Upload Date | September 18 2024 11:14 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% |
1387
258.0 IPS |
|
Image Classification (HP)
|
100% |
6276
1.17 KIPS |
|
Image Classification (Q)
|
96% |
5916
1.10 KIPS |
|
Image Segmentation (SP)
|
100% |
1374
22.3 IPS |
|
Image Segmentation (HP)
|
100% |
6610
107.1 IPS |
|
Image Segmentation (Q)
|
99% |
6752
109.4 IPS |
|
Pose Estimation (SP)
|
100% |
6539
7.63 IPS |
|
Pose Estimation (HP)
|
100% |
66214
77.3 IPS |
|
Pose Estimation (Q)
|
95% |
65675
77.0 IPS |
|
Object Detection (SP)
|
100% |
1512
120.0 IPS |
|
Object Detection (HP)
|
99% |
7210
573.5 IPS |
|
Object Detection (Q)
|
91% |
6654
531.7 IPS |
|
Face Detection (SP)
|
100% |
3048
36.2 IPS |
|
Face Detection (HP)
|
100% |
16068
190.9 IPS |
|
Face Detection (Q)
|
100% |
14988
178.1 IPS |
|
Depth Estimation (SP)
|
100% |
5833
44.9 IPS |
|
Depth Estimation (HP)
|
99% |
47348
364.8 IPS |
|
Depth Estimation (Q)
|
85% |
47581
371.8 IPS |
|
Style Transfer (SP)
|
100% |
17129
22.0 IPS |
|
Style Transfer (HP)
|
100% |
120769
155.3 IPS |
|
Style Transfer (Q)
|
96% |
114310
147.5 IPS |
|
Image Super-Resolution (SP)
|
100% |
3740
138.1 IPS |
|
Image Super-Resolution (HP)
|
100% |
22991
849.0 IPS |
|
Image Super-Resolution (Q)
|
99% |
23854
880.8 IPS |
|
Text Classification (SP)
|
100% |
2315
3.09 KIPS |
|
Text Classification (HP)
|
100% |
3841
5.13 KIPS |
|
Text Classification (Q)
|
93% |
3779
5.07 KIPS |
|
Machine Translation (SP)
|
100% |
2470
42.6 IPS |
|
Machine Translation (HP)
|
100% |
2324
40.0 IPS |
|
Machine Translation (Q)
|
98% |
2317
40.0 IPS |