Upload Date | May 28 2025 09:31 AM |
Views | 3 |
AI Information | |
---|---|
Framework | Core ML |
Backend | Neural Engine |
Device | Apple A14 Bionic |
System Information | |
---|---|
Operating System | iOS 18.5 |
Model | iPad Air (4th generation) |
Model ID | iPad13,1 |
Motherboard | J307AP |
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 | 3.78 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
1222
227.2 IPS |
|
Image Classification (HP)
|
100% |
4856
903.1 IPS |
|
Image Classification (Q)
|
96% |
4917
918.1 IPS |
|
Image Segmentation (SP)
|
100% |
1071
17.4 IPS |
|
Image Segmentation (HP)
|
100% |
8513
138.0 IPS |
|
Image Segmentation (Q)
|
99% |
8600
139.4 IPS |
|
Pose Estimation (SP)
|
100% |
5673
6.62 IPS |
|
Pose Estimation (HP)
|
100% |
63234
73.8 IPS |
|
Pose Estimation (Q)
|
95% |
61715
72.3 IPS |
|
Object Detection (SP)
|
100% |
1306
103.6 IPS |
|
Object Detection (HP)
|
99% |
5841
464.6 IPS |
|
Object Detection (Q)
|
91% |
4989
398.6 IPS |
|
Face Detection (SP)
|
100% |
2477
29.4 IPS |
|
Face Detection (HP)
|
100% |
14020
166.6 IPS |
|
Face Detection (Q)
|
100% |
11813
140.4 IPS |
|
Depth Estimation (SP)
|
100% |
4940
38.1 IPS |
|
Depth Estimation (HP)
|
99% |
38957
300.1 IPS |
|
Depth Estimation (Q)
|
85% |
36061
281.8 IPS |
|
Style Transfer (SP)
|
100% |
14819
19.0 IPS |
|
Style Transfer (HP)
|
100% |
101454
130.4 IPS |
|
Style Transfer (Q)
|
96% |
100019
129.1 IPS |
|
Image Super-Resolution (SP)
|
100% |
3258
120.3 IPS |
|
Image Super-Resolution (HP)
|
100% |
17703
653.7 IPS |
|
Image Super-Resolution (Q)
|
99% |
18272
674.7 IPS |
|
Text Classification (SP)
|
100% |
2081
2.78 KIPS |
|
Text Classification (HP)
|
100% |
2338
3.12 KIPS |
|
Text Classification (Q)
|
93% |
2300
3.09 KIPS |
|
Machine Translation (SP)
|
100% |
2303
39.7 IPS |
|
Machine Translation (HP)
|
100% |
4504
77.6 IPS |
|
Machine Translation (Q)
|
98% |
5503
95.1 IPS |