User | ElementalOwl |
Upload Date | October 31 2024 11:41 PM |
Views | 6 |
AI Information | |
---|---|
Framework | Core ML |
Backend | Neural Engine |
Device | Apple M1 |
System Information | |
---|---|
Operating System | iOS 18.1 |
Model | iPad Air (5th generation) |
Model ID | iPad13,16 |
Motherboard | J407AP |
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 | 7.47 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
1403
260.8 IPS |
|
Image Classification (HP)
|
100% |
5951
1.11 KIPS |
|
Image Classification (Q)
|
96% |
6000
1.12 KIPS |
|
Image Segmentation (SP)
|
100% |
1436
23.3 IPS |
|
Image Segmentation (HP)
|
100% |
9738
157.9 IPS |
|
Image Segmentation (Q)
|
99% |
10113
163.9 IPS |
|
Pose Estimation (SP)
|
100% |
6527
7.62 IPS |
|
Pose Estimation (HP)
|
100% |
70132
81.8 IPS |
|
Pose Estimation (Q)
|
95% |
66198
77.6 IPS |
|
Object Detection (SP)
|
100% |
1505
119.4 IPS |
|
Object Detection (HP)
|
99% |
7217
574.1 IPS |
|
Object Detection (Q)
|
91% |
6599
527.3 IPS |
|
Face Detection (SP)
|
100% |
3044
36.2 IPS |
|
Face Detection (HP)
|
100% |
16559
196.8 IPS |
|
Face Detection (Q)
|
100% |
15150
180.0 IPS |
|
Depth Estimation (SP)
|
100% |
5814
44.8 IPS |
|
Depth Estimation (HP)
|
99% |
47226
363.8 IPS |
|
Depth Estimation (Q)
|
85% |
47266
369.4 IPS |
|
Style Transfer (SP)
|
100% |
17117
22.0 IPS |
|
Style Transfer (HP)
|
100% |
119816
154.0 IPS |
|
Style Transfer (Q)
|
96% |
111742
144.2 IPS |
|
Image Super-Resolution (SP)
|
100% |
3740
138.1 IPS |
|
Image Super-Resolution (HP)
|
100% |
22920
846.3 IPS |
|
Image Super-Resolution (Q)
|
99% |
23548
869.5 IPS |
|
Text Classification (SP)
|
100% |
2275
3.04 KIPS |
|
Text Classification (HP)
|
100% |
3726
4.97 KIPS |
|
Text Classification (Q)
|
93% |
3714
4.98 KIPS |
|
Machine Translation (SP)
|
100% |
2451
42.2 IPS |
|
Machine Translation (HP)
|
100% |
5153
88.8 IPS |
|
Machine Translation (Q)
|
98% |
5453
94.2 IPS |