User | Wwessex |
Upload Date | August 15 2024 09:04 PM |
Views | 5 |
AI Information | |
---|---|
Framework | Core ML |
Backend | Neural Engine |
Device | Apple M1 |
System Information | |
---|---|
Operating System | iOS 18.1 |
Model | iPad Pro (12.9-inch 5th generation) |
Model ID | iPad13,8 |
Motherboard | J522AP |
CPU Information | |
---|---|
Name | Apple M1 |
Topology | 1 Processor, 8 Cores |
Identifier | ARM |
Base Frequency | 3.19 GHz |
Cluster 1 | 4 Cores |
Cluster 2 | 4 Cores |
Memory Information | |
---|---|
Size | 7.35 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
1406
261.5 IPS |
|
Image Classification (HP)
|
100% |
2778
516.7 IPS |
|
Image Classification (Q)
|
99% |
6164
1.15 KIPS |
|
Image Segmentation (SP)
|
100% |
1356
22.0 IPS |
|
Image Segmentation (HP)
|
100% |
6164
99.9 IPS |
|
Image Segmentation (Q)
|
100% |
6147
99.6 IPS |
|
Pose Estimation (SP)
|
100% |
6547
7.64 IPS |
|
Pose Estimation (HP)
|
100% |
67237
78.5 IPS |
|
Pose Estimation (Q)
|
94% |
64922
76.1 IPS |
|
Object Detection (SP)
|
100% |
1524
120.9 IPS |
|
Object Detection (HP)
|
99% |
6832
543.4 IPS |
|
Object Detection (Q)
|
91% |
6654
531.7 IPS |
|
Face Detection (SP)
|
100% |
3052
36.3 IPS |
|
Face Detection (HP)
|
100% |
12700
150.9 IPS |
|
Face Detection (Q)
|
100% |
13707
162.9 IPS |
|
Depth Estimation (SP)
|
100% |
5803
44.7 IPS |
|
Depth Estimation (HP)
|
99% |
43309
333.7 IPS |
|
Depth Estimation (Q)
|
97% |
45911
355.0 IPS |
|
Style Transfer (SP)
|
100% |
17169
22.1 IPS |
|
Style Transfer (HP)
|
100% |
116545
149.8 IPS |
|
Style Transfer (Q)
|
100% |
122149
157.0 IPS |
|
Image Super-Resolution (SP)
|
100% |
3744
138.2 IPS |
|
Image Super-Resolution (HP)
|
100% |
23077
852.1 IPS |
|
Image Super-Resolution (Q)
|
98% |
23960
887.7 IPS |
|
Text Classification (SP)
|
100% |
2310
3.08 KIPS |
|
Text Classification (HP)
|
100% |
4012
5.36 KIPS |
|
Text Classification (Q)
|
93% |
3957
5.31 KIPS |
|
Machine Translation (SP)
|
100% |
2547
43.9 IPS |
|
Machine Translation (HP)
|
100% |
2328
40.1 IPS |
|
Machine Translation (Q)
|
98% |
2298
39.7 IPS |