User | bkr899 |
Upload Date | August 26 2024 07:35 PM |
Views | 6 |
AI Information | |
---|---|
Framework | Core ML |
Backend | Neural Engine |
Device | Apple M1 |
System Information | |
---|---|
Operating System | iOS 18.1 |
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% |
1406
261.4 IPS |
|
Image Classification (HP)
|
100% |
6270
1.17 KIPS |
|
Image Classification (Q)
|
99% |
6468
1.21 KIPS |
|
Image Segmentation (SP)
|
100% |
1391
22.6 IPS |
|
Image Segmentation (HP)
|
100% |
6167
100.0 IPS |
|
Image Segmentation (Q)
|
100% |
6173
100.1 IPS |
|
Pose Estimation (SP)
|
100% |
6526
7.61 IPS |
|
Pose Estimation (HP)
|
100% |
67447
78.7 IPS |
|
Pose Estimation (Q)
|
94% |
64973
76.2 IPS |
|
Object Detection (SP)
|
100% |
1520
120.6 IPS |
|
Object Detection (HP)
|
99% |
7112
565.7 IPS |
|
Object Detection (Q)
|
91% |
6700
535.3 IPS |
|
Face Detection (SP)
|
100% |
3061
36.4 IPS |
|
Face Detection (HP)
|
100% |
12725
151.2 IPS |
|
Face Detection (Q)
|
100% |
13782
163.8 IPS |
|
Depth Estimation (SP)
|
100% |
5817
44.8 IPS |
|
Depth Estimation (HP)
|
99% |
43375
334.2 IPS |
|
Depth Estimation (Q)
|
97% |
46132
356.7 IPS |
|
Style Transfer (SP)
|
100% |
17292
22.2 IPS |
|
Style Transfer (HP)
|
100% |
116661
150.0 IPS |
|
Style Transfer (Q)
|
100% |
122625
157.6 IPS |
|
Image Super-Resolution (SP)
|
100% |
3760
138.9 IPS |
|
Image Super-Resolution (HP)
|
100% |
23210
857.0 IPS |
|
Image Super-Resolution (Q)
|
98% |
23579
873.6 IPS |
|
Text Classification (SP)
|
100% |
2291
3.06 KIPS |
|
Text Classification (HP)
|
100% |
3920
5.23 KIPS |
|
Text Classification (Q)
|
93% |
3901
5.24 KIPS |
|
Machine Translation (SP)
|
100% |
2480
42.7 IPS |
|
Machine Translation (HP)
|
100% |
2337
40.3 IPS |
|
Machine Translation (Q)
|
98% |
2334
40.3 IPS |