User | dcjm |
Upload Date | August 31 2024 10:03 AM |
Views | 5 |
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% |
1451
269.9 IPS |
|
Image Classification (HP)
|
100% |
9470
1.76 KIPS |
|
Image Classification (Q)
|
99% |
9996
1.86 KIPS |
|
Image Segmentation (SP)
|
100% |
1236
20.0 IPS |
|
Image Segmentation (HP)
|
100% |
10762
174.5 IPS |
|
Image Segmentation (Q)
|
100% |
10573
171.4 IPS |
|
Pose Estimation (SP)
|
100% |
6823
7.96 IPS |
|
Pose Estimation (HP)
|
100% |
98439
114.9 IPS |
|
Pose Estimation (Q)
|
94% |
199233
233.7 IPS |
|
Object Detection (SP)
|
100% |
1665
132.0 IPS |
|
Object Detection (HP)
|
100% |
12941
1.03 KIPS |
|
Object Detection (Q)
|
91% |
18575
1.48 KIPS |
|
Face Detection (SP)
|
100% |
2853
33.9 IPS |
|
Face Detection (HP)
|
100% |
21838
259.5 IPS |
|
Face Detection (Q)
|
100% |
34287
407.4 IPS |
|
Depth Estimation (SP)
|
100% |
6416
49.4 IPS |
|
Depth Estimation (HP)
|
99% |
63505
489.3 IPS |
|
Depth Estimation (Q)
|
97% |
73801
570.6 IPS |
|
Style Transfer (SP)
|
100% |
20082
25.8 IPS |
|
Style Transfer (HP)
|
100% |
138177
177.6 IPS |
|
Style Transfer (Q)
|
100% |
138840
178.5 IPS |
|
Image Super-Resolution (SP)
|
100% |
4595
169.7 IPS |
|
Image Super-Resolution (HP)
|
100% |
33733
1.25 KIPS |
|
Image Super-Resolution (Q)
|
98% |
56805
2.10 KIPS |
|
Text Classification (SP)
|
100% |
3157
4.21 KIPS |
|
Text Classification (HP)
|
100% |
2624
3.50 KIPS |
|
Text Classification (Q)
|
93% |
2050
2.75 KIPS |
|
Machine Translation (SP)
|
100% |
3271
56.3 IPS |
|
Machine Translation (HP)
|
100% |
5900
101.6 IPS |
|
Machine Translation (Q)
|
98% |
7298
126.1 IPS |