User | EdwinValdezEXD |
Upload Date | November 20 2024 11:48 PM |
Views | 4 |
AI Information | |
---|---|
Framework | Core ML |
Backend | GPU |
Device | Apple M1 |
System Information | |
---|---|
Operating System | iOS 18.2 |
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% |
2266
421.4 IPS |
|
Image Classification (HP)
|
100% |
2090
388.7 IPS |
|
Image Classification (Q)
|
97% |
1976
368.8 IPS |
|
Image Segmentation (SP)
|
100% |
2697
43.7 IPS |
|
Image Segmentation (HP)
|
100% |
3646
59.1 IPS |
|
Image Segmentation (Q)
|
99% |
3687
59.8 IPS |
|
Pose Estimation (SP)
|
100% |
16892
19.7 IPS |
|
Pose Estimation (HP)
|
100% |
18272
21.3 IPS |
|
Pose Estimation (Q)
|
95% |
17145
20.1 IPS |
|
Object Detection (SP)
|
100% |
2728
216.3 IPS |
|
Object Detection (HP)
|
100% |
2730
216.6 IPS |
|
Object Detection (Q)
|
91% |
2287
182.7 IPS |
|
Face Detection (SP)
|
100% |
6810
80.9 IPS |
|
Face Detection (HP)
|
100% |
8492
100.9 IPS |
|
Face Detection (Q)
|
100% |
5803
69.0 IPS |
|
Depth Estimation (SP)
|
100% |
12046
92.8 IPS |
|
Depth Estimation (HP)
|
99% |
13619
104.9 IPS |
|
Depth Estimation (Q)
|
85% |
11392
89.0 IPS |
|
Style Transfer (SP)
|
100% |
28897
37.1 IPS |
|
Style Transfer (HP)
|
100% |
35034
45.0 IPS |
|
Style Transfer (Q)
|
96% |
32587
42.1 IPS |
|
Image Super-Resolution (SP)
|
100% |
6433
237.5 IPS |
|
Image Super-Resolution (HP)
|
100% |
7091
261.8 IPS |
|
Image Super-Resolution (Q)
|
99% |
5295
195.5 IPS |
|
Text Classification (SP)
|
100% |
2305
3.08 KIPS |
|
Text Classification (HP)
|
100% |
4034
5.38 KIPS |
|
Text Classification (Q)
|
93% |
3946
5.30 KIPS |
|
Machine Translation (SP)
|
100% |
873
15.0 IPS |
|
Machine Translation (HP)
|
100% |
861
14.8 IPS |
|
Machine Translation (Q)
|
98% |
847
14.6 IPS |