User | buggshash |
Upload Date | December 10 2024 06:50 PM |
Views | 2 |
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% |
4479
833.0 IPS |
|
Image Classification (HP)
|
100% |
4804
893.5 IPS |
|
Image Classification (Q)
|
97% |
4209
785.5 IPS |
|
Image Segmentation (SP)
|
100% |
4876
79.0 IPS |
|
Image Segmentation (HP)
|
100% |
6696
108.6 IPS |
|
Image Segmentation (Q)
|
99% |
7145
115.8 IPS |
|
Pose Estimation (SP)
|
100% |
28078
32.8 IPS |
|
Pose Estimation (HP)
|
100% |
30058
35.1 IPS |
|
Pose Estimation (Q)
|
95% |
28596
33.5 IPS |
|
Object Detection (SP)
|
100% |
4794
380.2 IPS |
|
Object Detection (HP)
|
100% |
5212
413.4 IPS |
|
Object Detection (Q)
|
91% |
4432
354.1 IPS |
|
Face Detection (SP)
|
100% |
12927
153.6 IPS |
|
Face Detection (HP)
|
100% |
16462
195.6 IPS |
|
Face Detection (Q)
|
100% |
11969
142.2 IPS |
|
Depth Estimation (SP)
|
100% |
20510
158.0 IPS |
|
Depth Estimation (HP)
|
99% |
22320
172.0 IPS |
|
Depth Estimation (Q)
|
85% |
19059
149.0 IPS |
|
Style Transfer (SP)
|
100% |
56416
72.5 IPS |
|
Style Transfer (HP)
|
100% |
67978
87.4 IPS |
|
Style Transfer (Q)
|
96% |
64243
82.9 IPS |
|
Image Super-Resolution (SP)
|
100% |
12045
444.8 IPS |
|
Image Super-Resolution (HP)
|
100% |
12932
477.5 IPS |
|
Image Super-Resolution (Q)
|
99% |
10552
389.6 IPS |
|
Text Classification (SP)
|
100% |
3008
4.01 KIPS |
|
Text Classification (HP)
|
100% |
5480
7.31 KIPS |
|
Text Classification (Q)
|
93% |
5352
7.18 KIPS |
|
Machine Translation (SP)
|
100% |
1895
32.6 IPS |
|
Machine Translation (HP)
|
100% |
2089
36.0 IPS |
|
Machine Translation (Q)
|
98% |
1650
28.5 IPS |