User | albertoyan |
Upload Date | August 16 2024 02:57 AM |
Views | 4 |
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% |
1229
228.6 IPS |
|
Image Classification (HP)
|
100% |
5807
1.08 KIPS |
|
Image Classification (Q)
|
99% |
6176
1.15 KIPS |
|
Image Segmentation (SP)
|
100% |
747
12.1 IPS |
|
Image Segmentation (HP)
|
100% |
4976
80.7 IPS |
|
Image Segmentation (Q)
|
100% |
5041
81.7 IPS |
|
Pose Estimation (SP)
|
100% |
6482
7.56 IPS |
|
Pose Estimation (HP)
|
100% |
79118
92.3 IPS |
|
Pose Estimation (Q)
|
94% |
84178
98.7 IPS |
|
Object Detection (SP)
|
100% |
1321
104.8 IPS |
|
Object Detection (HP)
|
100% |
7375
585.0 IPS |
|
Object Detection (Q)
|
93% |
8354
666.6 IPS |
|
Face Detection (SP)
|
100% |
2203
26.2 IPS |
|
Face Detection (HP)
|
100% |
10840
128.8 IPS |
|
Face Detection (Q)
|
100% |
12915
153.5 IPS |
|
Depth Estimation (SP)
|
100% |
4166
32.1 IPS |
|
Depth Estimation (HP)
|
99% |
41149
317.0 IPS |
|
Depth Estimation (Q)
|
97% |
46918
362.8 IPS |
|
Style Transfer (SP)
|
100% |
11264
14.5 IPS |
|
Style Transfer (HP)
|
100% |
120540
155.0 IPS |
|
Style Transfer (Q)
|
100% |
122139
157.0 IPS |
|
Image Super-Resolution (SP)
|
100% |
3287
121.4 IPS |
|
Image Super-Resolution (HP)
|
100% |
16111
594.9 IPS |
|
Image Super-Resolution (Q)
|
98% |
21289
788.7 IPS |
|
Text Classification (SP)
|
100% |
1373
1.83 KIPS |
|
Text Classification (HP)
|
100% |
3409
4.55 KIPS |
|
Text Classification (Q)
|
93% |
3578
4.80 KIPS |
|
Machine Translation (SP)
|
100% |
1631
28.1 IPS |
|
Machine Translation (HP)
|
100% |
2397
41.3 IPS |
|
Machine Translation (Q)
|
98% |
2380
41.1 IPS |