User | gmn17 |
Upload Date | July 15 2025 04:41 AM |
Views | 6 |
AI Information | |
---|---|
Framework | Core ML |
Backend | Neural Engine |
Device | Apple M1 |
System Information | |
---|---|
Operating System | iOS 18.5 |
Model | iPad Pro (12.9-inch 5th generation) |
Model ID | iPad13,9 |
Motherboard | J522xAP |
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 | 15.35 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
1419
263.8 IPS |
|
Image Classification (HP)
|
100% |
6271
1.17 KIPS |
|
Image Classification (Q)
|
96% |
5871
1.10 KIPS |
|
Image Segmentation (SP)
|
100% |
1361
22.1 IPS |
|
Image Segmentation (HP)
|
100% |
9671
156.8 IPS |
|
Image Segmentation (Q)
|
99% |
10073
163.3 IPS |
|
Pose Estimation (SP)
|
100% |
6485
7.57 IPS |
|
Pose Estimation (HP)
|
100% |
68667
80.1 IPS |
|
Pose Estimation (Q)
|
95% |
66929
78.4 IPS |
|
Object Detection (SP)
|
100% |
1506
119.5 IPS |
|
Object Detection (HP)
|
99% |
7242
576.1 IPS |
|
Object Detection (Q)
|
91% |
6683
534.0 IPS |
|
Face Detection (SP)
|
100% |
3024
35.9 IPS |
|
Face Detection (HP)
|
100% |
16699
198.4 IPS |
|
Face Detection (Q)
|
100% |
15253
181.2 IPS |
|
Depth Estimation (SP)
|
100% |
5644
43.5 IPS |
|
Depth Estimation (HP)
|
99% |
47573
366.5 IPS |
|
Depth Estimation (Q)
|
85% |
47498
371.2 IPS |
|
Style Transfer (SP)
|
100% |
16979
21.8 IPS |
|
Style Transfer (HP)
|
100% |
119828
154.0 IPS |
|
Style Transfer (Q)
|
96% |
114895
148.3 IPS |
|
Image Super-Resolution (SP)
|
100% |
3679
135.9 IPS |
|
Image Super-Resolution (HP)
|
100% |
23120
853.7 IPS |
|
Image Super-Resolution (Q)
|
99% |
23856
880.9 IPS |
|
Text Classification (SP)
|
100% |
2301
3.07 KIPS |
|
Text Classification (HP)
|
100% |
3971
5.30 KIPS |
|
Text Classification (Q)
|
93% |
3941
5.29 KIPS |
|
Machine Translation (SP)
|
100% |
2470
42.5 IPS |
|
Machine Translation (HP)
|
100% |
3549
61.1 IPS |
|
Machine Translation (Q)
|
98% |
3636
62.8 IPS |