User | Wolfgang1756 |
Upload Date | December 10 2024 04:13 AM |
Views | 3 |
AI Information | |
---|---|
Framework | Core ML |
Backend | GPU |
Device | Apple M4 |
System Information | |
---|---|
Operating System | iOS 18.1.1 |
Model | iPad Pro 13-inch (M4) |
Model ID | iPad16,5 |
Motherboard | J720AP |
CPU Information | |
---|---|
Name | Apple M4 |
Topology | 1 Processor, 10 Cores |
Identifier | ARM |
Base Frequency | 4.41 GHz |
Cluster 1 | 4 Cores |
Cluster 2 | 6 Cores |
Memory Information | |
---|---|
Size | 15.07 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
4492
835.4 IPS |
|
Image Classification (HP)
|
100% |
4821
896.5 IPS |
|
Image Classification (Q)
|
97% |
4152
774.9 IPS |
|
Image Segmentation (SP)
|
100% |
4920
79.8 IPS |
|
Image Segmentation (HP)
|
100% |
6731
109.1 IPS |
|
Image Segmentation (Q)
|
99% |
7140
115.7 IPS |
|
Pose Estimation (SP)
|
100% |
28214
32.9 IPS |
|
Pose Estimation (HP)
|
100% |
30269
35.3 IPS |
|
Pose Estimation (Q)
|
95% |
28799
33.8 IPS |
|
Object Detection (SP)
|
100% |
4745
376.4 IPS |
|
Object Detection (HP)
|
100% |
5199
412.4 IPS |
|
Object Detection (Q)
|
91% |
4431
354.1 IPS |
|
Face Detection (SP)
|
100% |
12896
153.2 IPS |
|
Face Detection (HP)
|
100% |
16396
194.8 IPS |
|
Face Detection (Q)
|
100% |
11985
142.4 IPS |
|
Depth Estimation (SP)
|
100% |
20466
157.7 IPS |
|
Depth Estimation (HP)
|
99% |
22379
172.4 IPS |
|
Depth Estimation (Q)
|
85% |
19044
148.9 IPS |
|
Style Transfer (SP)
|
100% |
56105
72.1 IPS |
|
Style Transfer (HP)
|
100% |
67835
87.2 IPS |
|
Style Transfer (Q)
|
96% |
63762
82.3 IPS |
|
Image Super-Resolution (SP)
|
100% |
11656
430.4 IPS |
|
Image Super-Resolution (HP)
|
100% |
12682
468.3 IPS |
|
Image Super-Resolution (Q)
|
99% |
10284
379.7 IPS |
|
Text Classification (SP)
|
100% |
3013
4.02 KIPS |
|
Text Classification (HP)
|
100% |
5570
7.43 KIPS |
|
Text Classification (Q)
|
93% |
5657
7.59 KIPS |
|
Machine Translation (SP)
|
100% |
1581
27.2 IPS |
|
Machine Translation (HP)
|
100% |
1668
28.7 IPS |
|
Machine Translation (Q)
|
98% |
1652
28.5 IPS |