User | EdwinValdezEXD |
Upload Date | December 07 2024 11:56 AM |
Views | 2 |
AI Information | |
---|---|
Framework | Core ML |
Backend | GPU |
Device | Apple M1 |
System Information | |
---|---|
Operating System | iOS 18.2 |
Model | iPad Pro (11-inch 3rd generation) |
Model ID | iPad13,6 |
Motherboard | J518AP |
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% |
2304
428.5 IPS |
|
Image Classification (HP)
|
100% |
1918
356.8 IPS |
|
Image Classification (Q)
|
97% |
2034
379.6 IPS |
|
Image Segmentation (SP)
|
100% |
2719
44.1 IPS |
|
Image Segmentation (HP)
|
100% |
3645
59.1 IPS |
|
Image Segmentation (Q)
|
99% |
3711
60.2 IPS |
|
Pose Estimation (SP)
|
100% |
16595
19.4 IPS |
|
Pose Estimation (HP)
|
100% |
18555
21.7 IPS |
|
Pose Estimation (Q)
|
95% |
16913
19.8 IPS |
|
Object Detection (SP)
|
100% |
2727
216.3 IPS |
|
Object Detection (HP)
|
100% |
2753
218.4 IPS |
|
Object Detection (Q)
|
91% |
2232
178.4 IPS |
|
Face Detection (SP)
|
100% |
6529
77.6 IPS |
|
Face Detection (HP)
|
100% |
8492
100.9 IPS |
|
Face Detection (Q)
|
100% |
6091
72.4 IPS |
|
Depth Estimation (SP)
|
100% |
12069
93.0 IPS |
|
Depth Estimation (HP)
|
99% |
13691
105.5 IPS |
|
Depth Estimation (Q)
|
85% |
11457
89.6 IPS |
|
Style Transfer (SP)
|
100% |
28929
37.2 IPS |
|
Style Transfer (HP)
|
100% |
34861
44.8 IPS |
|
Style Transfer (Q)
|
96% |
32022
41.3 IPS |
|
Image Super-Resolution (SP)
|
100% |
6386
235.8 IPS |
|
Image Super-Resolution (HP)
|
100% |
7166
264.6 IPS |
|
Image Super-Resolution (Q)
|
99% |
5325
196.6 IPS |
|
Text Classification (SP)
|
100% |
2290
3.06 KIPS |
|
Text Classification (HP)
|
100% |
3984
5.32 KIPS |
|
Text Classification (Q)
|
93% |
3979
5.34 KIPS |
|
Machine Translation (SP)
|
100% |
836
14.4 IPS |
|
Machine Translation (HP)
|
100% |
837
14.4 IPS |
|
Machine Translation (Q)
|
98% |
844
14.6 IPS |