User | Phizzle |
Upload Date | August 21 2024 05:03 AM |
Views | 12 |
AI Information | |
---|---|
Framework | Core ML |
Backend | Neural Engine |
Device | Apple A17 Pro |
System Information | |
---|---|
Operating System | iOS 17.6.1 |
Model | iPhone 15 Pro Max |
Model ID | iPhone16,2 |
Motherboard | D84AP |
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 | 7.44 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
1441
268.1 IPS |
|
Image Classification (HP)
|
100% |
6212
1.16 KIPS |
|
Image Classification (Q)
|
99% |
6746
1.26 KIPS |
|
Image Segmentation (SP)
|
100% |
830
13.4 IPS |
|
Image Segmentation (HP)
|
100% |
5189
84.1 IPS |
|
Image Segmentation (Q)
|
100% |
5195
84.2 IPS |
|
Pose Estimation (SP)
|
100% |
7876
9.19 IPS |
|
Pose Estimation (HP)
|
100% |
87478
102.1 IPS |
|
Pose Estimation (Q)
|
94% |
135011
158.4 IPS |
|
Object Detection (SP)
|
100% |
1467
116.4 IPS |
|
Object Detection (HP)
|
100% |
8270
656.0 IPS |
|
Object Detection (Q)
|
93% |
10111
806.7 IPS |
|
Face Detection (SP)
|
100% |
2214
26.3 IPS |
|
Face Detection (HP)
|
100% |
11168
132.7 IPS |
|
Face Detection (Q)
|
100% |
12977
154.2 IPS |
|
Depth Estimation (SP)
|
100% |
4460
34.4 IPS |
|
Depth Estimation (HP)
|
99% |
43010
331.4 IPS |
|
Depth Estimation (Q)
|
97% |
48003
371.2 IPS |
|
Style Transfer (SP)
|
100% |
12161
15.6 IPS |
|
Style Transfer (HP)
|
100% |
128000
164.5 IPS |
|
Style Transfer (Q)
|
100% |
128320
165.0 IPS |
|
Image Super-Resolution (SP)
|
100% |
3990
147.3 IPS |
|
Image Super-Resolution (HP)
|
100% |
18358
677.9 IPS |
|
Image Super-Resolution (Q)
|
98% |
25968
962.1 IPS |
|
Text Classification (SP)
|
100% |
1806
2.41 KIPS |
|
Text Classification (HP)
|
71% |
5294
7.61 KIPS |
|
Text Classification (Q)
|
69% |
3714
5.44 KIPS |
|
Machine Translation (SP)
|
100% |
1891
32.6 IPS |
|
Machine Translation (HP)
|
100% |
2515
43.3 IPS |
|
Machine Translation (Q)
|
98% |
2460
42.5 IPS |