Upload Date | January 02 2025 10:25 AM |
Views | 2 |
AI Information | |
---|---|
Framework | Core ML |
Backend | Neural Engine |
Device | Apple M2 |
System Information | |
---|---|
Operating System | iOS 18.1.1 |
Model | iPad Air 11-inch (M2) |
Model ID | iPad14,8 |
Motherboard | J507AP |
CPU Information | |
---|---|
Name | Apple M2 |
Topology | 1 Processor, 8 Cores |
Identifier | ARM |
Base Frequency | 3.48 GHz |
Cluster 1 | 4 Cores |
Cluster 2 | 4 Cores |
Memory Information | |
---|---|
Size | 7.47 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
1386
257.7 IPS |
|
Image Classification (HP)
|
100% |
14108
2.62 KIPS |
|
Image Classification (Q)
|
96% |
15091
2.82 KIPS |
|
Image Segmentation (SP)
|
100% |
1520
24.6 IPS |
|
Image Segmentation (HP)
|
100% |
18839
305.4 IPS |
|
Image Segmentation (Q)
|
99% |
23418
379.6 IPS |
|
Pose Estimation (SP)
|
100% |
6880
8.03 IPS |
|
Pose Estimation (HP)
|
100% |
105562
123.2 IPS |
|
Pose Estimation (Q)
|
95% |
104656
122.7 IPS |
|
Object Detection (SP)
|
100% |
1558
123.6 IPS |
|
Object Detection (HP)
|
99% |
15014
1.19 KIPS |
|
Object Detection (Q)
|
91% |
16958
1.36 KIPS |
|
Face Detection (SP)
|
100% |
3162
37.6 IPS |
|
Face Detection (HP)
|
100% |
32900
390.9 IPS |
|
Face Detection (Q)
|
100% |
41252
490.2 IPS |
|
Depth Estimation (SP)
|
100% |
5697
43.9 IPS |
|
Depth Estimation (HP)
|
99% |
84906
654.2 IPS |
|
Depth Estimation (Q)
|
85% |
103502
808.8 IPS |
|
Style Transfer (SP)
|
100% |
18848
24.2 IPS |
|
Style Transfer (HP)
|
100% |
201328
258.8 IPS |
|
Style Transfer (Q)
|
96% |
188269
243.0 IPS |
|
Image Super-Resolution (SP)
|
100% |
4059
149.9 IPS |
|
Image Super-Resolution (HP)
|
100% |
38825
1.43 KIPS |
|
Image Super-Resolution (Q)
|
99% |
46185
1.71 KIPS |
|
Text Classification (SP)
|
100% |
2173
2.90 KIPS |
|
Text Classification (HP)
|
100% |
3661
4.89 KIPS |
|
Text Classification (Q)
|
93% |
3624
4.86 KIPS |
|
Machine Translation (SP)
|
100% |
3571
61.5 IPS |
|
Machine Translation (HP)
|
100% |
6696
115.3 IPS |
|
Machine Translation (Q)
|
98% |
7291
126.0 IPS |