Upload Date | September 19 2024 09:44 AM |
Views | 1 |
AI Information | |
---|---|
Framework | Core ML |
Backend | Neural Engine |
Device | Apple A17 Pro |
System Information | |
---|---|
Operating System | iOS 18.1 |
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 | 7.48 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
1506
280.0 IPS |
|
Image Classification (HP)
|
100% |
6172
1.15 KIPS |
|
Image Classification (Q)
|
97% |
16720
3.12 KIPS |
|
Image Segmentation (SP)
|
100% |
1480
24.0 IPS |
|
Image Segmentation (HP)
|
100% |
13363
216.6 IPS |
|
Image Segmentation (Q)
|
99% |
16127
261.4 IPS |
|
Pose Estimation (SP)
|
100% |
6471
7.55 IPS |
|
Pose Estimation (HP)
|
100% |
98972
115.5 IPS |
|
Pose Estimation (Q)
|
95% |
197021
230.9 IPS |
|
Object Detection (SP)
|
100% |
1558
123.6 IPS |
|
Object Detection (HP)
|
100% |
13660
1.08 KIPS |
|
Object Detection (Q)
|
91% |
16784
1.34 KIPS |
|
Face Detection (SP)
|
100% |
2467
29.3 IPS |
|
Face Detection (HP)
|
100% |
27127
322.3 IPS |
|
Face Detection (Q)
|
100% |
49555
588.8 IPS |
|
Depth Estimation (SP)
|
100% |
5862
45.2 IPS |
|
Depth Estimation (HP)
|
99% |
78140
602.0 IPS |
|
Depth Estimation (Q)
|
85% |
126266
987.2 IPS |
|
Style Transfer (SP)
|
100% |
18727
24.1 IPS |
|
Style Transfer (HP)
|
100% |
201013
258.4 IPS |
|
Style Transfer (Q)
|
96% |
250753
323.6 IPS |
|
Image Super-Resolution (SP)
|
100% |
4319
159.5 IPS |
|
Image Super-Resolution (HP)
|
100% |
34367
1.27 KIPS |
|
Image Super-Resolution (Q)
|
99% |
61841
2.28 KIPS |
|
Text Classification (SP)
|
100% |
3098
4.13 KIPS |
|
Text Classification (HP)
|
100% |
3119
4.16 KIPS |
|
Text Classification (Q)
|
93% |
3576
4.80 KIPS |
|
Machine Translation (SP)
|
100% |
3020
52.0 IPS |
|
Machine Translation (HP)
|
100% |
6313
108.7 IPS |
|
Machine Translation (Q)
|
98% |
8408
145.3 IPS |