User | EdwinValdezEXD |
Upload Date | December 04 2024 04:47 PM |
Views | 3 |
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% |
2071
385.2 IPS |
|
Image Classification (HP)
|
100% |
1940
360.8 IPS |
|
Image Classification (Q)
|
97% |
1853
345.9 IPS |
|
Image Segmentation (SP)
|
100% |
2700
43.8 IPS |
|
Image Segmentation (HP)
|
100% |
3616
58.6 IPS |
|
Image Segmentation (Q)
|
99% |
3697
59.9 IPS |
|
Pose Estimation (SP)
|
100% |
16554
19.3 IPS |
|
Pose Estimation (HP)
|
100% |
18339
21.4 IPS |
|
Pose Estimation (Q)
|
95% |
16813
19.7 IPS |
|
Object Detection (SP)
|
100% |
2692
213.5 IPS |
|
Object Detection (HP)
|
100% |
2685
213.0 IPS |
|
Object Detection (Q)
|
91% |
2192
175.2 IPS |
|
Face Detection (SP)
|
100% |
6784
80.6 IPS |
|
Face Detection (HP)
|
100% |
8438
100.3 IPS |
|
Face Detection (Q)
|
100% |
6089
72.4 IPS |
|
Depth Estimation (SP)
|
100% |
12017
92.6 IPS |
|
Depth Estimation (HP)
|
99% |
13589
104.7 IPS |
|
Depth Estimation (Q)
|
85% |
11348
88.7 IPS |
|
Style Transfer (SP)
|
100% |
28610
36.8 IPS |
|
Style Transfer (HP)
|
100% |
34986
45.0 IPS |
|
Style Transfer (Q)
|
96% |
30995
40.0 IPS |
|
Image Super-Resolution (SP)
|
100% |
6300
232.6 IPS |
|
Image Super-Resolution (HP)
|
100% |
7016
259.1 IPS |
|
Image Super-Resolution (Q)
|
99% |
5303
195.8 IPS |
|
Text Classification (SP)
|
100% |
2216
2.96 KIPS |
|
Text Classification (HP)
|
100% |
3729
4.98 KIPS |
|
Text Classification (Q)
|
93% |
3696
4.96 KIPS |
|
Machine Translation (SP)
|
100% |
839
14.4 IPS |
|
Machine Translation (HP)
|
100% |
817
14.1 IPS |
|
Machine Translation (Q)
|
98% |
821
14.2 IPS |