Upload Date | October 19 2024 04:23 PM |
Views | 22 |
AI Information | |
---|---|
Framework | Core ML |
Backend | Neural Engine |
Device | Apple M2 |
System Information | |
---|---|
Operating System | iOS 18.1 |
Model | iPad Pro (11-inch, 4th generation) |
Model ID | iPad14,3 |
Motherboard | J617AP |
CPU Information | |
---|---|
Name | Apple M2 |
Topology | 1 Processor, 8 Cores |
Identifier | ARM |
Base Frequency | 3.49 GHz |
Cluster 1 | 4 Cores |
Cluster 2 | 4 Cores |
Memory Information | |
---|---|
Size | 7.37 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
1370
254.8 IPS |
|
Image Classification (HP)
|
100% |
14532
2.70 KIPS |
|
Image Classification (Q)
|
96% |
14935
2.79 KIPS |
|
Image Segmentation (SP)
|
100% |
1506
24.4 IPS |
|
Image Segmentation (HP)
|
100% |
18973
307.6 IPS |
|
Image Segmentation (Q)
|
99% |
23649
383.4 IPS |
|
Pose Estimation (SP)
|
100% |
6807
7.94 IPS |
|
Pose Estimation (HP)
|
100% |
105138
122.7 IPS |
|
Pose Estimation (Q)
|
95% |
104341
122.3 IPS |
|
Object Detection (SP)
|
100% |
1549
122.9 IPS |
|
Object Detection (HP)
|
99% |
14961
1.19 KIPS |
|
Object Detection (Q)
|
91% |
16835
1.35 KIPS |
|
Face Detection (SP)
|
100% |
3104
36.9 IPS |
|
Face Detection (HP)
|
100% |
32756
389.2 IPS |
|
Face Detection (Q)
|
100% |
41390
491.8 IPS |
|
Depth Estimation (SP)
|
100% |
5619
43.3 IPS |
|
Depth Estimation (HP)
|
99% |
84449
650.6 IPS |
|
Depth Estimation (Q)
|
85% |
102937
804.4 IPS |
|
Style Transfer (SP)
|
100% |
18679
24.0 IPS |
|
Style Transfer (HP)
|
100% |
199558
256.5 IPS |
|
Style Transfer (Q)
|
96% |
187444
241.9 IPS |
|
Image Super-Resolution (SP)
|
100% |
4044
149.3 IPS |
|
Image Super-Resolution (HP)
|
100% |
37780
1.40 KIPS |
|
Image Super-Resolution (Q)
|
99% |
45667
1.69 KIPS |
|
Text Classification (SP)
|
100% |
2201
2.94 KIPS |
|
Text Classification (HP)
|
100% |
3690
4.93 KIPS |
|
Text Classification (Q)
|
93% |
3688
4.95 KIPS |
|
Machine Translation (SP)
|
100% |
3554
61.2 IPS |
|
Machine Translation (HP)
|
100% |
6692
115.3 IPS |
|
Machine Translation (Q)
|
98% |
7335
126.8 IPS |