User | buggshash |
Upload Date | December 10 2024 06:52 PM |
Views | 2 |
AI Information | |
---|---|
Framework | Core ML |
Backend | Neural Engine |
Device | Apple M4 |
System Information | |
---|---|
Operating System | iOS 18.1.1 |
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% |
2003
372.5 IPS |
|
Image Classification (HP)
|
100% |
16870
3.14 KIPS |
|
Image Classification (Q)
|
97% |
24637
4.60 KIPS |
|
Image Segmentation (SP)
|
100% |
2125
34.4 IPS |
|
Image Segmentation (HP)
|
100% |
22056
357.6 IPS |
|
Image Segmentation (Q)
|
99% |
30583
495.8 IPS |
|
Pose Estimation (SP)
|
100% |
10102
11.8 IPS |
|
Pose Estimation (HP)
|
100% |
123677
144.3 IPS |
|
Pose Estimation (Q)
|
95% |
233234
273.4 IPS |
|
Object Detection (SP)
|
100% |
2224
176.4 IPS |
|
Object Detection (HP)
|
100% |
18423
1.46 KIPS |
|
Object Detection (Q)
|
91% |
25654
2.05 KIPS |
|
Face Detection (SP)
|
100% |
4005
47.6 IPS |
|
Face Detection (HP)
|
100% |
43231
513.7 IPS |
|
Face Detection (Q)
|
100% |
63046
749.1 IPS |
|
Depth Estimation (SP)
|
100% |
8326
64.1 IPS |
|
Depth Estimation (HP)
|
99% |
98585
759.5 IPS |
|
Depth Estimation (Q)
|
85% |
172464
1.35 KIPS |
|
Style Transfer (SP)
|
100% |
25277
32.5 IPS |
|
Style Transfer (HP)
|
100% |
235806
303.1 IPS |
|
Style Transfer (Q)
|
96% |
298800
385.6 IPS |
|
Image Super-Resolution (SP)
|
100% |
5867
216.6 IPS |
|
Image Super-Resolution (HP)
|
100% |
48799
1.80 KIPS |
|
Image Super-Resolution (Q)
|
99% |
85094
3.14 KIPS |
|
Text Classification (SP)
|
100% |
2998
4.00 KIPS |
|
Text Classification (HP)
|
100% |
6286
8.39 KIPS |
|
Text Classification (Q)
|
93% |
6438
8.64 KIPS |
|
Machine Translation (SP)
|
100% |
3949
68.0 IPS |
|
Machine Translation (HP)
|
100% |
16475
283.8 IPS |
|
Machine Translation (Q)
|
98% |
18000
311.1 IPS |