User | yasin9300 |
Upload Date | December 22 2024 09:39 AM |
Views | 1 |
AI Information | |
---|---|
Framework | Core ML |
Backend | Neural Engine |
Device | Apple M1 |
System Information | |
---|---|
Operating System | iOS 18.2 |
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% |
1405
261.3 IPS |
|
Image Classification (HP)
|
100% |
6288
1.17 KIPS |
|
Image Classification (Q)
|
96% |
5955
1.11 KIPS |
|
Image Segmentation (SP)
|
100% |
1388
22.5 IPS |
|
Image Segmentation (HP)
|
100% |
9774
158.4 IPS |
|
Image Segmentation (Q)
|
99% |
10164
164.8 IPS |
|
Pose Estimation (SP)
|
100% |
6545
7.64 IPS |
|
Pose Estimation (HP)
|
100% |
67177
78.4 IPS |
|
Pose Estimation (Q)
|
95% |
65853
77.2 IPS |
|
Object Detection (SP)
|
100% |
1515
120.1 IPS |
|
Object Detection (HP)
|
99% |
7355
585.1 IPS |
|
Object Detection (Q)
|
91% |
6714
536.5 IPS |
|
Face Detection (SP)
|
100% |
3050
36.2 IPS |
|
Face Detection (HP)
|
100% |
16514
196.2 IPS |
|
Face Detection (Q)
|
100% |
15315
182.0 IPS |
|
Depth Estimation (SP)
|
100% |
5778
44.5 IPS |
|
Depth Estimation (HP)
|
99% |
47219
363.8 IPS |
|
Depth Estimation (Q)
|
85% |
47722
372.9 IPS |
|
Style Transfer (SP)
|
100% |
17160
22.1 IPS |
|
Style Transfer (HP)
|
100% |
119879
154.1 IPS |
|
Style Transfer (Q)
|
96% |
112191
144.8 IPS |
|
Image Super-Resolution (SP)
|
100% |
3756
138.7 IPS |
|
Image Super-Resolution (HP)
|
100% |
23271
859.3 IPS |
|
Image Super-Resolution (Q)
|
99% |
24087
889.4 IPS |
|
Text Classification (SP)
|
100% |
2292
3.06 KIPS |
|
Text Classification (HP)
|
100% |
3934
5.25 KIPS |
|
Text Classification (Q)
|
93% |
3897
5.23 KIPS |
|
Machine Translation (SP)
|
100% |
2498
43.0 IPS |
|
Machine Translation (HP)
|
100% |
3230
55.6 IPS |
|
Machine Translation (Q)
|
98% |
3405
58.8 IPS |