User | sichunlam |
Upload Date | August 15 2024 08:49 PM |
Views | 3 |
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% |
1335
248.3 IPS |
|
Image Classification (HP)
|
100% |
6255
1.16 KIPS |
|
Image Classification (Q)
|
99% |
7255
1.35 KIPS |
|
Image Segmentation (SP)
|
100% |
761
12.3 IPS |
|
Image Segmentation (HP)
|
100% |
5213
84.5 IPS |
|
Image Segmentation (Q)
|
100% |
5191
84.1 IPS |
|
Pose Estimation (SP)
|
100% |
7754
9.05 IPS |
|
Pose Estimation (HP)
|
100% |
88817
103.6 IPS |
|
Pose Estimation (Q)
|
94% |
150037
176.0 IPS |
|
Object Detection (SP)
|
100% |
1435
113.8 IPS |
|
Object Detection (HP)
|
100% |
8223
652.2 IPS |
|
Object Detection (Q)
|
93% |
9315
743.3 IPS |
|
Face Detection (SP)
|
100% |
2196
26.1 IPS |
|
Face Detection (HP)
|
100% |
11206
133.1 IPS |
|
Face Detection (Q)
|
100% |
13211
157.0 IPS |
|
Depth Estimation (SP)
|
100% |
4798
37.0 IPS |
|
Depth Estimation (HP)
|
99% |
42239
325.4 IPS |
|
Depth Estimation (Q)
|
97% |
48403
374.3 IPS |
|
Style Transfer (SP)
|
100% |
12253
15.8 IPS |
|
Style Transfer (HP)
|
100% |
128057
164.6 IPS |
|
Style Transfer (Q)
|
100% |
128810
165.6 IPS |
|
Image Super-Resolution (SP)
|
100% |
3902
144.1 IPS |
|
Image Super-Resolution (HP)
|
100% |
18320
676.5 IPS |
|
Image Super-Resolution (Q)
|
98% |
26500
981.8 IPS |
|
Text Classification (SP)
|
100% |
1817
2.42 KIPS |
|
Text Classification (HP)
|
71% |
4517
6.50 KIPS |
|
Text Classification (Q)
|
69% |
4057
5.95 KIPS |
|
Machine Translation (SP)
|
100% |
1896
32.7 IPS |
|
Machine Translation (HP)
|
100% |
2538
43.7 IPS |
|
Machine Translation (Q)
|
98% |
2534
43.8 IPS |