Upload Date | November 18 2024 12:46 PM |
Views | 1 |
AI Information | |
---|---|
Framework | Core ML |
Backend | Neural Engine |
Device | Apple M1 |
System Information | |
---|---|
Operating System | iOS 18.1 |
Model | iPad Pro (11-inch 3rd generation) |
Model ID | iPad13,5 |
Motherboard | J517xAP |
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 | 15.37 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
1404
261.2 IPS |
|
Image Classification (HP)
|
100% |
6219
1.16 KIPS |
|
Image Classification (Q)
|
96% |
5743
1.07 KIPS |
|
Image Segmentation (SP)
|
100% |
1390
22.5 IPS |
|
Image Segmentation (HP)
|
100% |
9747
158.0 IPS |
|
Image Segmentation (Q)
|
99% |
9991
162.0 IPS |
|
Pose Estimation (SP)
|
100% |
6531
7.62 IPS |
|
Pose Estimation (HP)
|
100% |
66799
77.9 IPS |
|
Pose Estimation (Q)
|
95% |
66223
77.6 IPS |
|
Object Detection (SP)
|
100% |
1507
119.5 IPS |
|
Object Detection (HP)
|
99% |
7134
567.5 IPS |
|
Object Detection (Q)
|
91% |
6534
522.1 IPS |
|
Face Detection (SP)
|
100% |
3057
36.3 IPS |
|
Face Detection (HP)
|
100% |
16317
193.9 IPS |
|
Face Detection (Q)
|
100% |
15088
179.3 IPS |
|
Depth Estimation (SP)
|
100% |
5825
44.9 IPS |
|
Depth Estimation (HP)
|
99% |
48039
370.1 IPS |
|
Depth Estimation (Q)
|
85% |
47150
368.5 IPS |
|
Style Transfer (SP)
|
100% |
17186
22.1 IPS |
|
Style Transfer (HP)
|
100% |
119861
154.1 IPS |
|
Style Transfer (Q)
|
96% |
111165
143.5 IPS |
|
Image Super-Resolution (SP)
|
100% |
3777
139.5 IPS |
|
Image Super-Resolution (HP)
|
100% |
22583
833.9 IPS |
|
Image Super-Resolution (Q)
|
99% |
23272
859.3 IPS |
|
Text Classification (SP)
|
100% |
2283
3.05 KIPS |
|
Text Classification (HP)
|
100% |
3944
5.26 KIPS |
|
Text Classification (Q)
|
93% |
3908
5.25 KIPS |
|
Machine Translation (SP)
|
100% |
2492
42.9 IPS |
|
Machine Translation (HP)
|
100% |
5441
93.7 IPS |
|
Machine Translation (Q)
|
98% |
5712
98.7 IPS |