User | raylee930 |
Upload Date | August 18 2024 09:32 AM |
Views | 6 |
AI Information | |
---|---|
Framework | Core ML |
Backend | Neural Engine |
Device | Apple M2 |
System Information | |
---|---|
Operating System | iOS 17.6.1 |
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 | 7.33 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
1254
233.1 IPS |
|
Image Classification (HP)
|
100% |
7286
1.35 KIPS |
|
Image Classification (Q)
|
99% |
7710
1.44 KIPS |
|
Image Segmentation (SP)
|
100% |
750
12.2 IPS |
|
Image Segmentation (HP)
|
100% |
5041
81.7 IPS |
|
Image Segmentation (Q)
|
100% |
5036
81.6 IPS |
|
Pose Estimation (SP)
|
100% |
5993
6.99 IPS |
|
Pose Estimation (HP)
|
100% |
87819
102.5 IPS |
|
Pose Estimation (Q)
|
94% |
86705
101.7 IPS |
|
Object Detection (SP)
|
100% |
1358
107.7 IPS |
|
Object Detection (HP)
|
99% |
8346
663.9 IPS |
|
Object Detection (Q)
|
93% |
8767
699.5 IPS |
|
Face Detection (SP)
|
100% |
2449
29.1 IPS |
|
Face Detection (HP)
|
100% |
11273
133.9 IPS |
|
Face Detection (Q)
|
100% |
13061
155.2 IPS |
|
Depth Estimation (SP)
|
100% |
4135
31.9 IPS |
|
Depth Estimation (HP)
|
99% |
47606
366.8 IPS |
|
Depth Estimation (Q)
|
97% |
51584
398.9 IPS |
|
Style Transfer (SP)
|
100% |
11042
14.2 IPS |
|
Style Transfer (HP)
|
100% |
138023
177.4 IPS |
|
Style Transfer (Q)
|
100% |
137438
176.7 IPS |
|
Image Super-Resolution (SP)
|
100% |
3142
116.0 IPS |
|
Image Super-Resolution (HP)
|
100% |
18962
700.2 IPS |
|
Image Super-Resolution (Q)
|
98% |
24828
919.9 IPS |
|
Text Classification (SP)
|
100% |
1189
1.59 KIPS |
|
Text Classification (HP)
|
100% |
799
1.07 KIPS |
|
Text Classification (Q)
|
93% |
796
1.07 KIPS |
|
Machine Translation (SP)
|
100% |
1610
27.7 IPS |
|
Machine Translation (HP)
|
100% |
2354
40.6 IPS |
|
Machine Translation (Q)
|
98% |
2346
40.5 IPS |