User | DVB |
Upload Date | December 25 2024 07:03 PM |
Views | 2 |
AI Information | |
---|---|
Framework | Core ML |
Backend | Neural Engine |
Device | Apple M4 |
System Information | |
---|---|
Operating System | iOS 18.2 |
Model | iPad Pro 11-inch (M4) |
Model ID | iPad16,3 |
Motherboard | J717AP |
CPU Information | |
---|---|
Name | Apple M4 |
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% |
2021
375.8 IPS |
|
Image Classification (HP)
|
100% |
17318
3.22 KIPS |
|
Image Classification (Q)
|
97% |
24826
4.63 KIPS |
|
Image Segmentation (SP)
|
100% |
2171
35.2 IPS |
|
Image Segmentation (HP)
|
100% |
22096
358.2 IPS |
|
Image Segmentation (Q)
|
99% |
30365
492.2 IPS |
|
Pose Estimation (SP)
|
100% |
10080
11.8 IPS |
|
Pose Estimation (HP)
|
100% |
123498
144.1 IPS |
|
Pose Estimation (Q)
|
95% |
233082
273.2 IPS |
|
Object Detection (SP)
|
100% |
2248
178.4 IPS |
|
Object Detection (HP)
|
100% |
18361
1.46 KIPS |
|
Object Detection (Q)
|
91% |
26027
2.08 KIPS |
|
Face Detection (SP)
|
100% |
4006
47.6 IPS |
|
Face Detection (HP)
|
100% |
42228
501.8 IPS |
|
Face Detection (Q)
|
100% |
62786
746.0 IPS |
|
Depth Estimation (SP)
|
100% |
8308
64.0 IPS |
|
Depth Estimation (HP)
|
99% |
99080
763.4 IPS |
|
Depth Estimation (Q)
|
85% |
169802
1.33 KIPS |
|
Style Transfer (SP)
|
100% |
25122
32.3 IPS |
|
Style Transfer (HP)
|
100% |
234155
301.0 IPS |
|
Style Transfer (Q)
|
96% |
296051
382.0 IPS |
|
Image Super-Resolution (SP)
|
100% |
5859
216.3 IPS |
|
Image Super-Resolution (HP)
|
100% |
48774
1.80 KIPS |
|
Image Super-Resolution (Q)
|
99% |
85139
3.14 KIPS |
|
Text Classification (SP)
|
100% |
2933
3.92 KIPS |
|
Text Classification (HP)
|
100% |
5976
7.98 KIPS |
|
Text Classification (Q)
|
93% |
5992
8.04 KIPS |
|
Machine Translation (SP)
|
100% |
3943
67.9 IPS |
|
Machine Translation (HP)
|
100% |
16437
283.1 IPS |
|
Machine Translation (Q)
|
98% |
18041
311.8 IPS |