User | Betancd |
Upload Date | September 07 2024 01:28 AM |
Views | 4 |
AI Information | |
---|---|
Framework | Core ML |
Backend | Neural Engine |
Device | Apple M1 |
System Information | |
---|---|
Operating System | iOS 17.6.1 |
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 | 15.33 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
1077
200.4 IPS |
|
Image Classification (HP)
|
100% |
6504
1.21 KIPS |
|
Image Classification (Q)
|
96% |
5703
1.07 KIPS |
|
Image Segmentation (SP)
|
100% |
684
11.1 IPS |
|
Image Segmentation (HP)
|
100% |
4225
68.5 IPS |
|
Image Segmentation (Q)
|
99% |
518
8.40 IPS |
|
Pose Estimation (SP)
|
100% |
5741
6.70 IPS |
|
Pose Estimation (HP)
|
100% |
65391
76.3 IPS |
|
Pose Estimation (Q)
|
95% |
64514
75.6 IPS |
|
Object Detection (SP)
|
100% |
1178
93.5 IPS |
|
Object Detection (HP)
|
99% |
7062
561.8 IPS |
|
Object Detection (Q)
|
93% |
6486
517.6 IPS |
|
Face Detection (SP)
|
100% |
2129
25.3 IPS |
|
Face Detection (HP)
|
100% |
12502
148.6 IPS |
|
Face Detection (Q)
|
100% |
12760
151.6 IPS |
|
Depth Estimation (SP)
|
100% |
3840
29.6 IPS |
|
Depth Estimation (HP)
|
99% |
43319
333.7 IPS |
|
Depth Estimation (Q)
|
85% |
51225
400.3 IPS |
|
Style Transfer (SP)
|
100% |
10298
13.2 IPS |
|
Style Transfer (HP)
|
100% |
116656
150.0 IPS |
|
Style Transfer (Q)
|
96% |
111095
143.4 IPS |
|
Image Super-Resolution (SP)
|
100% |
2849
105.2 IPS |
|
Image Super-Resolution (HP)
|
100% |
17868
659.8 IPS |
|
Image Super-Resolution (Q)
|
99% |
20543
758.5 IPS |
|
Text Classification (SP)
|
100% |
1270
1.69 KIPS |
|
Text Classification (HP)
|
100% |
2487
3.32 KIPS |
|
Text Classification (Q)
|
93% |
2594
3.48 KIPS |
|
Machine Translation (SP)
|
100% |
1342
23.1 IPS |
|
Machine Translation (HP)
|
100% |
2279
39.3 IPS |
|
Machine Translation (Q)
|
98% |
2259
39.0 IPS |