User | Rohan_C |
Upload Date | November 03 2024 08:40 PM |
Views | 1 |
AI Information | |
---|---|
Framework | Core ML |
Backend | Neural Engine |
Device | Apple A16 Bionic |
System Information | |
---|---|
Operating System | iOS 18.1 |
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% |
1415
263.2 IPS |
|
Image Classification (HP)
|
100% |
10354
1.93 KIPS |
|
Image Classification (Q)
|
97% |
12233
2.28 KIPS |
|
Image Segmentation (SP)
|
100% |
1432
23.2 IPS |
|
Image Segmentation (HP)
|
100% |
13341
216.3 IPS |
|
Image Segmentation (Q)
|
99% |
17285
280.2 IPS |
|
Pose Estimation (SP)
|
100% |
6703
7.82 IPS |
|
Pose Estimation (HP)
|
100% |
95919
111.9 IPS |
|
Pose Estimation (Q)
|
95% |
101289
118.7 IPS |
|
Object Detection (SP)
|
100% |
1565
124.1 IPS |
|
Object Detection (HP)
|
100% |
12844
1.02 KIPS |
|
Object Detection (Q)
|
91% |
14874
1.19 KIPS |
|
Face Detection (SP)
|
100% |
3063
36.4 IPS |
|
Face Detection (HP)
|
100% |
29570
351.4 IPS |
|
Face Detection (Q)
|
100% |
38823
461.3 IPS |
|
Depth Estimation (SP)
|
100% |
6155
47.4 IPS |
|
Depth Estimation (HP)
|
99% |
75422
581.1 IPS |
|
Depth Estimation (Q)
|
85% |
94398
738.0 IPS |
|
Style Transfer (SP)
|
100% |
18701
24.0 IPS |
|
Style Transfer (HP)
|
100% |
164390
211.3 IPS |
|
Style Transfer (Q)
|
96% |
170931
220.6 IPS |
|
Image Super-Resolution (SP)
|
100% |
4134
152.6 IPS |
|
Image Super-Resolution (HP)
|
100% |
31361
1.16 KIPS |
|
Image Super-Resolution (Q)
|
99% |
36343
1.34 KIPS |
|
Text Classification (SP)
|
100% |
2598
3.47 KIPS |
|
Text Classification (HP)
|
100% |
2150
2.87 KIPS |
|
Text Classification (Q)
|
93% |
2025
2.72 KIPS |
|
Machine Translation (SP)
|
100% |
3421
58.9 IPS |
|
Machine Translation (HP)
|
100% |
5566
95.9 IPS |
|
Machine Translation (Q)
|
98% |
5914
102.2 IPS |