User | BrentCato001 |
Upload Date | November 20 2024 06:56 AM |
Views | 4 |
AI Information | |
---|---|
Framework | Core ML |
Backend | Neural Engine |
Device | Apple M1 |
System Information | |
---|---|
Operating System | iOS 18.1 |
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 | 15.31 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
1289
239.8 IPS |
|
Image Classification (HP)
|
100% |
2421
450.3 IPS |
|
Image Classification (Q)
|
96% |
1706
318.5 IPS |
|
Image Segmentation (SP)
|
100% |
1420
23.0 IPS |
|
Image Segmentation (HP)
|
100% |
2389
38.7 IPS |
|
Image Segmentation (Q)
|
99% |
2757
44.7 IPS |
|
Pose Estimation (SP)
|
100% |
6686
7.80 IPS |
|
Pose Estimation (HP)
|
100% |
14687
17.1 IPS |
|
Pose Estimation (Q)
|
95% |
12759
15.0 IPS |
|
Object Detection (SP)
|
100% |
1449
115.0 IPS |
|
Object Detection (HP)
|
97% |
2790
222.1 IPS |
|
Object Detection (Q)
|
94% |
2029
161.7 IPS |
|
Face Detection (SP)
|
100% |
2968
35.3 IPS |
|
Face Detection (HP)
|
100% |
5815
69.1 IPS |
|
Face Detection (Q)
|
100% |
3369
40.0 IPS |
|
Depth Estimation (SP)
|
100% |
5446
42.0 IPS |
|
Depth Estimation (HP)
|
98% |
11185
86.5 IPS |
|
Depth Estimation (Q)
|
85% |
7798
61.0 IPS |
|
Style Transfer (SP)
|
100% |
18078
23.2 IPS |
|
Style Transfer (HP)
|
100% |
28133
36.2 IPS |
|
Style Transfer (Q)
|
96% |
23348
30.1 IPS |
|
Image Super-Resolution (SP)
|
100% |
4031
148.8 IPS |
|
Image Super-Resolution (HP)
|
100% |
4888
180.5 IPS |
|
Image Super-Resolution (Q)
|
99% |
3568
131.8 IPS |
|
Text Classification (SP)
|
100% |
2215
2.96 KIPS |
|
Text Classification (HP)
|
100% |
3776
5.04 KIPS |
|
Text Classification (Q)
|
93% |
3766
5.05 KIPS |
|
Machine Translation (SP)
|
100% |
3413
58.8 IPS |
|
Machine Translation (HP)
|
98% |
5526
95.5 IPS |
|
Machine Translation (Q)
|
98% |
5432
93.9 IPS |