Upload Date | November 13 2024 05:06 AM |
Views | 1 |
AI Information | |
---|---|
Framework | Core ML |
Backend | Neural Engine |
Device | Apple M2 |
System Information | |
---|---|
Operating System | iOS 18.2 |
Model | iPad Pro (11-inch, 4th generation) |
Model ID | iPad14,3 |
Motherboard | J617AP |
CPU Information | |
---|---|
Name | Apple M2 |
Topology | 1 Processor, 8 Cores |
Identifier | ARM |
Base Frequency | 3.49 GHz |
Cluster 1 | 4 Cores |
Cluster 2 | 4 Cores |
Memory Information | |
---|---|
Size | 7.36 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
1383
257.1 IPS |
|
Image Classification (HP)
|
100% |
14032
2.61 KIPS |
|
Image Classification (Q)
|
96% |
14350
2.68 KIPS |
|
Image Segmentation (SP)
|
100% |
1519
24.6 IPS |
|
Image Segmentation (HP)
|
100% |
18975
307.6 IPS |
|
Image Segmentation (Q)
|
99% |
23650
383.4 IPS |
|
Pose Estimation (SP)
|
100% |
6879
8.03 IPS |
|
Pose Estimation (HP)
|
100% |
102465
119.6 IPS |
|
Pose Estimation (Q)
|
95% |
104899
122.9 IPS |
|
Object Detection (SP)
|
100% |
1569
124.4 IPS |
|
Object Detection (HP)
|
99% |
15039
1.20 KIPS |
|
Object Detection (Q)
|
91% |
16646
1.33 KIPS |
|
Face Detection (SP)
|
100% |
3172
37.7 IPS |
|
Face Detection (HP)
|
100% |
32875
390.6 IPS |
|
Face Detection (Q)
|
100% |
41295
490.7 IPS |
|
Depth Estimation (SP)
|
100% |
5699
43.9 IPS |
|
Depth Estimation (HP)
|
99% |
86657
667.6 IPS |
|
Depth Estimation (Q)
|
85% |
104157
813.9 IPS |
|
Style Transfer (SP)
|
100% |
18930
24.3 IPS |
|
Style Transfer (HP)
|
100% |
200571
257.8 IPS |
|
Style Transfer (Q)
|
96% |
188852
243.7 IPS |
|
Image Super-Resolution (SP)
|
100% |
4169
154.0 IPS |
|
Image Super-Resolution (HP)
|
100% |
37619
1.39 KIPS |
|
Image Super-Resolution (Q)
|
99% |
45702
1.69 KIPS |
|
Text Classification (SP)
|
100% |
2185
2.92 KIPS |
|
Text Classification (HP)
|
100% |
3665
4.89 KIPS |
|
Text Classification (Q)
|
93% |
3628
4.87 KIPS |
|
Machine Translation (SP)
|
100% |
3552
61.2 IPS |
|
Machine Translation (HP)
|
100% |
6561
113.0 IPS |
|
Machine Translation (Q)
|
98% |
7236
125.0 IPS |