User | ju83 |
Upload Date | December 04 2024 05:40 AM |
Views | 5 |
AI Information | |
---|---|
Framework | Core ML |
Backend | CPU |
Device | Apple A12 Bionic |
System Information | |
---|---|
Operating System | iOS 18.0 |
Model | iPad Air (3rd generation) |
Model ID | iPad11,3 |
Motherboard | J217AP |
CPU Information | |
---|---|
Name | Apple A12 Bionic |
Topology | 1 Processor, 6 Cores |
Identifier | ARM |
Base Frequency | 2.49 GHz |
Cluster 1 | 2 Cores |
Cluster 2 | 4 Cores |
Memory Information | |
---|---|
Size | 2.84 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
390
72.6 IPS |
|
Image Classification (HP)
|
100% |
669
124.4 IPS |
|
Image Classification (Q)
|
96% |
551
102.9 IPS |
|
Image Segmentation (SP)
|
100% |
430
6.97 IPS |
|
Image Segmentation (HP)
|
100% |
751
12.2 IPS |
|
Image Segmentation (Q)
|
99% |
808
13.1 IPS |
|
Pose Estimation (SP)
|
100% |
1257
1.47 IPS |
|
Pose Estimation (HP)
|
100% |
1236
1.44 IPS |
|
Pose Estimation (Q)
|
96% |
1172
1.37 IPS |
|
Object Detection (SP)
|
100% |
384
30.4 IPS |
|
Object Detection (HP)
|
99% |
734
58.2 IPS |
|
Object Detection (Q)
|
92% |
626
49.9 IPS |
|
Face Detection (SP)
|
100% |
959
11.4 IPS |
|
Face Detection (HP)
|
100% |
1871
22.2 IPS |
|
Face Detection (Q)
|
100% |
1246
14.8 IPS |
|
Depth Estimation (SP)
|
100% |
1054
8.12 IPS |
|
Depth Estimation (HP)
|
98% |
1695
13.1 IPS |
|
Depth Estimation (Q)
|
85% |
1614
12.6 IPS |
|
Style Transfer (SP)
|
100% |
2601
3.34 IPS |
|
Style Transfer (HP)
|
100% |
4453
5.73 IPS |
|
Style Transfer (Q)
|
96% |
4093
5.28 IPS |
|
Image Super-Resolution (SP)
|
100% |
704
26.0 IPS |
|
Image Super-Resolution (HP)
|
100% |
959
35.4 IPS |
|
Image Super-Resolution (Q)
|
99% |
832
30.7 IPS |
|
Text Classification (SP)
|
100% |
289
385.2 IPS |
|
Text Classification (HP)
|
100% |
562
750.2 IPS |
|
Text Classification (Q)
|
93% |
560
751.4 IPS |
|
Machine Translation (SP)
|
100% |
627
10.8 IPS |
|
Machine Translation (HP)
|
98% |
1093
18.9 IPS |
|
Machine Translation (Q)
|
98% |
1145
19.8 IPS |