Upload Date | April 13 2025 09:54 AM |
Views | 3 |
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% |
1191
221.4 IPS |
|
Image Classification (HP)
|
100% |
4493
835.5 IPS |
|
Image Classification (Q)
|
96% |
4776
891.9 IPS |
|
Image Segmentation (SP)
|
100% |
1042
16.9 IPS |
|
Image Segmentation (HP)
|
100% |
8166
132.4 IPS |
|
Image Segmentation (Q)
|
99% |
8470
137.3 IPS |
|
Pose Estimation (SP)
|
100% |
5737
6.69 IPS |
|
Pose Estimation (HP)
|
100% |
62222
72.6 IPS |
|
Pose Estimation (Q)
|
95% |
62863
73.7 IPS |
|
Object Detection (SP)
|
100% |
1274
101.0 IPS |
|
Object Detection (HP)
|
99% |
5817
462.7 IPS |
|
Object Detection (Q)
|
91% |
5210
416.3 IPS |
|
Face Detection (SP)
|
100% |
2444
29.0 IPS |
|
Face Detection (HP)
|
100% |
14037
166.8 IPS |
|
Face Detection (Q)
|
100% |
11816
140.4 IPS |
|
Depth Estimation (SP)
|
100% |
4918
37.9 IPS |
|
Depth Estimation (HP)
|
99% |
39219
302.2 IPS |
|
Depth Estimation (Q)
|
85% |
36729
287.0 IPS |
|
Style Transfer (SP)
|
100% |
14675
18.9 IPS |
|
Style Transfer (HP)
|
100% |
99075
127.4 IPS |
|
Style Transfer (Q)
|
96% |
94206
121.6 IPS |
|
Image Super-Resolution (SP)
|
100% |
3216
118.8 IPS |
|
Image Super-Resolution (HP)
|
100% |
17596
649.7 IPS |
|
Image Super-Resolution (Q)
|
99% |
18356
677.8 IPS |
|
Text Classification (SP)
|
100% |
2053
2.74 KIPS |
|
Text Classification (HP)
|
100% |
2385
3.18 KIPS |
|
Text Classification (Q)
|
93% |
2398
3.22 KIPS |
|
Machine Translation (SP)
|
100% |
2283
39.3 IPS |
|
Machine Translation (HP)
|
100% |
4620
79.6 IPS |
|
Machine Translation (Q)
|
98% |
5464
94.4 IPS |