Upload Date | September 17 2024 01:54 PM |
Views | 1 |
AI Information | |
---|---|
Framework | Core ML |
Backend | Neural Engine |
Device | Apple M1 |
System Information | |
---|---|
Operating System | iOS 18.0 |
Model | iPad Pro (11-inch 3rd generation) |
Model ID | iPad13,4 |
Motherboard | J517AP |
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% |
1395
259.5 IPS |
|
Image Classification (HP)
|
100% |
6293
1.17 KIPS |
|
Image Classification (Q)
|
96% |
5880
1.10 KIPS |
|
Image Segmentation (SP)
|
100% |
1378
22.3 IPS |
|
Image Segmentation (HP)
|
100% |
6642
107.7 IPS |
|
Image Segmentation (Q)
|
99% |
6796
110.2 IPS |
|
Pose Estimation (SP)
|
100% |
6091
7.11 IPS |
|
Pose Estimation (HP)
|
100% |
65574
76.5 IPS |
|
Pose Estimation (Q)
|
95% |
65836
77.2 IPS |
|
Object Detection (SP)
|
100% |
1495
118.6 IPS |
|
Object Detection (HP)
|
99% |
6351
505.2 IPS |
|
Object Detection (Q)
|
91% |
6694
534.9 IPS |
|
Face Detection (SP)
|
100% |
3010
35.8 IPS |
|
Face Detection (HP)
|
100% |
14834
176.3 IPS |
|
Face Detection (Q)
|
100% |
14949
177.6 IPS |
|
Depth Estimation (SP)
|
100% |
5760
44.4 IPS |
|
Depth Estimation (HP)
|
99% |
46069
354.9 IPS |
|
Depth Estimation (Q)
|
85% |
48090
375.8 IPS |
|
Style Transfer (SP)
|
100% |
17135
22.0 IPS |
|
Style Transfer (HP)
|
100% |
121715
156.5 IPS |
|
Style Transfer (Q)
|
96% |
114902
148.3 IPS |
|
Image Super-Resolution (SP)
|
100% |
3545
130.9 IPS |
|
Image Super-Resolution (HP)
|
100% |
22332
824.6 IPS |
|
Image Super-Resolution (Q)
|
99% |
23820
879.6 IPS |
|
Text Classification (SP)
|
100% |
2265
3.02 KIPS |
|
Text Classification (HP)
|
100% |
3900
5.21 KIPS |
|
Text Classification (Q)
|
93% |
3893
5.22 KIPS |
|
Machine Translation (SP)
|
100% |
2473
42.6 IPS |
|
Machine Translation (HP)
|
100% |
2250
38.8 IPS |
|
Machine Translation (Q)
|
98% |
2245
38.8 IPS |