User | mitgeek |
Upload Date | September 10 2024 12:22 PM |
Views | 5 |
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% |
1409
262.0 IPS |
|
Image Classification (HP)
|
100% |
6085
1.13 KIPS |
|
Image Classification (Q)
|
97% |
7693
1.44 KIPS |
|
Image Segmentation (SP)
|
100% |
799
13.0 IPS |
|
Image Segmentation (HP)
|
100% |
5195
84.2 IPS |
|
Image Segmentation (Q)
|
99% |
10240
166.0 IPS |
|
Pose Estimation (SP)
|
100% |
7098
8.28 IPS |
|
Pose Estimation (HP)
|
100% |
88179
102.9 IPS |
|
Pose Estimation (Q)
|
95% |
152592
178.8 IPS |
|
Object Detection (SP)
|
100% |
1438
114.1 IPS |
|
Object Detection (HP)
|
100% |
8066
639.8 IPS |
|
Object Detection (Q)
|
93% |
9737
776.9 IPS |
|
Face Detection (SP)
|
100% |
2159
25.7 IPS |
|
Face Detection (HP)
|
100% |
11256
133.7 IPS |
|
Face Detection (Q)
|
100% |
13390
159.1 IPS |
|
Depth Estimation (SP)
|
100% |
4557
35.1 IPS |
|
Depth Estimation (HP)
|
99% |
42154
324.8 IPS |
|
Depth Estimation (Q)
|
85% |
61818
483.3 IPS |
|
Style Transfer (SP)
|
100% |
12007
15.4 IPS |
|
Style Transfer (HP)
|
100% |
127581
164.0 IPS |
|
Style Transfer (Q)
|
96% |
137432
177.3 IPS |
|
Image Super-Resolution (SP)
|
100% |
3924
144.9 IPS |
|
Image Super-Resolution (HP)
|
100% |
18334
677.0 IPS |
|
Image Super-Resolution (Q)
|
99% |
26902
993.4 IPS |
|
Text Classification (SP)
|
100% |
1811
2.42 KIPS |
|
Text Classification (HP)
|
71% |
4741
6.82 KIPS |
|
Text Classification (Q)
|
69% |
4696
6.88 KIPS |
|
Machine Translation (SP)
|
100% |
1893
32.6 IPS |
|
Machine Translation (HP)
|
100% |
2538
43.7 IPS |
|
Machine Translation (Q)
|
98% |
2503
43.3 IPS |