Upload Date | December 22 2024 12:19 PM |
Views | 1 |
AI Information | |
---|---|
Framework | Core ML |
Backend | Neural Engine |
Device | Apple M2 |
System Information | |
---|---|
Operating System | iOS 18.2 |
Model | iPad Pro (12.9-inch, 6th generation) |
Model ID | iPad14,5 |
Motherboard | J620AP |
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 | 7.35 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
1371
254.9 IPS |
|
Image Classification (HP)
|
100% |
13920
2.59 KIPS |
|
Image Classification (Q)
|
96% |
14562
2.72 KIPS |
|
Image Segmentation (SP)
|
100% |
1521
24.7 IPS |
|
Image Segmentation (HP)
|
100% |
18894
306.3 IPS |
|
Image Segmentation (Q)
|
99% |
23701
384.2 IPS |
|
Pose Estimation (SP)
|
100% |
6876
8.02 IPS |
|
Pose Estimation (HP)
|
100% |
105472
123.1 IPS |
|
Pose Estimation (Q)
|
95% |
105786
124.0 IPS |
|
Object Detection (SP)
|
100% |
1562
123.9 IPS |
|
Object Detection (HP)
|
99% |
15383
1.22 KIPS |
|
Object Detection (Q)
|
91% |
15933
1.27 KIPS |
|
Face Detection (SP)
|
100% |
3092
36.7 IPS |
|
Face Detection (HP)
|
100% |
32312
383.9 IPS |
|
Face Detection (Q)
|
100% |
40665
483.2 IPS |
|
Depth Estimation (SP)
|
100% |
5730
44.1 IPS |
|
Depth Estimation (HP)
|
99% |
84395
650.2 IPS |
|
Depth Estimation (Q)
|
85% |
102219
798.8 IPS |
|
Style Transfer (SP)
|
100% |
18711
24.1 IPS |
|
Style Transfer (HP)
|
100% |
199504
256.5 IPS |
|
Style Transfer (Q)
|
96% |
187636
242.1 IPS |
|
Image Super-Resolution (SP)
|
100% |
4135
152.7 IPS |
|
Image Super-Resolution (HP)
|
100% |
36722
1.36 KIPS |
|
Image Super-Resolution (Q)
|
99% |
44447
1.64 KIPS |
|
Text Classification (SP)
|
100% |
2250
3.00 KIPS |
|
Text Classification (HP)
|
100% |
3713
4.96 KIPS |
|
Text Classification (Q)
|
93% |
3661
4.91 KIPS |
|
Machine Translation (SP)
|
100% |
3536
60.9 IPS |
|
Machine Translation (HP)
|
100% |
3948
68.0 IPS |
|
Machine Translation (Q)
|
98% |
4103
70.9 IPS |