User | Streambox |
Upload Date | August 17 2024 06:30 PM |
Views | 4 |
AI Information | |
---|---|
Framework | Core ML |
Backend | Neural Engine |
Device | Apple A17 Pro |
System Information | |
---|---|
Operating System | iOS 17.5.1 |
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% |
1407
261.6 IPS |
|
Image Classification (HP)
|
100% |
6160
1.15 KIPS |
|
Image Classification (Q)
|
99% |
6930
1.29 KIPS |
|
Image Segmentation (SP)
|
100% |
803
13.0 IPS |
|
Image Segmentation (HP)
|
100% |
5210
84.5 IPS |
|
Image Segmentation (Q)
|
100% |
5164
83.7 IPS |
|
Pose Estimation (SP)
|
100% |
7510
8.76 IPS |
|
Pose Estimation (HP)
|
100% |
87558
102.2 IPS |
|
Pose Estimation (Q)
|
94% |
130529
153.1 IPS |
|
Object Detection (SP)
|
100% |
1477
117.2 IPS |
|
Object Detection (HP)
|
100% |
8180
648.8 IPS |
|
Object Detection (Q)
|
93% |
9981
796.4 IPS |
|
Face Detection (SP)
|
100% |
2188
26.0 IPS |
|
Face Detection (HP)
|
100% |
11080
131.6 IPS |
|
Face Detection (Q)
|
100% |
12882
153.1 IPS |
|
Depth Estimation (SP)
|
100% |
4639
35.7 IPS |
|
Depth Estimation (HP)
|
99% |
42893
330.5 IPS |
|
Depth Estimation (Q)
|
97% |
48293
373.4 IPS |
|
Style Transfer (SP)
|
100% |
12412
16.0 IPS |
|
Style Transfer (HP)
|
100% |
127887
164.4 IPS |
|
Style Transfer (Q)
|
100% |
128117
164.7 IPS |
|
Image Super-Resolution (SP)
|
100% |
4019
148.4 IPS |
|
Image Super-Resolution (HP)
|
100% |
18683
689.9 IPS |
|
Image Super-Resolution (Q)
|
98% |
25834
957.1 IPS |
|
Text Classification (SP)
|
100% |
1810
2.42 KIPS |
|
Text Classification (HP)
|
71% |
4308
6.19 KIPS |
|
Text Classification (Q)
|
69% |
4159
6.10 KIPS |
|
Machine Translation (SP)
|
100% |
1911
32.9 IPS |
|
Machine Translation (HP)
|
100% |
2537
43.7 IPS |
|
Machine Translation (Q)
|
98% |
2487
43.0 IPS |