Upload Date | January 12 2025 01:36 PM |
Views | 2 |
AI Information | |
---|---|
Framework | Core ML |
Backend | Neural Engine |
Device | Apple M2 |
System Information | |
---|---|
Operating System | macOS 15.2 (Build 24C101) |
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 | 3.18 GHz |
Cluster 1 | 4 Cores |
Cluster 2 | 4 Cores |
Memory Information | |
---|---|
Size | 16.00 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
1007
187.2 IPS |
|
Image Classification (HP)
|
100% |
10453
1.94 KIPS |
|
Image Classification (Q)
|
96% |
14444
2.70 KIPS |
|
Image Segmentation (SP)
|
100% |
885
14.3 IPS |
|
Image Segmentation (HP)
|
100% |
16805
272.4 IPS |
|
Image Segmentation (Q)
|
99% |
21165
343.1 IPS |
|
Pose Estimation (SP)
|
100% |
4622
5.39 IPS |
|
Pose Estimation (HP)
|
100% |
95695
111.7 IPS |
|
Pose Estimation (Q)
|
95% |
93800
109.9 IPS |
|
Object Detection (SP)
|
100% |
1118
88.6 IPS |
|
Object Detection (HP)
|
99% |
14085
1.12 KIPS |
|
Object Detection (Q)
|
91% |
13816
1.10 KIPS |
|
Face Detection (SP)
|
100% |
2032
24.1 IPS |
|
Face Detection (HP)
|
100% |
28446
338.0 IPS |
|
Face Detection (Q)
|
100% |
36223
430.4 IPS |
|
Depth Estimation (SP)
|
100% |
4077
31.4 IPS |
|
Depth Estimation (HP)
|
99% |
73630
567.3 IPS |
|
Depth Estimation (Q)
|
85% |
102007
797.1 IPS |
|
Style Transfer (SP)
|
100% |
13430
17.3 IPS |
|
Style Transfer (HP)
|
100% |
178711
229.7 IPS |
|
Style Transfer (Q)
|
96% |
179231
231.3 IPS |
|
Image Super-Resolution (SP)
|
100% |
2852
105.3 IPS |
|
Image Super-Resolution (HP)
|
100% |
36521
1.35 KIPS |
|
Image Super-Resolution (Q)
|
99% |
42796
1.58 KIPS |
|
Text Classification (SP)
|
100% |
2019
2.69 KIPS |
|
Text Classification (HP)
|
100% |
3462
4.62 KIPS |
|
Text Classification (Q)
|
93% |
3394
4.56 KIPS |
|
Machine Translation (SP)
|
100% |
2472
42.6 IPS |
|
Machine Translation (HP)
|
100% |
2959
51.0 IPS |
|
Machine Translation (Q)
|
98% |
2698
46.6 IPS |