Upload Date | January 04 2025 03:28 PM |
Views | 2 |
AI Information | |
---|---|
Framework | Core ML |
Backend | GPU |
Device | Apple M2 Pro |
System Information | |
---|---|
Operating System | macOS 15.1.1 (Build 24B91) |
Model | Mac mini (2023) |
Model ID | Mac14,12 |
Motherboard | Mac14,12 |
CPU Information | |
---|---|
Name | Apple M2 Pro |
Topology | 1 Processor, 10 Cores |
Identifier | Apple M2 Pro |
Base Frequency | 3.41 GHz |
Cluster 1 | 6 Cores |
Cluster 2 | 4 Cores |
Memory Information | |
---|---|
Size | 16.00 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
5212
969.2 IPS |
|
Image Classification (HP)
|
100% |
5317
988.7 IPS |
|
Image Classification (Q)
|
97% |
4510
841.7 IPS |
|
Image Segmentation (SP)
|
100% |
7315
118.6 IPS |
|
Image Segmentation (HP)
|
100% |
7282
118.0 IPS |
|
Image Segmentation (Q)
|
99% |
7173
116.3 IPS |
|
Pose Estimation (SP)
|
100% |
36105
42.1 IPS |
|
Pose Estimation (HP)
|
100% |
38533
45.0 IPS |
|
Pose Estimation (Q)
|
95% |
35773
41.9 IPS |
|
Object Detection (SP)
|
100% |
4807
381.3 IPS |
|
Object Detection (HP)
|
100% |
4892
388.0 IPS |
|
Object Detection (Q)
|
91% |
4109
328.3 IPS |
|
Face Detection (SP)
|
100% |
16512
196.2 IPS |
|
Face Detection (HP)
|
100% |
17501
207.9 IPS |
|
Face Detection (Q)
|
100% |
12408
147.4 IPS |
|
Depth Estimation (SP)
|
100% |
23818
183.5 IPS |
|
Depth Estimation (HP)
|
99% |
24807
191.1 IPS |
|
Depth Estimation (Q)
|
85% |
20363
159.1 IPS |
|
Style Transfer (SP)
|
100% |
67629
86.9 IPS |
|
Style Transfer (HP)
|
100% |
73769
94.8 IPS |
|
Style Transfer (Q)
|
96% |
68608
88.5 IPS |
|
Image Super-Resolution (SP)
|
100% |
13493
498.2 IPS |
|
Image Super-Resolution (HP)
|
100% |
14210
524.7 IPS |
|
Image Super-Resolution (Q)
|
99% |
11011
406.6 IPS |
|
Text Classification (SP)
|
100% |
2298
3.07 KIPS |
|
Text Classification (HP)
|
100% |
4034
5.39 KIPS |
|
Text Classification (Q)
|
93% |
3847
5.16 KIPS |
|
Machine Translation (SP)
|
100% |
822
14.2 IPS |
|
Machine Translation (HP)
|
100% |
802
13.8 IPS |
|
Machine Translation (Q)
|
98% |
734
12.7 IPS |