User | Rohan_C |
Upload Date | December 12 2024 04:47 AM |
Views | 2 |
AI Information | |
---|---|
Framework | Core ML |
Backend | Neural Engine |
Device | Apple A16 Bionic |
System Information | |
---|---|
Operating System | iOS 18.1.1 |
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% |
1411
262.4 IPS |
|
Image Classification (HP)
|
100% |
10341
1.92 KIPS |
|
Image Classification (Q)
|
97% |
12455
2.32 KIPS |
|
Image Segmentation (SP)
|
100% |
1430
23.2 IPS |
|
Image Segmentation (HP)
|
100% |
13312
215.8 IPS |
|
Image Segmentation (Q)
|
99% |
18095
293.3 IPS |
|
Pose Estimation (SP)
|
100% |
7012
8.18 IPS |
|
Pose Estimation (HP)
|
100% |
99893
116.6 IPS |
|
Pose Estimation (Q)
|
95% |
101211
118.6 IPS |
|
Object Detection (SP)
|
100% |
1590
126.2 IPS |
|
Object Detection (HP)
|
100% |
12921
1.02 KIPS |
|
Object Detection (Q)
|
91% |
15294
1.22 KIPS |
|
Face Detection (SP)
|
100% |
2914
34.6 IPS |
|
Face Detection (HP)
|
100% |
30136
358.1 IPS |
|
Face Detection (Q)
|
100% |
39743
472.2 IPS |
|
Depth Estimation (SP)
|
100% |
6275
48.3 IPS |
|
Depth Estimation (HP)
|
99% |
74818
576.4 IPS |
|
Depth Estimation (Q)
|
85% |
96723
756.2 IPS |
|
Style Transfer (SP)
|
100% |
18937
24.3 IPS |
|
Style Transfer (HP)
|
100% |
167236
215.0 IPS |
|
Style Transfer (Q)
|
96% |
169472
218.7 IPS |
|
Image Super-Resolution (SP)
|
100% |
4257
157.2 IPS |
|
Image Super-Resolution (HP)
|
100% |
34206
1.26 KIPS |
|
Image Super-Resolution (Q)
|
99% |
37560
1.39 KIPS |
|
Text Classification (SP)
|
100% |
2664
3.56 KIPS |
|
Text Classification (HP)
|
100% |
2236
2.98 KIPS |
|
Text Classification (Q)
|
93% |
2390
3.21 KIPS |
|
Machine Translation (SP)
|
100% |
3400
58.6 IPS |
|
Machine Translation (HP)
|
100% |
5675
97.8 IPS |
|
Machine Translation (Q)
|
98% |
6143
106.2 IPS |