User | sichunlam |
Upload Date | August 15 2024 11:39 PM |
Views | 6 |
AI Information | |
---|---|
Framework | Core ML |
Backend | Neural Engine |
Device | Apple A12Z Bionic |
System Information | |
---|---|
Operating System | iOS 17.6.1 |
Model | iPad Pro 11-inch (2nd generation) |
Model ID | iPad8,9 |
Motherboard | J417AP |
CPU Information | |
---|---|
Name | Apple A12Z Bionic |
Topology | 1 Processor, 8 Cores |
Identifier | ARM |
Base Frequency | 2.49 GHz |
Cluster 1 | 4 Cores |
Cluster 2 | 4 Cores |
Memory Information | |
---|---|
Size | 5.56 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
349
64.9 IPS |
|
Image Classification (HP)
|
100% |
2438
453.3 IPS |
|
Image Classification (Q)
|
99% |
2373
442.6 IPS |
|
Image Segmentation (SP)
|
100% |
298
4.83 IPS |
|
Image Segmentation (HP)
|
100% |
417
6.76 IPS |
|
Image Segmentation (Q)
|
100% |
411
6.67 IPS |
|
Pose Estimation (SP)
|
100% |
2198
2.56 IPS |
|
Pose Estimation (HP)
|
100% |
27905
32.6 IPS |
|
Pose Estimation (Q)
|
94% |
1494
1.75 IPS |
|
Object Detection (SP)
|
100% |
389
30.9 IPS |
|
Object Detection (HP)
|
100% |
1449
114.9 IPS |
|
Object Detection (Q)
|
94% |
211
16.9 IPS |
|
Face Detection (SP)
|
100% |
860
10.2 IPS |
|
Face Detection (HP)
|
100% |
6569
78.1 IPS |
|
Face Detection (Q)
|
100% |
301
3.58 IPS |
|
Depth Estimation (SP)
|
100% |
1052
8.10 IPS |
|
Depth Estimation (HP)
|
99% |
22929
176.7 IPS |
|
Depth Estimation (Q)
|
97% |
23764
183.7 IPS |
|
Style Transfer (SP)
|
100% |
3529
4.54 IPS |
|
Style Transfer (HP)
|
100% |
3483
4.48 IPS |
|
Style Transfer (Q)
|
100% |
3494
4.49 IPS |
|
Image Super-Resolution (SP)
|
100% |
965
35.6 IPS |
|
Image Super-Resolution (HP)
|
100% |
3627
133.9 IPS |
|
Image Super-Resolution (Q)
|
98% |
496
18.4 IPS |
|
Text Classification (SP)
|
100% |
272
363.1 IPS |
|
Text Classification (HP)
|
100% |
302
403.2 IPS |
|
Text Classification (Q)
|
93% |
306
410.9 IPS |
|
Machine Translation (SP)
|
100% |
480
8.26 IPS |
|
Machine Translation (HP)
|
100% |
366
6.30 IPS |
|
Machine Translation (Q)
|
98% |
364
6.29 IPS |