User | waleriewitch |
Upload Date | October 17 2024 06:40 AM |
Views | 4 |
AI Information | |
---|---|
Framework | Core ML |
Backend | Neural Engine |
Device | Apple M1 |
System Information | |
---|---|
Operating System | iOS 18.0.1 |
Model | iPad Pro (11-inch 3rd generation) |
Model ID | iPad13,4 |
Motherboard | J517AP |
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 | 7.37 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
1408
261.9 IPS |
|
Image Classification (HP)
|
100% |
6372
1.19 KIPS |
|
Image Classification (Q)
|
96% |
5876
1.10 KIPS |
|
Image Segmentation (SP)
|
100% |
1389
22.5 IPS |
|
Image Segmentation (HP)
|
100% |
6634
107.5 IPS |
|
Image Segmentation (Q)
|
99% |
6770
109.7 IPS |
|
Pose Estimation (SP)
|
100% |
6543
7.63 IPS |
|
Pose Estimation (HP)
|
100% |
68000
79.3 IPS |
|
Pose Estimation (Q)
|
95% |
65783
77.1 IPS |
|
Object Detection (SP)
|
100% |
1516
120.2 IPS |
|
Object Detection (HP)
|
99% |
7211
573.6 IPS |
|
Object Detection (Q)
|
91% |
6665
532.5 IPS |
|
Face Detection (SP)
|
100% |
3056
36.3 IPS |
|
Face Detection (HP)
|
100% |
16450
195.5 IPS |
|
Face Detection (Q)
|
100% |
15239
181.1 IPS |
|
Depth Estimation (SP)
|
100% |
5821
44.8 IPS |
|
Depth Estimation (HP)
|
99% |
47239
363.9 IPS |
|
Depth Estimation (Q)
|
85% |
48413
378.3 IPS |
|
Style Transfer (SP)
|
100% |
17116
22.0 IPS |
|
Style Transfer (HP)
|
100% |
119717
153.9 IPS |
|
Style Transfer (Q)
|
96% |
111139
143.4 IPS |
|
Image Super-Resolution (SP)
|
100% |
3724
137.5 IPS |
|
Image Super-Resolution (HP)
|
100% |
23147
854.7 IPS |
|
Image Super-Resolution (Q)
|
99% |
23745
876.8 IPS |
|
Text Classification (SP)
|
100% |
2284
3.05 KIPS |
|
Text Classification (HP)
|
100% |
3790
5.06 KIPS |
|
Text Classification (Q)
|
93% |
3763
5.05 KIPS |
|
Machine Translation (SP)
|
100% |
2473
42.6 IPS |
|
Machine Translation (HP)
|
100% |
2340
40.3 IPS |
|
Machine Translation (Q)
|
98% |
2320
40.1 IPS |