User | AdrienRL |
Upload Date | August 16 2024 03:37 AM |
Views | 3 |
AI Information | |
---|---|
Framework | Core ML |
Backend | Neural Engine |
Device | Apple A14 Bionic |
System Information | |
---|---|
Operating System | iOS 18.0 |
Model | iPhone 12 Pro |
Model ID | iPhone13,3 |
Motherboard | D53pAP |
CPU Information | |
---|---|
Name | Apple A14 Bionic |
Topology | 1 Processor, 6 Cores |
Identifier | ARM |
Base Frequency | 2.99 GHz |
Cluster 1 | 2 Cores |
Cluster 2 | 4 Cores |
Memory Information | |
---|---|
Size | 5.58 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
1246
231.8 IPS |
|
Image Classification (HP)
|
100% |
4125
767.2 IPS |
|
Image Classification (Q)
|
99% |
4791
893.6 IPS |
|
Image Segmentation (SP)
|
100% |
1120
18.2 IPS |
|
Image Segmentation (HP)
|
100% |
5561
90.2 IPS |
|
Image Segmentation (Q)
|
100% |
5559
90.1 IPS |
|
Pose Estimation (SP)
|
100% |
5123
5.98 IPS |
|
Pose Estimation (HP)
|
100% |
57187
66.7 IPS |
|
Pose Estimation (Q)
|
94% |
59896
70.3 IPS |
|
Object Detection (SP)
|
100% |
1305
103.5 IPS |
|
Object Detection (HP)
|
99% |
5906
469.8 IPS |
|
Object Detection (Q)
|
91% |
5570
445.0 IPS |
|
Face Detection (SP)
|
100% |
2511
29.8 IPS |
|
Face Detection (HP)
|
100% |
11602
137.9 IPS |
|
Face Detection (Q)
|
100% |
11485
136.5 IPS |
|
Depth Estimation (SP)
|
100% |
4896
37.7 IPS |
|
Depth Estimation (HP)
|
99% |
35906
276.6 IPS |
|
Depth Estimation (Q)
|
97% |
40421
312.5 IPS |
|
Style Transfer (SP)
|
100% |
13410
17.2 IPS |
|
Style Transfer (HP)
|
100% |
97890
125.8 IPS |
|
Style Transfer (Q)
|
100% |
100816
129.6 IPS |
|
Image Super-Resolution (SP)
|
100% |
2931
108.2 IPS |
|
Image Super-Resolution (HP)
|
100% |
16722
617.5 IPS |
|
Image Super-Resolution (Q)
|
98% |
17579
651.3 IPS |
|
Text Classification (SP)
|
100% |
2101
2.80 KIPS |
|
Text Classification (HP)
|
100% |
2294
3.06 KIPS |
|
Text Classification (Q)
|
93% |
2405
3.23 KIPS |
|
Machine Translation (SP)
|
100% |
2295
39.5 IPS |
|
Machine Translation (HP)
|
100% |
2005
34.5 IPS |
|
Machine Translation (Q)
|
98% |
1923
33.2 IPS |