User | Rohan_C |
Upload Date | September 16 2024 06:29 PM |
Views | 3 |
AI Information | |
---|---|
Framework | Core ML |
Backend | Neural Engine |
Device | Apple A16 Bionic |
System Information | |
---|---|
Operating System | iOS 17.6.1 |
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 | 5.48 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
1221
227.1 IPS |
|
Image Classification (HP)
|
100% |
5875
1.09 KIPS |
|
Image Classification (Q)
|
97% |
6168
1.15 KIPS |
|
Image Segmentation (SP)
|
100% |
760
12.3 IPS |
|
Image Segmentation (HP)
|
100% |
5049
81.8 IPS |
|
Image Segmentation (Q)
|
99% |
9353
151.6 IPS |
|
Pose Estimation (SP)
|
100% |
6430
7.50 IPS |
|
Pose Estimation (HP)
|
100% |
80569
94.0 IPS |
|
Pose Estimation (Q)
|
95% |
85404
100.1 IPS |
|
Object Detection (SP)
|
100% |
1336
106.0 IPS |
|
Object Detection (HP)
|
100% |
7604
603.1 IPS |
|
Object Detection (Q)
|
93% |
8255
658.7 IPS |
|
Face Detection (SP)
|
100% |
2236
26.6 IPS |
|
Face Detection (HP)
|
100% |
10630
126.3 IPS |
|
Face Detection (Q)
|
100% |
12928
153.6 IPS |
|
Depth Estimation (SP)
|
100% |
4184
32.2 IPS |
|
Depth Estimation (HP)
|
99% |
40856
314.8 IPS |
|
Depth Estimation (Q)
|
85% |
51221
400.5 IPS |
|
Style Transfer (SP)
|
100% |
11349
14.6 IPS |
|
Style Transfer (HP)
|
100% |
120735
155.2 IPS |
|
Style Transfer (Q)
|
96% |
113574
146.6 IPS |
|
Image Super-Resolution (SP)
|
100% |
3338
123.3 IPS |
|
Image Super-Resolution (HP)
|
100% |
16758
618.8 IPS |
|
Image Super-Resolution (Q)
|
99% |
21610
797.9 IPS |
|
Text Classification (SP)
|
100% |
1397
1.86 KIPS |
|
Text Classification (HP)
|
100% |
3118
4.16 KIPS |
|
Text Classification (Q)
|
93% |
3027
4.06 KIPS |
|
Machine Translation (SP)
|
100% |
1622
27.9 IPS |
|
Machine Translation (HP)
|
100% |
2414
41.6 IPS |
|
Machine Translation (Q)
|
98% |
2400
41.5 IPS |