User | visualvictor |
Upload Date | March 25 2025 01:23 AM |
Views | 10 |
AI Information | |
---|---|
Framework | Core ML |
Backend | GPU |
Device | Apple M4 |
System Information | |
---|---|
Operating System | iOS 18.3.2 |
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% |
4444
826.4 IPS |
|
Image Classification (HP)
|
100% |
4859
903.7 IPS |
|
Image Classification (Q)
|
97% |
4120
768.9 IPS |
|
Image Segmentation (SP)
|
100% |
4901
79.4 IPS |
|
Image Segmentation (HP)
|
100% |
6734
109.2 IPS |
|
Image Segmentation (Q)
|
99% |
7152
115.9 IPS |
|
Pose Estimation (SP)
|
100% |
27913
32.6 IPS |
|
Pose Estimation (HP)
|
100% |
30035
35.0 IPS |
|
Pose Estimation (Q)
|
95% |
28608
33.5 IPS |
|
Object Detection (SP)
|
100% |
4680
371.2 IPS |
|
Object Detection (HP)
|
100% |
5174
410.4 IPS |
|
Object Detection (Q)
|
91% |
4403
351.8 IPS |
|
Face Detection (SP)
|
100% |
12849
152.7 IPS |
|
Face Detection (HP)
|
100% |
16442
195.4 IPS |
|
Face Detection (Q)
|
100% |
11969
142.2 IPS |
|
Depth Estimation (SP)
|
100% |
20220
155.8 IPS |
|
Depth Estimation (HP)
|
99% |
22256
171.5 IPS |
|
Depth Estimation (Q)
|
85% |
19337
151.2 IPS |
|
Style Transfer (SP)
|
100% |
56175
72.2 IPS |
|
Style Transfer (HP)
|
100% |
66998
86.1 IPS |
|
Style Transfer (Q)
|
96% |
62686
80.9 IPS |
|
Image Super-Resolution (SP)
|
100% |
11591
428.0 IPS |
|
Image Super-Resolution (HP)
|
100% |
12644
466.9 IPS |
|
Image Super-Resolution (Q)
|
99% |
10373
383.0 IPS |
|
Text Classification (SP)
|
100% |
2983
3.98 KIPS |
|
Text Classification (HP)
|
100% |
5513
7.36 KIPS |
|
Text Classification (Q)
|
93% |
5570
7.48 KIPS |
|
Machine Translation (SP)
|
100% |
1981
34.1 IPS |
|
Machine Translation (HP)
|
100% |
1611
27.7 IPS |
|
Machine Translation (Q)
|
98% |
2100
36.3 IPS |