Upload Date | December 04 2024 01:03 AM |
Views | 1 |
AI Information | |
---|---|
Framework | Core ML |
Backend | Neural Engine |
Device | Apple M2 |
System Information | |
---|---|
Operating System | iOS 18.1 |
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% |
1376
255.9 IPS |
|
Image Classification (HP)
|
100% |
14127
2.63 KIPS |
|
Image Classification (Q)
|
96% |
14701
2.75 KIPS |
|
Image Segmentation (SP)
|
100% |
1530
24.8 IPS |
|
Image Segmentation (HP)
|
100% |
18469
299.4 IPS |
|
Image Segmentation (Q)
|
99% |
23605
382.7 IPS |
|
Pose Estimation (SP)
|
100% |
6900
8.05 IPS |
|
Pose Estimation (HP)
|
100% |
102382
119.5 IPS |
|
Pose Estimation (Q)
|
95% |
104776
122.8 IPS |
|
Object Detection (SP)
|
100% |
1551
123.0 IPS |
|
Object Detection (HP)
|
99% |
14852
1.18 KIPS |
|
Object Detection (Q)
|
91% |
17676
1.41 KIPS |
|
Face Detection (SP)
|
100% |
3155
37.5 IPS |
|
Face Detection (HP)
|
100% |
32775
389.4 IPS |
|
Face Detection (Q)
|
100% |
41264
490.3 IPS |
|
Depth Estimation (SP)
|
100% |
5684
43.8 IPS |
|
Depth Estimation (HP)
|
99% |
85672
660.1 IPS |
|
Depth Estimation (Q)
|
85% |
105460
824.1 IPS |
|
Style Transfer (SP)
|
100% |
18908
24.3 IPS |
|
Style Transfer (HP)
|
100% |
201137
258.6 IPS |
|
Style Transfer (Q)
|
96% |
190392
245.7 IPS |
|
Image Super-Resolution (SP)
|
100% |
4073
150.4 IPS |
|
Image Super-Resolution (HP)
|
100% |
37570
1.39 KIPS |
|
Image Super-Resolution (Q)
|
99% |
47341
1.75 KIPS |
|
Text Classification (SP)
|
100% |
2281
3.04 KIPS |
|
Text Classification (HP)
|
100% |
3830
5.11 KIPS |
|
Text Classification (Q)
|
93% |
3746
5.03 KIPS |
|
Machine Translation (SP)
|
100% |
3528
60.8 IPS |
|
Machine Translation (HP)
|
100% |
6670
114.9 IPS |
|
Machine Translation (Q)
|
98% |
7358
127.2 IPS |