Upload Date | September 17 2024 02:22 PM |
Views | 2 |
AI Information | |
---|---|
Framework | Core ML |
Backend | Neural Engine |
Device | Apple A17 Pro |
System Information | |
---|---|
Operating System | iOS 18.0 |
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% |
1699
315.9 IPS |
|
Image Classification (HP)
|
100% |
11096
2.06 KIPS |
|
Image Classification (Q)
|
97% |
15462
2.89 KIPS |
|
Image Segmentation (SP)
|
100% |
1612
26.1 IPS |
|
Image Segmentation (HP)
|
100% |
13023
211.1 IPS |
|
Image Segmentation (Q)
|
99% |
16003
259.4 IPS |
|
Pose Estimation (SP)
|
100% |
7837
9.14 IPS |
|
Pose Estimation (HP)
|
100% |
105265
122.8 IPS |
|
Pose Estimation (Q)
|
95% |
203304
238.3 IPS |
|
Object Detection (SP)
|
100% |
1770
140.4 IPS |
|
Object Detection (HP)
|
100% |
13625
1.08 KIPS |
|
Object Detection (Q)
|
91% |
19027
1.52 KIPS |
|
Face Detection (SP)
|
100% |
3149
37.4 IPS |
|
Face Detection (HP)
|
100% |
33559
398.8 IPS |
|
Face Detection (Q)
|
100% |
48960
581.8 IPS |
|
Depth Estimation (SP)
|
100% |
6996
53.9 IPS |
|
Depth Estimation (HP)
|
99% |
78223
602.7 IPS |
|
Depth Estimation (Q)
|
85% |
128447
1.00 KIPS |
|
Style Transfer (SP)
|
100% |
20489
26.3 IPS |
|
Style Transfer (HP)
|
100% |
202571
260.4 IPS |
|
Style Transfer (Q)
|
96% |
246920
318.6 IPS |
|
Image Super-Resolution (SP)
|
100% |
4815
177.8 IPS |
|
Image Super-Resolution (HP)
|
100% |
35367
1.31 KIPS |
|
Image Super-Resolution (Q)
|
99% |
55998
2.07 KIPS |
|
Text Classification (SP)
|
100% |
3190
4.26 KIPS |
|
Text Classification (HP)
|
100% |
3081
4.11 KIPS |
|
Text Classification (Q)
|
93% |
3228
4.33 KIPS |
|
Machine Translation (SP)
|
100% |
3125
53.8 IPS |
|
Machine Translation (HP)
|
100% |
6143
105.8 IPS |
|
Machine Translation (Q)
|
98% |
7391
127.7 IPS |