User | KD8UXA |
Upload Date | December 05 2024 09:50 PM |
Views | 2 |
AI Information | |
---|---|
Framework | Core ML |
Backend | Neural Engine |
Device | Apple M2 |
System Information | |
---|---|
Operating System | macOS 14.4 (Build 23E214) |
Model | Mac mini (2023) |
Model ID | Mac14,3 |
Motherboard | Mac14,3 |
CPU Information | |
---|---|
Name | Apple M2 |
Topology | 1 Processor, 8 Cores |
Identifier | Apple M2 |
Base Frequency | 3.48 GHz |
Cluster 1 | 4 Cores |
Cluster 2 | 4 Cores |
Memory Information | |
---|---|
Size | 8.00 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
1167
217.0 IPS |
|
Image Classification (HP)
|
100% |
7647
1.42 KIPS |
|
Image Classification (Q)
|
96% |
7905
1.48 KIPS |
|
Image Segmentation (SP)
|
100% |
708
11.5 IPS |
|
Image Segmentation (HP)
|
100% |
5157
83.6 IPS |
|
Image Segmentation (Q)
|
99% |
8239
133.6 IPS |
|
Pose Estimation (SP)
|
100% |
5936
6.93 IPS |
|
Pose Estimation (HP)
|
100% |
90794
105.9 IPS |
|
Pose Estimation (Q)
|
95% |
89195
104.5 IPS |
|
Object Detection (SP)
|
100% |
1243
98.6 IPS |
|
Object Detection (HP)
|
99% |
8696
691.8 IPS |
|
Object Detection (Q)
|
93% |
9067
723.5 IPS |
|
Face Detection (SP)
|
100% |
2117
25.2 IPS |
|
Face Detection (HP)
|
100% |
11599
137.8 IPS |
|
Face Detection (Q)
|
100% |
13560
161.1 IPS |
|
Depth Estimation (SP)
|
100% |
3822
29.4 IPS |
|
Depth Estimation (HP)
|
99% |
48506
373.7 IPS |
|
Depth Estimation (Q)
|
85% |
60178
470.3 IPS |
|
Style Transfer (SP)
|
100% |
10659
13.7 IPS |
|
Style Transfer (HP)
|
100% |
139443
179.3 IPS |
|
Style Transfer (Q)
|
95% |
126304
163.1 IPS |
|
Image Super-Resolution (SP)
|
100% |
3092
114.2 IPS |
|
Image Super-Resolution (HP)
|
100% |
19859
733.3 IPS |
|
Image Super-Resolution (Q)
|
99% |
25739
950.4 IPS |
|
Text Classification (SP)
|
100% |
813
1.09 KIPS |
|
Text Classification (HP)
|
100% |
693
924.8 IPS |
|
Text Classification (Q)
|
93% |
683
917.0 IPS |
|
Machine Translation (SP)
|
100% |
1661
28.6 IPS |
|
Machine Translation (HP)
|
100% |
2401
41.4 IPS |
|
Machine Translation (Q)
|
98% |
2391
41.3 IPS |