User | techne2718 |
Upload Date | May 31 2025 07:07 PM |
Views | 7 |
AI Information | |
---|---|
Framework | Core ML |
Backend | Neural Engine |
Device | Apple M1 |
System Information | |
---|---|
Operating System | iOS 18.3.2 |
Model | iPad Air (5th generation) |
Model ID | iPad13,16 |
Motherboard | J407AP |
CPU Information | |
---|---|
Name | Apple M1 |
Topology | 1 Processor, 8 Cores |
Identifier | ARM |
Base Frequency | 3.19 GHz |
Cluster 1 | 4 Cores |
Cluster 2 | 4 Cores |
Memory Information | |
---|---|
Size | 7.47 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
1393
259.1 IPS |
|
Image Classification (HP)
|
100% |
6280
1.17 KIPS |
|
Image Classification (Q)
|
96% |
5854
1.09 KIPS |
|
Image Segmentation (SP)
|
100% |
1375
22.3 IPS |
|
Image Segmentation (HP)
|
100% |
9766
158.3 IPS |
|
Image Segmentation (Q)
|
99% |
9945
161.2 IPS |
|
Pose Estimation (SP)
|
100% |
6549
7.64 IPS |
|
Pose Estimation (HP)
|
100% |
68370
79.8 IPS |
|
Pose Estimation (Q)
|
95% |
65687
77.0 IPS |
|
Object Detection (SP)
|
100% |
1520
120.5 IPS |
|
Object Detection (HP)
|
99% |
7213
573.8 IPS |
|
Object Detection (Q)
|
91% |
6730
537.8 IPS |
|
Face Detection (SP)
|
100% |
3054
36.3 IPS |
|
Face Detection (HP)
|
100% |
16528
196.4 IPS |
|
Face Detection (Q)
|
100% |
15317
182.0 IPS |
|
Depth Estimation (SP)
|
100% |
5802
44.7 IPS |
|
Depth Estimation (HP)
|
99% |
47250
364.0 IPS |
|
Depth Estimation (Q)
|
85% |
48363
377.9 IPS |
|
Style Transfer (SP)
|
100% |
17166
22.1 IPS |
|
Style Transfer (HP)
|
100% |
120077
154.4 IPS |
|
Style Transfer (Q)
|
96% |
112615
145.3 IPS |
|
Image Super-Resolution (SP)
|
100% |
3747
138.4 IPS |
|
Image Super-Resolution (HP)
|
100% |
23167
855.4 IPS |
|
Image Super-Resolution (Q)
|
99% |
23890
882.2 IPS |
|
Text Classification (SP)
|
100% |
2294
3.06 KIPS |
|
Text Classification (HP)
|
100% |
3886
5.19 KIPS |
|
Text Classification (Q)
|
93% |
3891
5.22 KIPS |
|
Machine Translation (SP)
|
100% |
2475
42.6 IPS |
|
Machine Translation (HP)
|
100% |
3653
62.9 IPS |
|
Machine Translation (Q)
|
98% |
3772
65.2 IPS |