Upload Date | December 27 2024 07:37 PM |
Views | 1 |
AI Information | |
---|---|
Framework | Core ML |
Backend | Neural Engine |
Device | Apple M4 |
System Information | |
---|---|
Operating System | iOS 18.2 |
Model | iPad Pro 11-inch (M4) |
Model ID | iPad16,3 |
Motherboard | J717AP |
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 | 7.29 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
2026
376.7 IPS |
|
Image Classification (HP)
|
100% |
16949
3.15 KIPS |
|
Image Classification (Q)
|
97% |
24020
4.48 KIPS |
|
Image Segmentation (SP)
|
100% |
2145
34.8 IPS |
|
Image Segmentation (HP)
|
100% |
22058
357.6 IPS |
|
Image Segmentation (Q)
|
99% |
30231
490.1 IPS |
|
Pose Estimation (SP)
|
100% |
10077
11.8 IPS |
|
Pose Estimation (HP)
|
100% |
123638
144.3 IPS |
|
Pose Estimation (Q)
|
95% |
232679
272.7 IPS |
|
Object Detection (SP)
|
100% |
2254
178.8 IPS |
|
Object Detection (HP)
|
100% |
18094
1.44 KIPS |
|
Object Detection (Q)
|
91% |
26091
2.08 KIPS |
|
Face Detection (SP)
|
100% |
3987
47.4 IPS |
|
Face Detection (HP)
|
100% |
42561
505.7 IPS |
|
Face Detection (Q)
|
100% |
62309
740.4 IPS |
|
Depth Estimation (SP)
|
100% |
8290
63.9 IPS |
|
Depth Estimation (HP)
|
99% |
98504
758.9 IPS |
|
Depth Estimation (Q)
|
85% |
165620
1.29 KIPS |
|
Style Transfer (SP)
|
100% |
25121
32.3 IPS |
|
Style Transfer (HP)
|
100% |
232973
299.5 IPS |
|
Style Transfer (Q)
|
96% |
298467
385.2 IPS |
|
Image Super-Resolution (SP)
|
100% |
5974
220.6 IPS |
|
Image Super-Resolution (HP)
|
100% |
48593
1.79 KIPS |
|
Image Super-Resolution (Q)
|
99% |
81586
3.01 KIPS |
|
Text Classification (SP)
|
100% |
3499
4.67 KIPS |
|
Text Classification (HP)
|
100% |
5944
7.93 KIPS |
|
Text Classification (Q)
|
93% |
6128
8.23 KIPS |
|
Machine Translation (SP)
|
100% |
4123
71.0 IPS |
|
Machine Translation (HP)
|
100% |
16124
277.7 IPS |
|
Machine Translation (Q)
|
98% |
17618
304.5 IPS |