Upload Date | December 30 2024 04:50 PM |
Views | 1 |
AI Information | |
---|---|
Framework | Core ML |
Backend | Neural Engine |
Device | Apple M1 |
System Information | |
---|---|
Operating System | iOS 18.2 |
Model | iPad Pro (11-inch 3rd generation) |
Model ID | iPad13,4 |
Motherboard | J517AP |
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 | 7.37 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
1396
259.6 IPS |
|
Image Classification (HP)
|
100% |
6023
1.12 KIPS |
|
Image Classification (Q)
|
96% |
5697
1.06 KIPS |
|
Image Segmentation (SP)
|
100% |
1407
22.8 IPS |
|
Image Segmentation (HP)
|
100% |
9799
158.8 IPS |
|
Image Segmentation (Q)
|
99% |
10060
163.1 IPS |
|
Pose Estimation (SP)
|
100% |
6542
7.63 IPS |
|
Pose Estimation (HP)
|
100% |
67978
79.3 IPS |
|
Pose Estimation (Q)
|
95% |
65783
77.1 IPS |
|
Object Detection (SP)
|
100% |
1492
118.3 IPS |
|
Object Detection (HP)
|
99% |
7317
582.1 IPS |
|
Object Detection (Q)
|
91% |
6621
529.0 IPS |
|
Face Detection (SP)
|
100% |
3053
36.3 IPS |
|
Face Detection (HP)
|
100% |
16697
198.4 IPS |
|
Face Detection (Q)
|
100% |
15297
181.8 IPS |
|
Depth Estimation (SP)
|
100% |
5827
44.9 IPS |
|
Depth Estimation (HP)
|
99% |
46560
358.7 IPS |
|
Depth Estimation (Q)
|
85% |
48142
376.2 IPS |
|
Style Transfer (SP)
|
100% |
17224
22.1 IPS |
|
Style Transfer (HP)
|
100% |
120749
155.2 IPS |
|
Style Transfer (Q)
|
96% |
112271
144.9 IPS |
|
Image Super-Resolution (SP)
|
100% |
3766
139.1 IPS |
|
Image Super-Resolution (HP)
|
100% |
23077
852.1 IPS |
|
Image Super-Resolution (Q)
|
99% |
24086
889.4 IPS |
|
Text Classification (SP)
|
100% |
2286
3.05 KIPS |
|
Text Classification (HP)
|
100% |
3894
5.20 KIPS |
|
Text Classification (Q)
|
93% |
3950
5.30 KIPS |
|
Machine Translation (SP)
|
100% |
2548
43.9 IPS |
|
Machine Translation (HP)
|
100% |
3254
56.1 IPS |
|
Machine Translation (Q)
|
98% |
3356
58.0 IPS |