User | MidniteMarv |
Upload Date | February 11 2025 03:47 PM |
Views | 7 |
AI Information | |
---|---|
Framework | Core ML |
Backend | Neural Engine |
Device | Apple M1 |
System Information | |
---|---|
Operating System | iOS 18.3 |
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% |
1404
261.1 IPS |
|
Image Classification (HP)
|
100% |
6264
1.16 KIPS |
|
Image Classification (Q)
|
96% |
5845
1.09 KIPS |
|
Image Segmentation (SP)
|
100% |
1382
22.4 IPS |
|
Image Segmentation (HP)
|
100% |
9736
157.8 IPS |
|
Image Segmentation (Q)
|
99% |
10080
163.4 IPS |
|
Pose Estimation (SP)
|
100% |
6544
7.64 IPS |
|
Pose Estimation (HP)
|
100% |
66839
78.0 IPS |
|
Pose Estimation (Q)
|
95% |
65562
76.8 IPS |
|
Object Detection (SP)
|
100% |
1518
120.4 IPS |
|
Object Detection (HP)
|
99% |
7101
564.8 IPS |
|
Object Detection (Q)
|
91% |
6623
529.2 IPS |
|
Face Detection (SP)
|
100% |
3040
36.1 IPS |
|
Face Detection (HP)
|
100% |
16477
195.8 IPS |
|
Face Detection (Q)
|
100% |
15299
181.8 IPS |
|
Depth Estimation (SP)
|
100% |
5842
45.0 IPS |
|
Depth Estimation (HP)
|
99% |
47191
363.6 IPS |
|
Depth Estimation (Q)
|
85% |
48470
378.8 IPS |
|
Style Transfer (SP)
|
100% |
17344
22.3 IPS |
|
Style Transfer (HP)
|
100% |
120057
154.3 IPS |
|
Style Transfer (Q)
|
96% |
112593
145.3 IPS |
|
Image Super-Resolution (SP)
|
100% |
3756
138.7 IPS |
|
Image Super-Resolution (HP)
|
100% |
22708
838.5 IPS |
|
Image Super-Resolution (Q)
|
99% |
23464
866.4 IPS |
|
Text Classification (SP)
|
100% |
2294
3.06 KIPS |
|
Text Classification (HP)
|
100% |
3877
5.18 KIPS |
|
Text Classification (Q)
|
93% |
3872
5.20 KIPS |
|
Machine Translation (SP)
|
100% |
2473
42.6 IPS |
|
Machine Translation (HP)
|
100% |
3632
62.6 IPS |
|
Machine Translation (Q)
|
98% |
3755
64.9 IPS |