User | virtuatony95 |
Upload Date | September 10 2024 09:05 PM |
Views | 25 |
AI Information | |
---|---|
Framework | Core ML |
Backend | Neural Engine |
Device | ARM |
System Information | |
---|---|
Operating System | iOS 18.0 |
Model | iPad16,3 |
Model ID | iPad16,3 |
Motherboard | J717AP |
CPU Information | |
---|---|
Name | ARM |
Topology | 1 Processor, 9 Cores |
Identifier | ARM |
Base Frequency | 4.41 GHz |
Cluster 1 | 3 Cores |
Cluster 2 | 6 Cores |
Memory Information | |
---|---|
Size | 7.29 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
1970
366.3 IPS |
|
Image Classification (HP)
|
100% |
18374
3.42 KIPS |
|
Image Classification (Q)
|
97% |
28394
5.30 KIPS |
|
Image Segmentation (SP)
|
100% |
2137
34.6 IPS |
|
Image Segmentation (HP)
|
100% |
16275
263.8 IPS |
|
Image Segmentation (Q)
|
99% |
20581
333.6 IPS |
|
Pose Estimation (SP)
|
100% |
9993
11.7 IPS |
|
Pose Estimation (HP)
|
100% |
123135
143.7 IPS |
|
Pose Estimation (Q)
|
95% |
231125
270.9 IPS |
|
Object Detection (SP)
|
100% |
2211
175.4 IPS |
|
Object Detection (HP)
|
100% |
18784
1.49 KIPS |
|
Object Detection (Q)
|
91% |
26644
2.13 KIPS |
|
Face Detection (SP)
|
100% |
3946
46.9 IPS |
|
Face Detection (HP)
|
100% |
42178
501.2 IPS |
|
Face Detection (Q)
|
100% |
60794
722.4 IPS |
|
Depth Estimation (SP)
|
100% |
8301
64.0 IPS |
|
Depth Estimation (HP)
|
99% |
98853
761.6 IPS |
|
Depth Estimation (Q)
|
85% |
170352
1.33 KIPS |
|
Style Transfer (SP)
|
100% |
25075
32.2 IPS |
|
Style Transfer (HP)
|
100% |
232602
299.0 IPS |
|
Style Transfer (Q)
|
96% |
294699
380.3 IPS |
|
Image Super-Resolution (SP)
|
100% |
5841
215.7 IPS |
|
Image Super-Resolution (HP)
|
100% |
49527
1.83 KIPS |
|
Image Super-Resolution (Q)
|
99% |
87369
3.23 KIPS |
|
Text Classification (SP)
|
100% |
3000
4.00 KIPS |
|
Text Classification (HP)
|
100% |
7041
9.40 KIPS |
|
Text Classification (Q)
|
93% |
7056
9.47 KIPS |
|
Machine Translation (SP)
|
100% |
3918
67.5 IPS |
|
Machine Translation (HP)
|
100% |
16815
289.6 IPS |
|
Machine Translation (Q)
|
98% |
18696
323.1 IPS |