User | wangshuy |
Upload Date | September 12 2024 07:47 AM |
Views | 6 |
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 | iPad13,6 |
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 | 7.37 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
1390
258.4 IPS |
|
Image Classification (HP)
|
100% |
6202
1.15 KIPS |
|
Image Classification (Q)
|
96% |
5821
1.09 KIPS |
|
Image Segmentation (SP)
|
100% |
1367
22.2 IPS |
|
Image Segmentation (HP)
|
100% |
6647
107.7 IPS |
|
Image Segmentation (Q)
|
99% |
6774
109.8 IPS |
|
Pose Estimation (SP)
|
100% |
6520
7.61 IPS |
|
Pose Estimation (HP)
|
100% |
68193
79.6 IPS |
|
Pose Estimation (Q)
|
95% |
65615
76.9 IPS |
|
Object Detection (SP)
|
100% |
1511
119.9 IPS |
|
Object Detection (HP)
|
99% |
7288
579.7 IPS |
|
Object Detection (Q)
|
91% |
6706
535.9 IPS |
|
Face Detection (SP)
|
100% |
3021
35.9 IPS |
|
Face Detection (HP)
|
100% |
16106
191.4 IPS |
|
Face Detection (Q)
|
100% |
14983
178.0 IPS |
|
Depth Estimation (SP)
|
100% |
5781
44.5 IPS |
|
Depth Estimation (HP)
|
99% |
47511
366.0 IPS |
|
Depth Estimation (Q)
|
85% |
47399
370.4 IPS |
|
Style Transfer (SP)
|
100% |
17062
21.9 IPS |
|
Style Transfer (HP)
|
100% |
120028
154.3 IPS |
|
Style Transfer (Q)
|
96% |
111948
144.5 IPS |
|
Image Super-Resolution (SP)
|
100% |
3756
138.7 IPS |
|
Image Super-Resolution (HP)
|
100% |
22935
846.9 IPS |
|
Image Super-Resolution (Q)
|
99% |
23786
878.3 IPS |
|
Text Classification (SP)
|
100% |
2287
3.05 KIPS |
|
Text Classification (HP)
|
100% |
3835
5.12 KIPS |
|
Text Classification (Q)
|
93% |
3814
5.12 KIPS |
|
Machine Translation (SP)
|
100% |
2494
43.0 IPS |
|
Machine Translation (HP)
|
100% |
2288
39.4 IPS |
|
Machine Translation (Q)
|
98% |
2291
39.6 IPS |