User | vacantsouls |
Upload Date | August 17 2024 03:05 AM |
Views | 7 |
AI Information | |
---|---|
Framework | Core ML |
Backend | Neural Engine |
Device | Apple M1 |
System Information | |
---|---|
Operating System | iOS 17.6.1 |
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 | 7.31 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
1085
201.7 IPS |
|
Image Classification (HP)
|
100% |
6301
1.17 KIPS |
|
Image Classification (Q)
|
99% |
6550
1.22 KIPS |
|
Image Segmentation (SP)
|
100% |
694
11.2 IPS |
|
Image Segmentation (HP)
|
100% |
4213
68.3 IPS |
|
Image Segmentation (Q)
|
100% |
4225
68.5 IPS |
|
Pose Estimation (SP)
|
100% |
5760
6.72 IPS |
|
Pose Estimation (HP)
|
100% |
67372
78.6 IPS |
|
Pose Estimation (Q)
|
94% |
64389
75.5 IPS |
|
Object Detection (SP)
|
100% |
1187
94.1 IPS |
|
Object Detection (HP)
|
99% |
7167
570.1 IPS |
|
Object Detection (Q)
|
93% |
6757
539.1 IPS |
|
Face Detection (SP)
|
100% |
2137
25.4 IPS |
|
Face Detection (HP)
|
100% |
12585
149.5 IPS |
|
Face Detection (Q)
|
100% |
12942
153.8 IPS |
|
Depth Estimation (SP)
|
100% |
3816
29.4 IPS |
|
Depth Estimation (HP)
|
99% |
43379
334.2 IPS |
|
Depth Estimation (Q)
|
97% |
45316
350.4 IPS |
|
Style Transfer (SP)
|
100% |
10242
13.2 IPS |
|
Style Transfer (HP)
|
100% |
116978
150.4 IPS |
|
Style Transfer (Q)
|
100% |
123211
158.4 IPS |
|
Image Super-Resolution (SP)
|
100% |
2783
102.8 IPS |
|
Image Super-Resolution (HP)
|
100% |
17798
657.2 IPS |
|
Image Super-Resolution (Q)
|
98% |
20443
757.4 IPS |
|
Text Classification (SP)
|
100% |
1255
1.67 KIPS |
|
Text Classification (HP)
|
100% |
2531
3.38 KIPS |
|
Text Classification (Q)
|
93% |
2889
3.88 KIPS |
|
Machine Translation (SP)
|
100% |
1322
22.8 IPS |
|
Machine Translation (HP)
|
100% |
2294
39.5 IPS |
|
Machine Translation (Q)
|
98% |
2292
39.6 IPS |