Upload Date | December 22 2024 02:14 AM |
Views | 1 |
AI Information | |
---|---|
Framework | Core ML |
Backend | Neural Engine |
Device | Apple M1 |
System Information | |
---|---|
Operating System | iOS 18.2 |
Model | iPad Pro (11-inch 3rd generation) |
Model ID | iPad13,6 |
Motherboard | J518AP |
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% |
1399
260.1 IPS |
|
Image Classification (HP)
|
100% |
6216
1.16 KIPS |
|
Image Classification (Q)
|
96% |
5904
1.10 KIPS |
|
Image Segmentation (SP)
|
100% |
1378
22.3 IPS |
|
Image Segmentation (HP)
|
100% |
9754
158.1 IPS |
|
Image Segmentation (Q)
|
99% |
10020
162.4 IPS |
|
Pose Estimation (SP)
|
100% |
6530
7.62 IPS |
|
Pose Estimation (HP)
|
100% |
67243
78.5 IPS |
|
Pose Estimation (Q)
|
95% |
65676
77.0 IPS |
|
Object Detection (SP)
|
100% |
1509
119.7 IPS |
|
Object Detection (HP)
|
99% |
7220
574.3 IPS |
|
Object Detection (Q)
|
91% |
6686
534.3 IPS |
|
Face Detection (SP)
|
100% |
3062
36.4 IPS |
|
Face Detection (HP)
|
100% |
16432
195.2 IPS |
|
Face Detection (Q)
|
100% |
15155
180.1 IPS |
|
Depth Estimation (SP)
|
100% |
5831
44.9 IPS |
|
Depth Estimation (HP)
|
99% |
47319
364.6 IPS |
|
Depth Estimation (Q)
|
85% |
47979
374.9 IPS |
|
Style Transfer (SP)
|
100% |
17151
22.0 IPS |
|
Style Transfer (HP)
|
100% |
120137
154.4 IPS |
|
Style Transfer (Q)
|
96% |
112814
145.6 IPS |
|
Image Super-Resolution (SP)
|
100% |
3744
138.2 IPS |
|
Image Super-Resolution (HP)
|
100% |
23279
859.6 IPS |
|
Image Super-Resolution (Q)
|
99% |
23839
880.2 IPS |
|
Text Classification (SP)
|
100% |
2288
3.05 KIPS |
|
Text Classification (HP)
|
100% |
3991
5.33 KIPS |
|
Text Classification (Q)
|
93% |
3952
5.30 KIPS |
|
Machine Translation (SP)
|
100% |
2488
42.9 IPS |
|
Machine Translation (HP)
|
100% |
3235
55.7 IPS |
|
Machine Translation (Q)
|
98% |
3415
59.0 IPS |