Upload Date | December 23 2024 10:57 PM |
Views | 1 |
AI Information | |
---|---|
Framework | Core ML |
Backend | Neural Engine |
Device | Apple M1 |
System Information | |
---|---|
Operating System | iOS 18.3 |
Model | iPad Pro (12.9-inch 5th generation) |
Model ID | iPad13,8 |
Motherboard | J522AP |
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 | 7.35 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
1388
258.0 IPS |
|
Image Classification (HP)
|
100% |
6134
1.14 KIPS |
|
Image Classification (Q)
|
96% |
5805
1.08 KIPS |
|
Image Segmentation (SP)
|
100% |
1407
22.8 IPS |
|
Image Segmentation (HP)
|
100% |
9716
157.5 IPS |
|
Image Segmentation (Q)
|
99% |
9999
162.1 IPS |
|
Pose Estimation (SP)
|
100% |
6525
7.61 IPS |
|
Pose Estimation (HP)
|
100% |
69117
80.6 IPS |
|
Pose Estimation (Q)
|
95% |
65955
77.3 IPS |
|
Object Detection (SP)
|
100% |
1509
119.7 IPS |
|
Object Detection (HP)
|
99% |
7272
578.5 IPS |
|
Object Detection (Q)
|
91% |
6712
536.3 IPS |
|
Face Detection (SP)
|
100% |
3052
36.3 IPS |
|
Face Detection (HP)
|
100% |
16559
196.8 IPS |
|
Face Detection (Q)
|
100% |
15264
181.4 IPS |
|
Depth Estimation (SP)
|
100% |
5804
44.7 IPS |
|
Depth Estimation (HP)
|
99% |
47365
364.9 IPS |
|
Depth Estimation (Q)
|
85% |
48220
376.8 IPS |
|
Style Transfer (SP)
|
100% |
17221
22.1 IPS |
|
Style Transfer (HP)
|
100% |
119821
154.0 IPS |
|
Style Transfer (Q)
|
96% |
114793
148.1 IPS |
|
Image Super-Resolution (SP)
|
100% |
3775
139.4 IPS |
|
Image Super-Resolution (HP)
|
100% |
23510
868.1 IPS |
|
Image Super-Resolution (Q)
|
99% |
23558
869.9 IPS |
|
Text Classification (SP)
|
100% |
2296
3.06 KIPS |
|
Text Classification (HP)
|
100% |
3970
5.30 KIPS |
|
Text Classification (Q)
|
93% |
3955
5.31 KIPS |
|
Machine Translation (SP)
|
100% |
2506
43.2 IPS |
|
Machine Translation (HP)
|
100% |
3579
61.7 IPS |
|
Machine Translation (Q)
|
98% |
3702
64.0 IPS |