User | mattmcq |
Upload Date | August 16 2024 01:05 AM |
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% |
1535
285.4 IPS |
|
Image Classification (HP)
|
100% |
2083
387.3 IPS |
|
Image Classification (Q)
|
99% |
2065
385.2 IPS |
|
Image Segmentation (SP)
|
100% |
2935
47.6 IPS |
|
Image Segmentation (HP)
|
100% |
3891
63.1 IPS |
|
Image Segmentation (Q)
|
100% |
3907
63.3 IPS |
|
Pose Estimation (SP)
|
100% |
15001
17.5 IPS |
|
Pose Estimation (HP)
|
100% |
15918
18.6 IPS |
|
Pose Estimation (Q)
|
96% |
14680
17.2 IPS |
|
Object Detection (SP)
|
100% |
2426
192.4 IPS |
|
Object Detection (HP)
|
100% |
2731
216.6 IPS |
|
Object Detection (Q)
|
92% |
2217
177.0 IPS |
|
Face Detection (SP)
|
100% |
6389
75.9 IPS |
|
Face Detection (HP)
|
100% |
8456
100.5 IPS |
|
Face Detection (Q)
|
100% |
6125
72.8 IPS |
|
Depth Estimation (SP)
|
100% |
11464
88.3 IPS |
|
Depth Estimation (HP)
|
99% |
13237
102.0 IPS |
|
Depth Estimation (Q)
|
97% |
13247
102.4 IPS |
|
Style Transfer (SP)
|
100% |
29565
38.0 IPS |
|
Style Transfer (HP)
|
100% |
35408
45.5 IPS |
|
Style Transfer (Q)
|
100% |
34281
44.1 IPS |
|
Image Super-Resolution (SP)
|
100% |
6252
230.9 IPS |
|
Image Super-Resolution (HP)
|
100% |
6602
243.8 IPS |
|
Image Super-Resolution (Q)
|
98% |
5263
195.0 IPS |
|
Text Classification (SP)
|
100% |
496
662.6 IPS |
|
Text Classification (HP)
|
100% |
508
677.8 IPS |
|
Text Classification (Q)
|
93% |
334
448.2 IPS |
|
Machine Translation (SP)
|
100% |
1164
20.1 IPS |
|
Machine Translation (HP)
|
100% |
1105
19.0 IPS |
|
Machine Translation (Q)
|
98% |
1605
27.7 IPS |