User | Hulkstern |
Upload Date | September 02 2024 03:50 PM |
Views | 7 |
AI Information | |
---|---|
Framework | Core ML |
Backend | GPU |
Device | Apple M1 |
System Information | |
---|---|
Operating System | iOS 18.1 |
Model | iPad Pro (12.9-inch 5th generation) |
Model ID | iPad13,10 |
Motherboard | J523AP |
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% |
1925
358.1 IPS |
|
Image Classification (HP)
|
100% |
2124
395.0 IPS |
|
Image Classification (Q)
|
99% |
2069
385.8 IPS |
|
Image Segmentation (SP)
|
100% |
2697
43.7 IPS |
|
Image Segmentation (HP)
|
100% |
3633
58.9 IPS |
|
Image Segmentation (Q)
|
100% |
3593
58.2 IPS |
|
Pose Estimation (SP)
|
100% |
16934
19.8 IPS |
|
Pose Estimation (HP)
|
100% |
18350
21.4 IPS |
|
Pose Estimation (Q)
|
97% |
16357
19.2 IPS |
|
Object Detection (SP)
|
100% |
2719
215.7 IPS |
|
Object Detection (HP)
|
100% |
2730
216.5 IPS |
|
Object Detection (Q)
|
91% |
2145
171.4 IPS |
|
Face Detection (SP)
|
100% |
6770
80.4 IPS |
|
Face Detection (HP)
|
100% |
8413
100.0 IPS |
|
Face Detection (Q)
|
100% |
5853
69.5 IPS |
|
Depth Estimation (SP)
|
100% |
12291
94.7 IPS |
|
Depth Estimation (HP)
|
99% |
13644
105.1 IPS |
|
Depth Estimation (Q)
|
97% |
1931
14.9 IPS |
|
Style Transfer (SP)
|
100% |
28542
36.7 IPS |
|
Style Transfer (HP)
|
100% |
34620
44.5 IPS |
|
Style Transfer (Q)
|
100% |
35049
45.1 IPS |
|
Image Super-Resolution (SP)
|
100% |
6412
236.8 IPS |
|
Image Super-Resolution (HP)
|
100% |
7136
263.5 IPS |
|
Image Super-Resolution (Q)
|
98% |
5226
193.6 IPS |
|
Text Classification (SP)
|
100% |
2302
3.07 KIPS |
|
Text Classification (HP)
|
100% |
3956
5.28 KIPS |
|
Text Classification (Q)
|
93% |
3947
5.30 KIPS |
|
Machine Translation (SP)
|
100% |
877
15.1 IPS |
|
Machine Translation (HP)
|
100% |
851
14.7 IPS |
|
Machine Translation (Q)
|
98% |
919
15.9 IPS |