Upload Date | December 25 2024 07:58 AM |
Views | 1 |
AI Information | |
---|---|
Framework | Core ML |
Backend | Neural Engine |
Device | Apple M4 |
System Information | |
---|---|
Operating System | iOS 18.3 |
Model | iPad Pro 13-inch (M4) |
Model ID | iPad16,6 |
Motherboard | J721AP |
CPU Information | |
---|---|
Name | Apple M4 |
Topology | 1 Processor, 9 Cores |
Identifier | ARM |
Base Frequency | 4.41 GHz |
Cluster 1 | 3 Cores |
Cluster 2 | 6 Cores |
Memory Information | |
---|---|
Size | 7.21 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
1977
367.7 IPS |
|
Image Classification (HP)
|
100% |
17089
3.18 KIPS |
|
Image Classification (Q)
|
97% |
23993
4.48 KIPS |
|
Image Segmentation (SP)
|
100% |
2003
32.5 IPS |
|
Image Segmentation (HP)
|
100% |
22089
358.1 IPS |
|
Image Segmentation (Q)
|
99% |
30365
492.2 IPS |
|
Pose Estimation (SP)
|
100% |
10072
11.8 IPS |
|
Pose Estimation (HP)
|
100% |
124091
144.8 IPS |
|
Pose Estimation (Q)
|
95% |
232443
272.4 IPS |
|
Object Detection (SP)
|
100% |
2244
178.0 IPS |
|
Object Detection (HP)
|
100% |
18486
1.47 KIPS |
|
Object Detection (Q)
|
91% |
25262
2.02 KIPS |
|
Face Detection (SP)
|
100% |
3950
46.9 IPS |
|
Face Detection (HP)
|
100% |
41731
495.9 IPS |
|
Face Detection (Q)
|
100% |
62937
747.8 IPS |
|
Depth Estimation (SP)
|
100% |
8302
64.0 IPS |
|
Depth Estimation (HP)
|
99% |
98718
760.6 IPS |
|
Depth Estimation (Q)
|
85% |
167309
1.31 KIPS |
|
Style Transfer (SP)
|
100% |
25042
32.2 IPS |
|
Style Transfer (HP)
|
100% |
234112
301.0 IPS |
|
Style Transfer (Q)
|
96% |
298145
384.7 IPS |
|
Image Super-Resolution (SP)
|
100% |
5956
219.9 IPS |
|
Image Super-Resolution (HP)
|
100% |
48530
1.79 KIPS |
|
Image Super-Resolution (Q)
|
99% |
80993
2.99 KIPS |
|
Text Classification (SP)
|
100% |
3417
4.56 KIPS |
|
Text Classification (HP)
|
100% |
5725
7.64 KIPS |
|
Text Classification (Q)
|
93% |
5927
7.95 KIPS |
|
Machine Translation (SP)
|
100% |
4073
70.2 IPS |
|
Machine Translation (HP)
|
100% |
15872
273.4 IPS |
|
Machine Translation (Q)
|
98% |
17628
304.6 IPS |