User | Hogehoge |
Upload Date | August 24 2024 07:40 PM |
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 |
Model ID | iPhone15,2 |
Motherboard | D73AP |
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 | 5.50 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
1237
230.0 IPS |
|
Image Classification (HP)
|
100% |
5808
1.08 KIPS |
|
Image Classification (Q)
|
99% |
6024
1.12 KIPS |
|
Image Segmentation (SP)
|
100% |
744
12.1 IPS |
|
Image Segmentation (HP)
|
100% |
5036
81.6 IPS |
|
Image Segmentation (Q)
|
100% |
5063
82.1 IPS |
|
Pose Estimation (SP)
|
100% |
6246
7.29 IPS |
|
Pose Estimation (HP)
|
100% |
81191
94.7 IPS |
|
Pose Estimation (Q)
|
94% |
75283
88.3 IPS |
|
Object Detection (SP)
|
100% |
1289
102.2 IPS |
|
Object Detection (HP)
|
100% |
7451
591.0 IPS |
|
Object Detection (Q)
|
93% |
8273
660.1 IPS |
|
Face Detection (SP)
|
100% |
2151
25.6 IPS |
|
Face Detection (HP)
|
100% |
9075
107.8 IPS |
|
Face Detection (Q)
|
100% |
12145
144.3 IPS |
|
Depth Estimation (SP)
|
100% |
4026
31.0 IPS |
|
Depth Estimation (HP)
|
99% |
35396
272.7 IPS |
|
Depth Estimation (Q)
|
97% |
45238
349.8 IPS |
|
Style Transfer (SP)
|
100% |
10771
13.8 IPS |
|
Style Transfer (HP)
|
100% |
118007
151.7 IPS |
|
Style Transfer (Q)
|
100% |
123157
158.3 IPS |
|
Image Super-Resolution (SP)
|
100% |
3214
118.7 IPS |
|
Image Super-Resolution (HP)
|
100% |
15604
576.2 IPS |
|
Image Super-Resolution (Q)
|
98% |
20883
773.7 IPS |
|
Text Classification (SP)
|
100% |
1371
1.83 KIPS |
|
Text Classification (HP)
|
100% |
3590
4.79 KIPS |
|
Text Classification (Q)
|
93% |
3643
4.89 KIPS |
|
Machine Translation (SP)
|
100% |
1575
27.1 IPS |
|
Machine Translation (HP)
|
100% |
1751
30.2 IPS |
|
Machine Translation (Q)
|
98% |
1749
30.2 IPS |