User | asymptotepmo |
Upload Date | August 16 2024 09:12 AM |
Views | 7 |
AI Information | |
---|---|
Framework | Core ML |
Backend | Neural Engine |
Device | Apple M2 |
System Information | |
---|---|
Operating System | iOS 17.6.1 |
Model | iPad Pro (12.9-inch, 6th generation) |
Model ID | iPad14,5 |
Motherboard | J620AP |
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 | 7.31 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
1249
232.2 IPS |
|
Image Classification (HP)
|
100% |
7278
1.35 KIPS |
|
Image Classification (Q)
|
99% |
7732
1.44 KIPS |
|
Image Segmentation (SP)
|
100% |
746
12.1 IPS |
|
Image Segmentation (HP)
|
100% |
5021
81.4 IPS |
|
Image Segmentation (Q)
|
100% |
4986
80.8 IPS |
|
Pose Estimation (SP)
|
100% |
5989
6.99 IPS |
|
Pose Estimation (HP)
|
100% |
86396
100.8 IPS |
|
Pose Estimation (Q)
|
94% |
88761
104.1 IPS |
|
Object Detection (SP)
|
100% |
1357
107.7 IPS |
|
Object Detection (HP)
|
99% |
8396
667.9 IPS |
|
Object Detection (Q)
|
93% |
9029
720.5 IPS |
|
Face Detection (SP)
|
100% |
2467
29.3 IPS |
|
Face Detection (HP)
|
100% |
11679
138.8 IPS |
|
Face Detection (Q)
|
100% |
13126
156.0 IPS |
|
Depth Estimation (SP)
|
100% |
4118
31.7 IPS |
|
Depth Estimation (HP)
|
99% |
48323
372.3 IPS |
|
Depth Estimation (Q)
|
97% |
54105
418.3 IPS |
|
Style Transfer (SP)
|
100% |
10977
14.1 IPS |
|
Style Transfer (HP)
|
100% |
137705
177.0 IPS |
|
Style Transfer (Q)
|
100% |
138128
177.6 IPS |
|
Image Super-Resolution (SP)
|
100% |
3160
116.7 IPS |
|
Image Super-Resolution (HP)
|
100% |
20122
743.0 IPS |
|
Image Super-Resolution (Q)
|
98% |
22807
845.0 IPS |
|
Text Classification (SP)
|
100% |
1210
1.62 KIPS |
|
Text Classification (HP)
|
100% |
796
1.06 KIPS |
|
Text Classification (Q)
|
93% |
790
1.06 KIPS |
|
Machine Translation (SP)
|
100% |
1593
27.4 IPS |
|
Machine Translation (HP)
|
100% |
2405
41.4 IPS |
|
Machine Translation (Q)
|
98% |
2415
41.7 IPS |