User | NPoutanen |
Upload Date | November 26 2024 03:59 PM |
Views | 2 |
AI Information | |
---|---|
Framework | Core ML |
Backend | Neural Engine |
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 | 3.47 GHz |
Cluster 1 | 6 Cores |
Cluster 2 | 4 Cores |
Memory Information | |
---|---|
Size | 16.00 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
1392
258.9 IPS |
|
Image Classification (HP)
|
100% |
14045
2.61 KIPS |
|
Image Classification (Q)
|
96% |
17993
3.36 KIPS |
|
Image Segmentation (SP)
|
100% |
1667
27.0 IPS |
|
Image Segmentation (HP)
|
100% |
19536
316.7 IPS |
|
Image Segmentation (Q)
|
99% |
24039
389.7 IPS |
|
Pose Estimation (SP)
|
100% |
12747
14.9 IPS |
|
Pose Estimation (HP)
|
100% |
107657
125.6 IPS |
|
Pose Estimation (Q)
|
95% |
104194
122.1 IPS |
|
Object Detection (SP)
|
100% |
1666
132.2 IPS |
|
Object Detection (HP)
|
99% |
15329
1.22 KIPS |
|
Object Detection (Q)
|
91% |
16898
1.35 KIPS |
|
Face Detection (SP)
|
100% |
3584
42.6 IPS |
|
Face Detection (HP)
|
100% |
35516
422.0 IPS |
|
Face Detection (Q)
|
100% |
45265
537.8 IPS |
|
Depth Estimation (SP)
|
100% |
6335
48.8 IPS |
|
Depth Estimation (HP)
|
99% |
87823
676.6 IPS |
|
Depth Estimation (Q)
|
85% |
109148
852.9 IPS |
|
Style Transfer (SP)
|
100% |
24931
32.0 IPS |
|
Style Transfer (HP)
|
100% |
202479
260.3 IPS |
|
Style Transfer (Q)
|
96% |
189622
244.7 IPS |
|
Image Super-Resolution (SP)
|
100% |
5084
187.7 IPS |
|
Image Super-Resolution (HP)
|
100% |
41422
1.53 KIPS |
|
Image Super-Resolution (Q)
|
99% |
50675
1.87 KIPS |
|
Text Classification (SP)
|
100% |
2283
3.05 KIPS |
|
Text Classification (HP)
|
100% |
3995
5.33 KIPS |
|
Text Classification (Q)
|
93% |
3970
5.33 KIPS |
|
Machine Translation (SP)
|
100% |
4225
72.8 IPS |
|
Machine Translation (HP)
|
100% |
4846
83.5 IPS |
|
Machine Translation (Q)
|
98% |
5413
93.5 IPS |