Upload Date | November 21 2024 08:21 AM |
Views | 1 |
AI Information | |
---|---|
Framework | Core ML |
Backend | Neural Engine |
Device | Apple A14 Bionic |
System Information | |
---|---|
Operating System | iOS 18.1 |
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% |
1197
222.6 IPS |
|
Image Classification (HP)
|
100% |
3831
712.4 IPS |
|
Image Classification (Q)
|
96% |
4735
884.3 IPS |
|
Image Segmentation (SP)
|
100% |
1076
17.4 IPS |
|
Image Segmentation (HP)
|
100% |
8052
130.5 IPS |
|
Image Segmentation (Q)
|
99% |
8327
135.0 IPS |
|
Pose Estimation (SP)
|
100% |
5703
6.65 IPS |
|
Pose Estimation (HP)
|
100% |
60965
71.1 IPS |
|
Pose Estimation (Q)
|
95% |
60912
71.4 IPS |
|
Object Detection (SP)
|
100% |
1326
105.2 IPS |
|
Object Detection (HP)
|
99% |
5829
463.7 IPS |
|
Object Detection (Q)
|
91% |
5258
420.1 IPS |
|
Face Detection (SP)
|
100% |
2469
29.3 IPS |
|
Face Detection (HP)
|
100% |
14539
172.8 IPS |
|
Face Detection (Q)
|
100% |
12104
143.8 IPS |
|
Depth Estimation (SP)
|
100% |
5071
39.1 IPS |
|
Depth Estimation (HP)
|
99% |
36691
282.7 IPS |
|
Depth Estimation (Q)
|
85% |
37616
294.0 IPS |
|
Style Transfer (SP)
|
100% |
14791
19.0 IPS |
|
Style Transfer (HP)
|
100% |
94830
121.9 IPS |
|
Style Transfer (Q)
|
96% |
92924
119.9 IPS |
|
Image Super-Resolution (SP)
|
100% |
3267
120.7 IPS |
|
Image Super-Resolution (HP)
|
100% |
17310
639.2 IPS |
|
Image Super-Resolution (Q)
|
99% |
17977
663.8 IPS |
|
Text Classification (SP)
|
100% |
2063
2.75 KIPS |
|
Text Classification (HP)
|
100% |
2325
3.10 KIPS |
|
Text Classification (Q)
|
93% |
2230
2.99 KIPS |
|
Machine Translation (SP)
|
100% |
2254
38.8 IPS |
|
Machine Translation (HP)
|
100% |
3340
57.5 IPS |
|
Machine Translation (Q)
|
98% |
3939
68.1 IPS |