User | jayt |
Upload Date | September 29 2024 03:18 AM |
Views | 8 |
AI Information | |
---|---|
Framework | Core ML |
Backend | Neural Engine |
Device | Apple M1 |
System Information | |
---|---|
Operating System | iOS 18.1 |
Model | iPad Pro (12.9-inch 5th generation) |
Model ID | iPad13,8 |
Motherboard | J522AP |
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 | 7.35 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
1361
253.1 IPS |
|
Image Classification (HP)
|
100% |
6192
1.15 KIPS |
|
Image Classification (Q)
|
96% |
6020
1.12 KIPS |
|
Image Segmentation (SP)
|
100% |
1384
22.4 IPS |
|
Image Segmentation (HP)
|
100% |
9182
148.8 IPS |
|
Image Segmentation (Q)
|
99% |
9261
150.1 IPS |
|
Pose Estimation (SP)
|
100% |
6416
7.49 IPS |
|
Pose Estimation (HP)
|
100% |
66611
77.7 IPS |
|
Pose Estimation (Q)
|
95% |
63830
74.8 IPS |
|
Object Detection (SP)
|
100% |
1444
114.5 IPS |
|
Object Detection (HP)
|
99% |
7191
572.1 IPS |
|
Object Detection (Q)
|
91% |
6811
544.3 IPS |
|
Face Detection (SP)
|
100% |
3019
35.9 IPS |
|
Face Detection (HP)
|
100% |
16090
191.2 IPS |
|
Face Detection (Q)
|
100% |
15123
179.7 IPS |
|
Depth Estimation (SP)
|
100% |
5314
40.9 IPS |
|
Depth Estimation (HP)
|
99% |
45907
353.7 IPS |
|
Depth Estimation (Q)
|
85% |
48679
380.4 IPS |
|
Style Transfer (SP)
|
100% |
16804
21.6 IPS |
|
Style Transfer (HP)
|
100% |
115728
148.8 IPS |
|
Style Transfer (Q)
|
96% |
111304
143.6 IPS |
|
Image Super-Resolution (SP)
|
100% |
3450
127.4 IPS |
|
Image Super-Resolution (HP)
|
100% |
22687
837.7 IPS |
|
Image Super-Resolution (Q)
|
99% |
23565
870.2 IPS |
|
Text Classification (SP)
|
100% |
2183
2.91 KIPS |
|
Text Classification (HP)
|
100% |
3770
5.03 KIPS |
|
Text Classification (Q)
|
93% |
3775
5.07 KIPS |
|
Machine Translation (SP)
|
100% |
2366
40.8 IPS |
|
Machine Translation (HP)
|
100% |
2232
38.4 IPS |
|
Machine Translation (Q)
|
98% |
2295
39.7 IPS |