User | M1_MACBOOK |
Upload Date | November 01 2024 03:10 AM |
Views | 2 |
AI Information | |
---|---|
Framework | Core ML |
Backend | Neural Engine |
Device | Apple M1 |
System Information | |
---|---|
Operating System | macOS 14.7.1 (Build 23H222) |
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 | 1.30 GHz |
Cluster 1 | 4 Cores |
Cluster 2 | 4 Cores |
Memory Information | |
---|---|
Size | 8.00 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
378
70.2 IPS |
|
Image Classification (HP)
|
100% |
2828
525.9 IPS |
|
Image Classification (Q)
|
96% |
2577
481.2 IPS |
|
Image Segmentation (SP)
|
100% |
178
2.89 IPS |
|
Image Segmentation (HP)
|
100% |
1963
31.8 IPS |
|
Image Segmentation (Q)
|
99% |
142
2.30 IPS |
|
Pose Estimation (SP)
|
100% |
1527
1.78 IPS |
|
Pose Estimation (HP)
|
100% |
26999
31.5 IPS |
|
Pose Estimation (Q)
|
95% |
25964
30.4 IPS |
|
Object Detection (SP)
|
100% |
301
23.9 IPS |
|
Object Detection (HP)
|
99% |
2905
231.0 IPS |
|
Object Detection (Q)
|
93% |
2675
213.5 IPS |
|
Face Detection (SP)
|
100% |
567
6.74 IPS |
|
Face Detection (HP)
|
100% |
4860
57.7 IPS |
|
Face Detection (Q)
|
100% |
4878
58.0 IPS |
|
Depth Estimation (SP)
|
100% |
983
7.57 IPS |
|
Depth Estimation (HP)
|
99% |
19766
152.3 IPS |
|
Depth Estimation (Q)
|
85% |
21079
164.7 IPS |
|
Style Transfer (SP)
|
100% |
2770
3.56 IPS |
|
Style Transfer (HP)
|
100% |
54283
69.8 IPS |
|
Style Transfer (Q)
|
96% |
50272
64.9 IPS |
|
Image Super-Resolution (SP)
|
100% |
778
28.7 IPS |
|
Image Super-Resolution (HP)
|
100% |
8521
314.6 IPS |
|
Image Super-Resolution (Q)
|
99% |
9415
347.6 IPS |
|
Text Classification (SP)
|
100% |
147
195.6 IPS |
|
Text Classification (HP)
|
100% |
1626
2.17 KIPS |
|
Text Classification (Q)
|
93% |
1598
2.15 KIPS |
|
Machine Translation (SP)
|
100% |
529
9.11 IPS |
|
Machine Translation (HP)
|
100% |
940
16.2 IPS |
|
Machine Translation (Q)
|
98% |
1002
17.3 IPS |