Upload Date | September 14 2024 03:34 AM |
Views | 3 |
AI Information | |
---|---|
Framework | Core ML |
Backend | Neural Engine |
Device | Apple M2 |
System Information | |
---|---|
Operating System | macOS 15.0 (Build 24A335) |
Model | MacBook Air (2022) |
Model ID | Mac14,2 |
Motherboard | Mac14,2 |
CPU Information | |
---|---|
Name | Apple M2 |
Topology | 1 Processor, 8 Cores |
Identifier | Apple M2 |
Base Frequency | 1.95 GHz |
Cluster 1 | 4 Cores |
Cluster 2 | 4 Cores |
Memory Information | |
---|---|
Size | 16.00 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
886
164.8 IPS |
|
Image Classification (HP)
|
100% |
10810
2.01 KIPS |
|
Image Classification (Q)
|
99% |
11504
2.15 KIPS |
|
Image Segmentation (SP)
|
100% |
1017
16.5 IPS |
|
Image Segmentation (HP)
|
100% |
7092
115.0 IPS |
|
Image Segmentation (Q)
|
100% |
7090
114.9 IPS |
|
Pose Estimation (SP)
|
100% |
4232
4.94 IPS |
|
Pose Estimation (HP)
|
100% |
66716
77.8 IPS |
|
Pose Estimation (Q)
|
94% |
64608
75.8 IPS |
|
Object Detection (SP)
|
100% |
1021
81.0 IPS |
|
Object Detection (HP)
|
99% |
11431
909.3 IPS |
|
Object Detection (Q)
|
91% |
11975
956.8 IPS |
|
Face Detection (SP)
|
100% |
2191
26.0 IPS |
|
Face Detection (HP)
|
100% |
17659
209.8 IPS |
|
Face Detection (Q)
|
100% |
25599
304.2 IPS |
|
Depth Estimation (SP)
|
100% |
3678
28.3 IPS |
|
Depth Estimation (HP)
|
99% |
54174
417.4 IPS |
|
Depth Estimation (Q)
|
97% |
57675
446.0 IPS |
|
Style Transfer (SP)
|
100% |
11670
15.0 IPS |
|
Style Transfer (HP)
|
100% |
124055
159.5 IPS |
|
Style Transfer (Q)
|
100% |
124683
160.3 IPS |
|
Image Super-Resolution (SP)
|
100% |
2677
98.8 IPS |
|
Image Super-Resolution (HP)
|
100% |
29681
1.10 KIPS |
|
Image Super-Resolution (Q)
|
98% |
33056
1.22 KIPS |
|
Text Classification (SP)
|
100% |
1509
2.01 KIPS |
|
Text Classification (HP)
|
100% |
2382
3.18 KIPS |
|
Text Classification (Q)
|
93% |
2388
3.20 KIPS |
|
Machine Translation (SP)
|
100% |
2520
43.4 IPS |
|
Machine Translation (HP)
|
100% |
1644
28.3 IPS |
|
Machine Translation (Q)
|
98% |
1642
28.4 IPS |