User | pakitt |
Upload Date | December 13 2024 10:32 PM |
Views | 2 |
AI Information | |
---|---|
Framework | Core ML |
Backend | Neural Engine |
Device | Apple A17 Pro |
System Information | |
---|---|
Operating System | iOS 18.2 |
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% |
1632
303.6 IPS |
|
Image Classification (HP)
|
100% |
10798
2.01 KIPS |
|
Image Classification (Q)
|
97% |
15377
2.87 KIPS |
|
Image Segmentation (SP)
|
100% |
1586
25.7 IPS |
|
Image Segmentation (HP)
|
100% |
15583
252.6 IPS |
|
Image Segmentation (Q)
|
99% |
20877
338.4 IPS |
|
Pose Estimation (SP)
|
100% |
7407
8.64 IPS |
|
Pose Estimation (HP)
|
100% |
103551
120.8 IPS |
|
Pose Estimation (Q)
|
95% |
203159
238.1 IPS |
|
Object Detection (SP)
|
100% |
1762
139.8 IPS |
|
Object Detection (HP)
|
100% |
13849
1.10 KIPS |
|
Object Detection (Q)
|
91% |
19070
1.52 KIPS |
|
Face Detection (SP)
|
100% |
3135
37.2 IPS |
|
Face Detection (HP)
|
100% |
35443
421.1 IPS |
|
Face Detection (Q)
|
100% |
50768
603.2 IPS |
|
Depth Estimation (SP)
|
100% |
6777
52.2 IPS |
|
Depth Estimation (HP)
|
99% |
78174
602.3 IPS |
|
Depth Estimation (Q)
|
85% |
125467
981.0 IPS |
|
Style Transfer (SP)
|
100% |
20282
26.1 IPS |
|
Style Transfer (HP)
|
100% |
201742
259.3 IPS |
|
Style Transfer (Q)
|
96% |
245040
316.2 IPS |
|
Image Super-Resolution (SP)
|
100% |
4735
174.8 IPS |
|
Image Super-Resolution (HP)
|
100% |
33662
1.24 KIPS |
|
Image Super-Resolution (Q)
|
99% |
59298
2.19 KIPS |
|
Text Classification (SP)
|
100% |
3196
4.27 KIPS |
|
Text Classification (HP)
|
100% |
3014
4.02 KIPS |
|
Text Classification (Q)
|
93% |
3172
4.26 KIPS |
|
Machine Translation (SP)
|
100% |
3120
53.7 IPS |
|
Machine Translation (HP)
|
100% |
6214
107.0 IPS |
|
Machine Translation (Q)
|
98% |
7226
124.9 IPS |