User | bjoernt |
Upload Date | December 21 2024 09:24 PM |
Views | 2 |
AI Information | |
---|---|
Framework | Core ML |
Backend | Neural Engine |
Device | Apple M2 |
System Information | |
---|---|
Operating System | iOS 18.2 |
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% |
1394
259.2 IPS |
|
Image Classification (HP)
|
100% |
14610
2.72 KIPS |
|
Image Classification (Q)
|
96% |
15720
2.94 KIPS |
|
Image Segmentation (SP)
|
100% |
1534
24.9 IPS |
|
Image Segmentation (HP)
|
100% |
19056
308.9 IPS |
|
Image Segmentation (Q)
|
99% |
23818
386.1 IPS |
|
Pose Estimation (SP)
|
100% |
6868
8.01 IPS |
|
Pose Estimation (HP)
|
100% |
102964
120.1 IPS |
|
Pose Estimation (Q)
|
95% |
104508
122.5 IPS |
|
Object Detection (SP)
|
100% |
1562
123.9 IPS |
|
Object Detection (HP)
|
99% |
14994
1.19 KIPS |
|
Object Detection (Q)
|
91% |
16948
1.35 KIPS |
|
Face Detection (SP)
|
100% |
3169
37.7 IPS |
|
Face Detection (HP)
|
100% |
32469
385.8 IPS |
|
Face Detection (Q)
|
100% |
41560
493.8 IPS |
|
Depth Estimation (SP)
|
100% |
5691
43.8 IPS |
|
Depth Estimation (HP)
|
99% |
84919
654.2 IPS |
|
Depth Estimation (Q)
|
85% |
104993
820.5 IPS |
|
Style Transfer (SP)
|
100% |
18948
24.4 IPS |
|
Style Transfer (HP)
|
100% |
200742
258.1 IPS |
|
Style Transfer (Q)
|
96% |
189962
245.1 IPS |
|
Image Super-Resolution (SP)
|
100% |
4088
151.0 IPS |
|
Image Super-Resolution (HP)
|
100% |
38344
1.42 KIPS |
|
Image Super-Resolution (Q)
|
99% |
46098
1.70 KIPS |
|
Text Classification (SP)
|
100% |
2186
2.92 KIPS |
|
Text Classification (HP)
|
100% |
3763
5.02 KIPS |
|
Text Classification (Q)
|
93% |
3683
4.94 KIPS |
|
Machine Translation (SP)
|
100% |
3570
61.5 IPS |
|
Machine Translation (HP)
|
100% |
3934
67.8 IPS |
|
Machine Translation (Q)
|
98% |
4112
71.1 IPS |