User | saiht |
Upload Date | August 15 2024 09:17 PM |
Views | 14 |
AI Information | |
---|---|
Framework | Core ML |
Backend | Neural Engine |
Device | Apple M1 |
System Information | |
---|---|
Operating System | iOS 17.5.1 |
Model | iPad Pro (11-inch 3rd generation) |
Model ID | iPad13,6 |
Motherboard | J518AP |
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 | 7.33 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
1079
200.7 IPS |
|
Image Classification (HP)
|
100% |
6313
1.17 KIPS |
|
Image Classification (Q)
|
99% |
6405
1.19 KIPS |
|
Image Segmentation (SP)
|
100% |
674
10.9 IPS |
|
Image Segmentation (HP)
|
100% |
4290
69.5 IPS |
|
Image Segmentation (Q)
|
100% |
4245
68.8 IPS |
|
Pose Estimation (SP)
|
100% |
5742
6.70 IPS |
|
Pose Estimation (HP)
|
100% |
65090
75.9 IPS |
|
Pose Estimation (Q)
|
94% |
63852
74.9 IPS |
|
Object Detection (SP)
|
100% |
1184
93.9 IPS |
|
Object Detection (HP)
|
99% |
7166
570.1 IPS |
|
Object Detection (Q)
|
93% |
6525
520.7 IPS |
|
Face Detection (SP)
|
100% |
2110
25.1 IPS |
|
Face Detection (HP)
|
100% |
12462
148.1 IPS |
|
Face Detection (Q)
|
100% |
12740
151.4 IPS |
|
Depth Estimation (SP)
|
100% |
3841
29.6 IPS |
|
Depth Estimation (HP)
|
99% |
43262
333.3 IPS |
|
Depth Estimation (Q)
|
97% |
46213
357.3 IPS |
|
Style Transfer (SP)
|
100% |
10310
13.3 IPS |
|
Style Transfer (HP)
|
100% |
116596
149.9 IPS |
|
Style Transfer (Q)
|
100% |
122082
156.9 IPS |
|
Image Super-Resolution (SP)
|
100% |
2847
105.1 IPS |
|
Image Super-Resolution (HP)
|
100% |
17662
652.2 IPS |
|
Image Super-Resolution (Q)
|
98% |
20759
769.1 IPS |
|
Text Classification (SP)
|
100% |
1283
1.71 KIPS |
|
Text Classification (HP)
|
100% |
2782
3.71 KIPS |
|
Text Classification (Q)
|
93% |
2902
3.89 KIPS |
|
Machine Translation (SP)
|
100% |
1345
23.2 IPS |
|
Machine Translation (HP)
|
100% |
2251
38.8 IPS |
|
Machine Translation (Q)
|
98% |
2239
38.7 IPS |