User | RDNewman |
Upload Date | January 05 2025 03:04 AM |
Views | 2 |
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% |
1399
260.2 IPS |
|
Image Classification (HP)
|
100% |
10121
1.88 KIPS |
|
Image Classification (Q)
|
97% |
13084
2.44 KIPS |
|
Image Segmentation (SP)
|
100% |
1438
23.3 IPS |
|
Image Segmentation (HP)
|
100% |
14142
229.3 IPS |
|
Image Segmentation (Q)
|
99% |
17811
288.7 IPS |
|
Pose Estimation (SP)
|
100% |
7002
8.17 IPS |
|
Pose Estimation (HP)
|
100% |
95912
111.9 IPS |
|
Pose Estimation (Q)
|
95% |
101212
118.6 IPS |
|
Object Detection (SP)
|
100% |
1571
124.6 IPS |
|
Object Detection (HP)
|
100% |
12937
1.03 KIPS |
|
Object Detection (Q)
|
91% |
14861
1.19 KIPS |
|
Face Detection (SP)
|
100% |
2955
35.1 IPS |
|
Face Detection (HP)
|
100% |
29755
353.6 IPS |
|
Face Detection (Q)
|
100% |
39142
465.1 IPS |
|
Depth Estimation (SP)
|
100% |
6200
47.8 IPS |
|
Depth Estimation (HP)
|
99% |
74960
577.5 IPS |
|
Depth Estimation (Q)
|
85% |
95806
749.1 IPS |
|
Style Transfer (SP)
|
100% |
18731
24.1 IPS |
|
Style Transfer (HP)
|
100% |
165706
213.0 IPS |
|
Style Transfer (Q)
|
96% |
168324
217.2 IPS |
|
Image Super-Resolution (SP)
|
100% |
4171
154.0 IPS |
|
Image Super-Resolution (HP)
|
100% |
32887
1.21 KIPS |
|
Image Super-Resolution (Q)
|
99% |
37158
1.37 KIPS |
|
Text Classification (SP)
|
100% |
2661
3.55 KIPS |
|
Text Classification (HP)
|
100% |
1935
2.58 KIPS |
|
Text Classification (Q)
|
93% |
2247
3.02 KIPS |
|
Machine Translation (SP)
|
100% |
3459
59.6 IPS |
|
Machine Translation (HP)
|
100% |
5654
97.4 IPS |
|
Machine Translation (Q)
|
98% |
6153
106.3 IPS |