User | Wolfgang1756 |
Upload Date | December 10 2024 04:13 AM |
Views | 5 |
AI Information | |
---|---|
Framework | Core ML |
Backend | GPU |
Device | Apple M4 |
System Information | |
---|---|
Operating System | iOS 18.1.1 |
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% |
4518
840.2 IPS |
|
Image Classification (HP)
|
100% |
4833
898.8 IPS |
|
Image Classification (Q)
|
97% |
4216
786.7 IPS |
|
Image Segmentation (SP)
|
100% |
4921
79.8 IPS |
|
Image Segmentation (HP)
|
100% |
6717
108.9 IPS |
|
Image Segmentation (Q)
|
99% |
7152
115.9 IPS |
|
Pose Estimation (SP)
|
100% |
28208
32.9 IPS |
|
Pose Estimation (HP)
|
100% |
30244
35.3 IPS |
|
Pose Estimation (Q)
|
95% |
28825
33.8 IPS |
|
Object Detection (SP)
|
100% |
4786
379.6 IPS |
|
Object Detection (HP)
|
100% |
5201
412.5 IPS |
|
Object Detection (Q)
|
91% |
4446
355.2 IPS |
|
Face Detection (SP)
|
100% |
12884
153.1 IPS |
|
Face Detection (HP)
|
100% |
16431
195.2 IPS |
|
Face Detection (Q)
|
100% |
12014
142.8 IPS |
|
Depth Estimation (SP)
|
100% |
20489
157.9 IPS |
|
Depth Estimation (HP)
|
99% |
22447
172.9 IPS |
|
Depth Estimation (Q)
|
85% |
19154
149.7 IPS |
|
Style Transfer (SP)
|
100% |
58494
75.2 IPS |
|
Style Transfer (HP)
|
100% |
67885
87.3 IPS |
|
Style Transfer (Q)
|
96% |
63966
82.5 IPS |
|
Image Super-Resolution (SP)
|
100% |
11686
431.5 IPS |
|
Image Super-Resolution (HP)
|
100% |
12708
469.2 IPS |
|
Image Super-Resolution (Q)
|
99% |
10381
383.3 IPS |
|
Text Classification (SP)
|
100% |
2999
4.00 KIPS |
|
Text Classification (HP)
|
100% |
5581
7.45 KIPS |
|
Text Classification (Q)
|
93% |
5494
7.37 KIPS |
|
Machine Translation (SP)
|
100% |
1589
27.4 IPS |
|
Machine Translation (HP)
|
100% |
2101
36.2 IPS |
|
Machine Translation (Q)
|
98% |
1642
28.4 IPS |