Upload Date | September 18 2024 03:19 PM |
Views | 1 |
AI Information | |
---|---|
Framework | Core ML |
Backend | Neural Engine |
Device | Apple M1 |
System Information | |
---|---|
Operating System | iOS 18.0 |
Model | iPad Pro (11-inch 3rd generation) |
Model ID | iPad13,5 |
Motherboard | J517xAP |
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 | 15.37 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
1405
261.4 IPS |
|
Image Classification (HP)
|
100% |
6272
1.17 KIPS |
|
Image Classification (Q)
|
96% |
5861
1.09 KIPS |
|
Image Segmentation (SP)
|
100% |
1412
22.9 IPS |
|
Image Segmentation (HP)
|
100% |
6632
107.5 IPS |
|
Image Segmentation (Q)
|
99% |
6741
109.3 IPS |
|
Pose Estimation (SP)
|
100% |
6524
7.61 IPS |
|
Pose Estimation (HP)
|
100% |
68011
79.4 IPS |
|
Pose Estimation (Q)
|
95% |
65541
76.8 IPS |
|
Object Detection (SP)
|
100% |
1514
120.1 IPS |
|
Object Detection (HP)
|
99% |
7459
593.3 IPS |
|
Object Detection (Q)
|
91% |
6882
549.9 IPS |
|
Face Detection (SP)
|
100% |
3022
35.9 IPS |
|
Face Detection (HP)
|
100% |
16241
193.0 IPS |
|
Face Detection (Q)
|
100% |
15089
179.3 IPS |
|
Depth Estimation (SP)
|
100% |
5801
44.7 IPS |
|
Depth Estimation (HP)
|
99% |
48344
372.5 IPS |
|
Depth Estimation (Q)
|
85% |
48381
378.1 IPS |
|
Style Transfer (SP)
|
100% |
17353
22.3 IPS |
|
Style Transfer (HP)
|
100% |
120391
154.8 IPS |
|
Style Transfer (Q)
|
96% |
114125
147.3 IPS |
|
Image Super-Resolution (SP)
|
100% |
3809
140.6 IPS |
|
Image Super-Resolution (HP)
|
100% |
22569
833.4 IPS |
|
Image Super-Resolution (Q)
|
99% |
22983
848.6 IPS |
|
Text Classification (SP)
|
100% |
2296
3.06 KIPS |
|
Text Classification (HP)
|
100% |
4070
5.43 KIPS |
|
Text Classification (Q)
|
93% |
4051
5.44 KIPS |
|
Machine Translation (SP)
|
100% |
2593
44.7 IPS |
|
Machine Translation (HP)
|
100% |
2290
39.5 IPS |
|
Machine Translation (Q)
|
98% |
2288
39.5 IPS |