPS |
|
Style Transfer (SP)
|
100% |
12404
15.9 IPS |
|
Style Transfer (HP)
|
100% |
128087
164.7 IPS |
|
Style Transfer (Q)
|
96% |
138292
178.5 IPS |
|
Image Super-Resolution (SP)
|
100% |
4065
150.1 IPS |
|
Image Super-Resolution (HP)
|
100% |
18208
672.3 IPS |
|
Image Super-Resolution (Q)
|
99% |
26068
962.6 IPS |
|
Text Classification (SP)
|
100% |
1820
2.43 KIPS |
|
Text Classification (HP)
|
71% |
4064
5.84 KIPS |
|
Text Classification (Q)
|
69% |
4061
5.95 KIPS |
|
Machine Translation (SP)
|
100% |
1937
33.4 IPS |
|
Machine Translation (HP)
|
100% |
2590
44.6 IPS |
|
Machine Translation (Q)
|
98% |
2609
45.1 IPS |