Upload Date | September 17 2024 11:31 PM |
Views | 2 |
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% |
1682
312.9 IPS |
|
Image Classification (HP)
|
100% |
10948
2.04 KIPS |
|
Image Classification (Q)
|
97% |
14988
2.80 KIPS |
|
Image Segmentation (SP)
|
100% |
1583
25.7 IPS |
|
Image Segmentation (HP)
|
100% |
12854
208.4 IPS |
|
Image Segmentation (Q)
|
99% |
15996
259.3 IPS |
|
Pose Estimation (SP)
|
100% |
7466
8.71 IPS |
|
Pose Estimation (HP)
|
100% |
104319
121.7 IPS |
|
Pose Estimation (Q)
|
95% |
203353
238.3 IPS |
|
Object Detection (SP)
|
100% |
1757
139.4 IPS |
|
Object Detection (HP)
|
100% |
13672
1.08 KIPS |
|
Object Detection (Q)
|
91% |
19075
1.52 KIPS |
|
Face Detection (SP)
|
100% |
3118
37.1 IPS |
|
Face Detection (HP)
|
100% |
33584
399.1 IPS |
|
Face Detection (Q)
|
100% |
48831
580.2 IPS |
|
Depth Estimation (SP)
|
100% |
6914
53.3 IPS |
|
Depth Estimation (HP)
|
99% |
78359
603.7 IPS |
|
Depth Estimation (Q)
|
85% |
128346
1.00 KIPS |
|
Style Transfer (SP)
|
100% |
20756
26.7 IPS |
|
Style Transfer (HP)
|
100% |
138713
178.3 IPS |
|
Style Transfer (Q)
|
96% |
164988
212.9 IPS |
|
Image Super-Resolution (SP)
|
100% |
4838
178.6 IPS |
|
Image Super-Resolution (HP)
|
100% |
34184
1.26 KIPS |
|
Image Super-Resolution (Q)
|
99% |
58128
2.15 KIPS |
|
Text Classification (SP)
|
100% |
3175
4.24 KIPS |
|
Text Classification (HP)
|
100% |
3058
4.08 KIPS |
|
Text Classification (Q)
|
93% |
2417
3.24 KIPS |
|
Machine Translation (SP)
|
100% |
3232
55.7 IPS |
|
Machine Translation (HP)
|
100% |
6095
105.0 IPS |
|
Machine Translation (Q)
|
98% |
7374
127.4 IPS |