Upload Date | December 27 2024 06:54 AM |
Views | 1 |
AI Information | |
---|---|
Framework | Core ML |
Backend | Neural Engine |
Device | Apple A16 Bionic |
System Information | |
---|---|
Operating System | iOS 18.2 |
Model | iPhone 14 Pro Max |
Model ID | iPhone15,3 |
Motherboard | D74AP |
CPU Information | |
---|---|
Name | Apple A16 Bionic |
Topology | 1 Processor, 6 Cores |
Identifier | ARM |
Base Frequency | 3.46 GHz |
Cluster 1 | 2 Cores |
Cluster 2 | 4 Cores |
Memory Information | |
---|---|
Size | 5.51 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
1429
265.8 IPS |
|
Image Classification (HP)
|
100% |
10141
1.89 KIPS |
|
Image Classification (Q)
|
97% |
11858
2.21 KIPS |
|
Image Segmentation (SP)
|
100% |
1439
23.3 IPS |
|
Image Segmentation (HP)
|
100% |
13480
218.5 IPS |
|
Image Segmentation (Q)
|
99% |
17769
288.0 IPS |
|
Pose Estimation (SP)
|
100% |
6981
8.15 IPS |
|
Pose Estimation (HP)
|
100% |
94894
110.7 IPS |
|
Pose Estimation (Q)
|
95% |
101220
118.6 IPS |
|
Object Detection (SP)
|
100% |
1584
125.6 IPS |
|
Object Detection (HP)
|
100% |
12855
1.02 KIPS |
|
Object Detection (Q)
|
91% |
14856
1.19 KIPS |
|
Face Detection (SP)
|
100% |
3002
35.7 IPS |
|
Face Detection (HP)
|
100% |
29273
347.8 IPS |
|
Face Detection (Q)
|
100% |
38349
455.7 IPS |
|
Depth Estimation (SP)
|
100% |
6163
47.5 IPS |
|
Depth Estimation (HP)
|
99% |
75460
581.4 IPS |
|
Depth Estimation (Q)
|
85% |
95841
749.3 IPS |
|
Style Transfer (SP)
|
100% |
18676
24.0 IPS |
|
Style Transfer (HP)
|
100% |
163622
210.3 IPS |
|
Style Transfer (Q)
|
96% |
168781
217.8 IPS |
|
Image Super-Resolution (SP)
|
100% |
4167
153.9 IPS |
|
Image Super-Resolution (HP)
|
100% |
33481
1.24 KIPS |
|
Image Super-Resolution (Q)
|
99% |
36183
1.34 KIPS |
|
Text Classification (SP)
|
100% |
2620
3.50 KIPS |
|
Text Classification (HP)
|
100% |
1996
2.66 KIPS |
|
Text Classification (Q)
|
93% |
1690
2.27 KIPS |
|
Machine Translation (SP)
|
100% |
3449
59.4 IPS |
|
Machine Translation (HP)
|
100% |
6989
120.4 IPS |
|
Machine Translation (Q)
|
98% |
7646
132.1 IPS |