User | coorelle |
Upload Date | March 15 2025 05:46 AM |
Views | 6 |
AI Information | |
---|---|
Framework | Core ML |
Backend | Neural Engine |
Device | Apple M4 |
System Information | |
---|---|
Operating System | iOS 18.3.2 |
Model | iPad Pro 11-inch (M4) |
Model ID | iPad16,3 |
Motherboard | J717AP |
CPU Information | |
---|---|
Name | Apple M4 |
Topology | 1 Processor, 10 Cores |
Identifier | ARM |
Base Frequency | 4.41 GHz |
Cluster 1 | 4 Cores |
Cluster 2 | 6 Cores |
Memory Information | |
---|---|
Size | 15.14 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
2033
378.2 IPS |
|
Image Classification (HP)
|
100% |
16954
3.15 KIPS |
|
Image Classification (Q)
|
97% |
23234
4.34 KIPS |
|
Image Segmentation (SP)
|
100% |
2120
34.4 IPS |
|
Image Segmentation (HP)
|
100% |
22156
359.2 IPS |
|
Image Segmentation (Q)
|
99% |
30273
490.7 IPS |
|
Pose Estimation (SP)
|
100% |
10075
11.8 IPS |
|
Pose Estimation (HP)
|
100% |
123008
143.5 IPS |
|
Pose Estimation (Q)
|
95% |
232178
272.1 IPS |
|
Object Detection (SP)
|
100% |
2263
179.5 IPS |
|
Object Detection (HP)
|
100% |
17940
1.42 KIPS |
|
Object Detection (Q)
|
91% |
25552
2.04 KIPS |
|
Face Detection (SP)
|
100% |
4019
47.8 IPS |
|
Face Detection (HP)
|
100% |
42083
500.0 IPS |
|
Face Detection (Q)
|
100% |
62447
742.0 IPS |
|
Depth Estimation (SP)
|
100% |
8319
64.1 IPS |
|
Depth Estimation (HP)
|
99% |
97892
754.2 IPS |
|
Depth Estimation (Q)
|
85% |
164947
1.29 KIPS |
|
Style Transfer (SP)
|
100% |
25266
32.5 IPS |
|
Style Transfer (HP)
|
100% |
230718
296.6 IPS |
|
Style Transfer (Q)
|
96% |
296475
382.6 IPS |
|
Image Super-Resolution (SP)
|
100% |
5860
216.4 IPS |
|
Image Super-Resolution (HP)
|
100% |
48284
1.78 KIPS |
|
Image Super-Resolution (Q)
|
99% |
80869
2.99 KIPS |
|
Text Classification (SP)
|
100% |
2900
3.87 KIPS |
|
Text Classification (HP)
|
100% |
5506
7.35 KIPS |
|
Text Classification (Q)
|
93% |
5392
7.24 KIPS |
|
Machine Translation (SP)
|
100% |
3877
66.8 IPS |
|
Machine Translation (HP)
|
100% |
16002
275.6 IPS |
|
Machine Translation (Q)
|
98% |
17440
301.4 IPS |