User | Hogehoge |
Upload Date | September 09 2024 07:42 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 |
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% |
1231
228.9 IPS |
|
Image Classification (HP)
|
100% |
5827
1.08 KIPS |
|
Image Classification (Q)
|
99% |
6075
1.13 KIPS |
|
Image Segmentation (SP)
|
100% |
746
12.1 IPS |
|
Image Segmentation (HP)
|
100% |
5071
82.2 IPS |
|
Image Segmentation (Q)
|
100% |
5103
82.7 IPS |
|
Pose Estimation (SP)
|
100% |
6251
7.29 IPS |
|
Pose Estimation (HP)
|
100% |
78568
91.7 IPS |
|
Pose Estimation (Q)
|
94% |
83889
98.4 IPS |
|
Object Detection (SP)
|
100% |
1325
105.1 IPS |
|
Object Detection (HP)
|
100% |
7685
609.6 IPS |
|
Object Detection (Q)
|
93% |
8222
656.0 IPS |
|
Face Detection (SP)
|
100% |
2256
26.8 IPS |
|
Face Detection (HP)
|
100% |
10854
129.0 IPS |
|
Face Detection (Q)
|
100% |
12995
154.4 IPS |
|
Depth Estimation (SP)
|
100% |
4167
32.1 IPS |
|
Depth Estimation (HP)
|
99% |
43107
332.1 IPS |
|
Depth Estimation (Q)
|
97% |
44188
341.7 IPS |
|
Style Transfer (SP)
|
100% |
11351
14.6 IPS |
|
Style Transfer (HP)
|
100% |
121235
155.8 IPS |
|
Style Transfer (Q)
|
100% |
121719
156.5 IPS |
|
Image Super-Resolution (SP)
|
100% |
3319
122.5 IPS |
|
Image Super-Resolution (HP)
|
100% |
16696
616.5 IPS |
|
Image Super-Resolution (Q)
|
98% |
20868
773.1 IPS |
|
Text Classification (SP)
|
100% |
1376
1.84 KIPS |
|
Text Classification (HP)
|
100% |
3475
4.64 KIPS |
|
Text Classification (Q)
|
93% |
3490
4.68 KIPS |
|
Machine Translation (SP)
|
100% |
1642
28.3 IPS |
|
Machine Translation (HP)
|
100% |
2374
40.9 IPS |
|
Machine Translation (Q)
|
98% |
2321
40.1 IPS |