User | mitgeek |
Upload Date | September 10 2024 12:19 PM |
Views | 4 |
AI Information | |
---|---|
Framework | Core ML |
Backend | GPU |
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% |
1788
332.4 IPS |
|
Image Classification (HP)
|
100% |
1820
338.4 IPS |
|
Image Classification (Q)
|
97% |
1880
350.8 IPS |
|
Image Segmentation (SP)
|
100% |
2932
47.5 IPS |
|
Image Segmentation (HP)
|
100% |
3994
64.8 IPS |
|
Image Segmentation (Q)
|
99% |
4108
66.6 IPS |
|
Pose Estimation (SP)
|
100% |
14922
17.4 IPS |
|
Pose Estimation (HP)
|
100% |
15946
18.6 IPS |
|
Pose Estimation (Q)
|
97% |
14719
17.2 IPS |
|
Object Detection (SP)
|
100% |
2386
189.2 IPS |
|
Object Detection (HP)
|
100% |
2972
235.7 IPS |
|
Object Detection (Q)
|
92% |
2409
192.3 IPS |
|
Face Detection (SP)
|
100% |
6453
76.7 IPS |
|
Face Detection (HP)
|
100% |
8621
102.4 IPS |
|
Face Detection (Q)
|
100% |
6063
72.0 IPS |
|
Depth Estimation (SP)
|
100% |
11471
88.4 IPS |
|
Depth Estimation (HP)
|
99% |
13209
101.8 IPS |
|
Depth Estimation (Q)
|
1% |
0
83.5 IPS |
|
Style Transfer (SP)
|
100% |
29824
38.3 IPS |
|
Style Transfer (HP)
|
100% |
35180
45.2 IPS |
|
Style Transfer (Q)
|
96% |
33000
42.6 IPS |
|
Image Super-Resolution (SP)
|
100% |
6153
227.2 IPS |
|
Image Super-Resolution (HP)
|
100% |
6611
244.1 IPS |
|
Image Super-Resolution (Q)
|
99% |
5320
196.4 IPS |
|
Text Classification (SP)
|
100% |
501
668.9 IPS |
|
Text Classification (HP)
|
100% |
508
677.7 IPS |
|
Text Classification (Q)
|
93% |
309
414.2 IPS |
|
Machine Translation (SP)
|
100% |
1103
19.0 IPS |
|
Machine Translation (HP)
|
100% |
1243
21.4 IPS |
|
Machine Translation (Q)
|
98% |
1582
27.3 IPS |