Upload Date | August 16 2024 04:04 PM |
Views | 17 |
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 | iPad13,4 |
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 | 7.33 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
1084
201.5 IPS |
|
Image Classification (HP)
|
100% |
6307
1.17 KIPS |
|
Image Classification (Q)
|
99% |
6426
1.20 KIPS |
|
Image Segmentation (SP)
|
100% |
695
11.3 IPS |
|
Image Segmentation (HP)
|
100% |
4105
66.5 IPS |
|
Image Segmentation (Q)
|
100% |
4087
66.3 IPS |
|
Pose Estimation (SP)
|
100% |
5761
6.72 IPS |
|
Pose Estimation (HP)
|
100% |
64860
75.7 IPS |
|
Pose Estimation (Q)
|
94% |
64021
75.1 IPS |
|
Object Detection (SP)
|
100% |
1182
93.7 IPS |
|
Object Detection (HP)
|
99% |
7184
571.5 IPS |
|
Object Detection (Q)
|
93% |
6482
517.2 IPS |
|
Face Detection (SP)
|
100% |
2136
25.4 IPS |
|
Face Detection (HP)
|
100% |
12479
148.3 IPS |
|
Face Detection (Q)
|
100% |
12744
151.4 IPS |
|
Depth Estimation (SP)
|
100% |
3829
29.5 IPS |
|
Depth Estimation (HP)
|
99% |
43407
334.4 IPS |
|
Depth Estimation (Q)
|
97% |
46812
362.0 IPS |
|
Style Transfer (SP)
|
100% |
10362
13.3 IPS |
|
Style Transfer (HP)
|
100% |
116792
150.1 IPS |
|
Style Transfer (Q)
|
100% |
123587
158.9 IPS |
|
Image Super-Resolution (SP)
|
100% |
2853
105.3 IPS |
|
Image Super-Resolution (HP)
|
100% |
17871
659.9 IPS |
|
Image Super-Resolution (Q)
|
98% |
20200
748.4 IPS |
|
Text Classification (SP)
|
100% |
1279
1.71 KIPS |
|
Text Classification (HP)
|
100% |
2501
3.34 KIPS |
|
Text Classification (Q)
|
93% |
2500
3.36 KIPS |
|
Machine Translation (SP)
|
100% |
1348
23.2 IPS |
|
Machine Translation (HP)
|
100% |
2263
39.0 IPS |
|
Machine Translation (Q)
|
98% |
2242
38.8 IPS |