User | pakitt |
Upload Date | December 14 2024 03:10 AM |
Views | 19 |
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% |
1378
256.3 IPS |
|
Image Classification (HP)
|
100% |
14253
2.65 KIPS |
|
Image Classification (Q)
|
96% |
14947
2.79 KIPS |
|
Image Segmentation (SP)
|
100% |
1515
24.6 IPS |
|
Image Segmentation (HP)
|
100% |
18875
306.0 IPS |
|
Image Segmentation (Q)
|
99% |
23677
383.8 IPS |
|
Pose Estimation (SP)
|
100% |
6877
8.02 IPS |
|
Pose Estimation (HP)
|
100% |
105554
123.2 IPS |
|
Pose Estimation (Q)
|
95% |
104221
122.2 IPS |
|
Object Detection (SP)
|
100% |
1561
123.9 IPS |
|
Object Detection (HP)
|
99% |
14967
1.19 KIPS |
|
Object Detection (Q)
|
91% |
16965
1.36 KIPS |
|
Face Detection (SP)
|
100% |
3182
37.8 IPS |
|
Face Detection (HP)
|
100% |
32298
383.8 IPS |
|
Face Detection (Q)
|
100% |
41611
494.4 IPS |
|
Depth Estimation (SP)
|
100% |
5694
43.9 IPS |
|
Depth Estimation (HP)
|
99% |
86088
663.3 IPS |
|
Depth Estimation (Q)
|
85% |
104791
818.9 IPS |
|
Style Transfer (SP)
|
100% |
18854
24.2 IPS |
|
Style Transfer (HP)
|
100% |
200594
257.9 IPS |
|
Style Transfer (Q)
|
96% |
187860
242.4 IPS |
|
Image Super-Resolution (SP)
|
100% |
4153
153.4 IPS |
|
Image Super-Resolution (HP)
|
100% |
37998
1.40 KIPS |
|
Image Super-Resolution (Q)
|
99% |
46483
1.72 KIPS |
|
Text Classification (SP)
|
100% |
2240
2.99 KIPS |
|
Text Classification (HP)
|
100% |
3731
4.98 KIPS |
|
Text Classification (Q)
|
93% |
3679
4.94 KIPS |
|
Machine Translation (SP)
|
100% |
3549
61.1 IPS |
|
Machine Translation (HP)
|
100% |
3967
68.3 IPS |
|
Machine Translation (Q)
|
98% |
4118
71.2 IPS |