Upload Date | April 13 2025 10:04 AM |
Views | 1 |
AI Information | |
---|---|
Framework | Core ML |
Backend | Neural Engine |
Device | Apple A14 Bionic |
System Information | |
---|---|
Operating System | iOS 18.4 |
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% |
1215
225.9 IPS |
|
Image Classification (HP)
|
100% |
4302
800.0 IPS |
|
Image Classification (Q)
|
96% |
4194
783.2 IPS |
|
Image Segmentation (SP)
|
100% |
1046
17.0 IPS |
|
Image Segmentation (HP)
|
100% |
8126
131.7 IPS |
|
Image Segmentation (Q)
|
99% |
8714
141.3 IPS |
|
Pose Estimation (SP)
|
100% |
5721
6.67 IPS |
|
Pose Estimation (HP)
|
100% |
61867
72.2 IPS |
|
Pose Estimation (Q)
|
95% |
60684
71.1 IPS |
|
Object Detection (SP)
|
100% |
1273
101.0 IPS |
|
Object Detection (HP)
|
99% |
5828
463.6 IPS |
|
Object Detection (Q)
|
91% |
5053
403.7 IPS |
|
Face Detection (SP)
|
100% |
2450
29.1 IPS |
|
Face Detection (HP)
|
100% |
13936
165.6 IPS |
|
Face Detection (Q)
|
100% |
11804
140.3 IPS |
|
Depth Estimation (SP)
|
100% |
4920
37.9 IPS |
|
Depth Estimation (HP)
|
99% |
37133
286.1 IPS |
|
Depth Estimation (Q)
|
85% |
37832
295.6 IPS |
|
Style Transfer (SP)
|
100% |
14783
19.0 IPS |
|
Style Transfer (HP)
|
100% |
94046
120.9 IPS |
|
Style Transfer (Q)
|
96% |
98064
126.5 IPS |
|
Image Super-Resolution (SP)
|
100% |
3280
121.1 IPS |
|
Image Super-Resolution (HP)
|
100% |
16442
607.1 IPS |
|
Image Super-Resolution (Q)
|
99% |
17858
659.4 IPS |
|
Text Classification (SP)
|
100% |
2095
2.80 KIPS |
|
Text Classification (HP)
|
100% |
2274
3.04 KIPS |
|
Text Classification (Q)
|
93% |
2324
3.12 KIPS |
|
Machine Translation (SP)
|
100% |
2271
39.1 IPS |
|
Machine Translation (HP)
|
100% |
4468
77.0 IPS |
|
Machine Translation (Q)
|
98% |
5416
93.6 IPS |