Upload Date | November 20 2024 11:13 PM |
Views | 1 |
AI Information | |
---|---|
Framework | Core ML |
Backend | Neural Engine |
Device | Apple M1 |
System Information | |
---|---|
Operating System | iOS 18.1.1 |
Model | iPad Pro (11-inch 3rd generation) |
Model ID | iPad13,4 |
Motherboard | J517AP |
CPU Information | |
---|---|
Name | Apple M1 |
Topology | 1 Processor, 8 Cores |
Identifier | ARM |
Base Frequency | 3.19 GHz |
Cluster 1 | 4 Cores |
Cluster 2 | 4 Cores |
Memory Information | |
---|---|
Size | 7.37 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
1397
259.7 IPS |
|
Image Classification (HP)
|
100% |
6128
1.14 KIPS |
|
Image Classification (Q)
|
96% |
5811
1.09 KIPS |
|
Image Segmentation (SP)
|
100% |
1435
23.3 IPS |
|
Image Segmentation (HP)
|
100% |
9809
159.0 IPS |
|
Image Segmentation (Q)
|
99% |
10136
164.3 IPS |
|
Pose Estimation (SP)
|
100% |
6536
7.63 IPS |
|
Pose Estimation (HP)
|
100% |
68990
80.5 IPS |
|
Pose Estimation (Q)
|
95% |
65643
76.9 IPS |
|
Object Detection (SP)
|
100% |
1513
120.0 IPS |
|
Object Detection (HP)
|
99% |
7250
576.7 IPS |
|
Object Detection (Q)
|
91% |
6463
516.4 IPS |
|
Face Detection (SP)
|
100% |
3052
36.3 IPS |
|
Face Detection (HP)
|
100% |
16627
197.6 IPS |
|
Face Detection (Q)
|
100% |
15246
181.2 IPS |
|
Depth Estimation (SP)
|
100% |
5804
44.7 IPS |
|
Depth Estimation (HP)
|
99% |
47827
368.5 IPS |
|
Depth Estimation (Q)
|
85% |
48786
381.2 IPS |
|
Style Transfer (SP)
|
100% |
17304
22.2 IPS |
|
Style Transfer (HP)
|
100% |
119949
154.2 IPS |
|
Style Transfer (Q)
|
96% |
113225
146.1 IPS |
|
Image Super-Resolution (SP)
|
100% |
3814
140.8 IPS |
|
Image Super-Resolution (HP)
|
100% |
23288
859.9 IPS |
|
Image Super-Resolution (Q)
|
99% |
23679
874.3 IPS |
|
Text Classification (SP)
|
100% |
2309
3.08 KIPS |
|
Text Classification (HP)
|
100% |
4009
5.35 KIPS |
|
Text Classification (Q)
|
93% |
3947
5.30 KIPS |
|
Machine Translation (SP)
|
100% |
2542
43.8 IPS |
|
Machine Translation (HP)
|
100% |
5681
97.9 IPS |
|
Machine Translation (Q)
|
98% |
6078
105.0 IPS |