User | bkr899 |
Upload Date | August 17 2024 06:16 AM |
Views | 2 |
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 | iPad13,8 |
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 | 7.31 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
1077
200.3 IPS |
|
Image Classification (HP)
|
100% |
6293
1.17 KIPS |
|
Image Classification (Q)
|
99% |
6412
1.20 KIPS |
|
Image Segmentation (SP)
|
100% |
681
11.0 IPS |
|
Image Segmentation (HP)
|
100% |
4109
66.6 IPS |
|
Image Segmentation (Q)
|
100% |
4112
66.7 IPS |
|
Pose Estimation (SP)
|
100% |
5761
6.72 IPS |
|
Pose Estimation (HP)
|
100% |
67561
78.8 IPS |
|
Pose Estimation (Q)
|
94% |
64387
75.5 IPS |
|
Object Detection (SP)
|
100% |
1181
93.7 IPS |
|
Object Detection (HP)
|
99% |
7127
567.0 IPS |
|
Object Detection (Q)
|
93% |
6482
517.2 IPS |
|
Face Detection (SP)
|
100% |
2155
25.6 IPS |
|
Face Detection (HP)
|
100% |
12475
148.2 IPS |
|
Face Detection (Q)
|
100% |
12776
151.8 IPS |
|
Depth Estimation (SP)
|
100% |
3844
29.6 IPS |
|
Depth Estimation (HP)
|
99% |
43530
335.4 IPS |
|
Depth Estimation (Q)
|
97% |
46914
362.7 IPS |
|
Style Transfer (SP)
|
100% |
10391
13.4 IPS |
|
Style Transfer (HP)
|
100% |
117460
151.0 IPS |
|
Style Transfer (Q)
|
100% |
123340
158.6 IPS |
|
Image Super-Resolution (SP)
|
100% |
2851
105.3 IPS |
|
Image Super-Resolution (HP)
|
100% |
17881
660.3 IPS |
|
Image Super-Resolution (Q)
|
98% |
20287
751.6 IPS |
|
Text Classification (SP)
|
100% |
1268
1.69 KIPS |
|
Text Classification (HP)
|
100% |
2467
3.29 KIPS |
|
Text Classification (Q)
|
93% |
2546
3.42 KIPS |
|
Machine Translation (SP)
|
100% |
1356
23.4 IPS |
|
Machine Translation (HP)
|
100% |
2260
38.9 IPS |
|
Machine Translation (Q)
|
98% |
2245
38.8 IPS |