User | Aquilaarancione09 |
Upload Date | December 12 2024 10:01 PM |
Views | 2 |
AI Information | |
---|---|
Framework | Core ML |
Backend | Neural Engine |
Device | Apple M1 |
System Information | |
---|---|
Operating System | macOS 15.1.1 (Build 24B91) |
Model | MacBook Air (Late 2020) |
Model ID | MacBookAir10,1 |
Motherboard | MacBookAir10,1 |
CPU Information | |
---|---|
Name | Apple M1 |
Topology | 1 Processor, 8 Cores |
Identifier | Apple M1 |
Base Frequency | 3.20 GHz |
Cluster 1 | 4 Cores |
Cluster 2 | 4 Cores |
Memory Information | |
---|---|
Size | 8.00 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
1403
260.9 IPS |
|
Image Classification (HP)
|
100% |
6458
1.20 KIPS |
|
Image Classification (Q)
|
96% |
6123
1.14 KIPS |
|
Image Segmentation (SP)
|
100% |
1387
22.5 IPS |
|
Image Segmentation (HP)
|
100% |
9809
159.0 IPS |
|
Image Segmentation (Q)
|
99% |
10207
165.5 IPS |
|
Pose Estimation (SP)
|
100% |
6455
7.53 IPS |
|
Pose Estimation (HP)
|
100% |
69271
80.8 IPS |
|
Pose Estimation (Q)
|
95% |
67751
79.4 IPS |
|
Object Detection (SP)
|
100% |
1492
118.3 IPS |
|
Object Detection (HP)
|
99% |
7591
603.9 IPS |
|
Object Detection (Q)
|
91% |
6908
552.0 IPS |
|
Face Detection (SP)
|
100% |
3042
36.1 IPS |
|
Face Detection (HP)
|
100% |
17102
203.2 IPS |
|
Face Detection (Q)
|
100% |
15425
183.3 IPS |
|
Depth Estimation (SP)
|
100% |
5777
44.5 IPS |
|
Depth Estimation (HP)
|
99% |
48998
377.5 IPS |
|
Depth Estimation (Q)
|
85% |
50134
391.8 IPS |
|
Style Transfer (SP)
|
100% |
16780
21.6 IPS |
|
Style Transfer (HP)
|
100% |
122531
157.5 IPS |
|
Style Transfer (Q)
|
96% |
116446
150.3 IPS |
|
Image Super-Resolution (SP)
|
100% |
3764
139.0 IPS |
|
Image Super-Resolution (HP)
|
100% |
24192
893.3 IPS |
|
Image Super-Resolution (Q)
|
99% |
24971
922.1 IPS |
|
Text Classification (SP)
|
100% |
2367
3.16 KIPS |
|
Text Classification (HP)
|
100% |
4172
5.57 KIPS |
|
Text Classification (Q)
|
93% |
4139
5.56 KIPS |
|
Machine Translation (SP)
|
100% |
2506
43.2 IPS |
|
Machine Translation (HP)
|
100% |
4976
85.7 IPS |
|
Machine Translation (Q)
|
98% |
5094
88.0 IPS |