User | Angus72 |
Upload Date | October 31 2024 10:10 AM |
Views | 4 |
AI Information | |
---|---|
Framework | Core ML |
Backend | Neural Engine |
Device | ARM |
System Information | |
---|---|
Operating System | iOS 18.1 |
Model | iPad14,8 |
Model ID | iPad14,8 |
Motherboard | J507AP |
CPU Information | |
---|---|
Name | ARM |
Topology | 1 Processor, 8 Cores |
Identifier | ARM |
Base Frequency | 3.47 GHz |
Cluster 1 | 4 Cores |
Cluster 2 | 4 Cores |
Memory Information | |
---|---|
Size | 7.47 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
1379
256.5 IPS |
|
Image Classification (HP)
|
100% |
14536
2.70 KIPS |
|
Image Classification (Q)
|
96% |
14860
2.78 KIPS |
|
Image Segmentation (SP)
|
100% |
1525
24.7 IPS |
|
Image Segmentation (HP)
|
100% |
18861
305.7 IPS |
|
Image Segmentation (Q)
|
99% |
23782
385.5 IPS |
|
Pose Estimation (SP)
|
100% |
6892
8.04 IPS |
|
Pose Estimation (HP)
|
100% |
105760
123.4 IPS |
|
Pose Estimation (Q)
|
95% |
104124
122.0 IPS |
|
Object Detection (SP)
|
100% |
1561
123.9 IPS |
|
Object Detection (HP)
|
99% |
14971
1.19 KIPS |
|
Object Detection (Q)
|
91% |
17013
1.36 KIPS |
|
Face Detection (SP)
|
100% |
3152
37.5 IPS |
|
Face Detection (HP)
|
100% |
32965
391.7 IPS |
|
Face Detection (Q)
|
100% |
41391
491.8 IPS |
|
Depth Estimation (SP)
|
100% |
5668
43.7 IPS |
|
Depth Estimation (HP)
|
99% |
84606
651.8 IPS |
|
Depth Estimation (Q)
|
85% |
104066
813.2 IPS |
|
Style Transfer (SP)
|
100% |
18817
24.2 IPS |
|
Style Transfer (HP)
|
100% |
201308
258.8 IPS |
|
Style Transfer (Q)
|
96% |
191523
247.2 IPS |
|
Image Super-Resolution (SP)
|
100% |
4068
150.2 IPS |
|
Image Super-Resolution (HP)
|
100% |
38475
1.42 KIPS |
|
Image Super-Resolution (Q)
|
99% |
46071
1.70 KIPS |
|
Text Classification (SP)
|
100% |
2220
2.96 KIPS |
|
Text Classification (HP)
|
100% |
3626
4.84 KIPS |
|
Text Classification (Q)
|
93% |
3663
4.92 KIPS |
|
Machine Translation (SP)
|
100% |
3552
61.2 IPS |
|
Machine Translation (HP)
|
100% |
6756
116.4 IPS |
|
Machine Translation (Q)
|
98% |
7444
128.6 IPS |