Upload Date | September 10 2024 10:52 PM |
Views | 14 |
AI Information | |
---|---|
Framework | Core ML |
Backend | Neural Engine |
Device | Apple M1 |
System Information | |
---|---|
Operating System | iOS 18.0 |
Model | iPad Pro (11-inch 3rd generation) |
Model ID | iPad13,6 |
Motherboard | J518AP |
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 | 7.37 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
1405
261.3 IPS |
|
Image Classification (HP)
|
100% |
6407
1.19 KIPS |
|
Image Classification (Q)
|
96% |
5926
1.11 KIPS |
|
Image Segmentation (SP)
|
100% |
1376
22.3 IPS |
|
Image Segmentation (HP)
|
100% |
6624
107.4 IPS |
|
Image Segmentation (Q)
|
99% |
6736
109.2 IPS |
|
Pose Estimation (SP)
|
100% |
6536
7.63 IPS |
|
Pose Estimation (HP)
|
100% |
66881
78.0 IPS |
|
Pose Estimation (Q)
|
95% |
65665
77.0 IPS |
|
Object Detection (SP)
|
100% |
1514
120.1 IPS |
|
Object Detection (HP)
|
99% |
7113
565.8 IPS |
|
Object Detection (Q)
|
91% |
6576
525.5 IPS |
|
Face Detection (SP)
|
100% |
3041
36.1 IPS |
|
Face Detection (HP)
|
100% |
16146
191.8 IPS |
|
Face Detection (Q)
|
100% |
14954
177.7 IPS |
|
Depth Estimation (SP)
|
100% |
5809
44.8 IPS |
|
Depth Estimation (HP)
|
99% |
46666
359.5 IPS |
|
Depth Estimation (Q)
|
85% |
46699
364.9 IPS |
|
Style Transfer (SP)
|
100% |
17168
22.1 IPS |
|
Style Transfer (HP)
|
100% |
120088
154.4 IPS |
|
Style Transfer (Q)
|
96% |
111472
143.8 IPS |
|
Image Super-Resolution (SP)
|
100% |
3752
138.6 IPS |
|
Image Super-Resolution (HP)
|
100% |
22884
845.0 IPS |
|
Image Super-Resolution (Q)
|
99% |
23444
865.7 IPS |
|
Text Classification (SP)
|
100% |
2281
3.04 KIPS |
|
Text Classification (HP)
|
100% |
3811
5.09 KIPS |
|
Text Classification (Q)
|
93% |
3812
5.12 KIPS |
|
Machine Translation (SP)
|
100% |
2478
42.7 IPS |
|
Machine Translation (HP)
|
100% |
2318
39.9 IPS |
|
Machine Translation (Q)
|
98% |
2317
40.0 IPS |