User | austinwewn98 |
Upload Date | February 19 2025 05:37 AM |
Views | 2 |
AI Information | |
---|---|
Framework | Core ML |
Backend | Neural Engine |
Device | Apple M2 Pro |
System Information | |
---|---|
Operating System | macOS 15.3.1 (Build 24D70) |
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 | 3.42 GHz |
Cluster 1 | 6 Cores |
Cluster 2 | 4 Cores |
Memory Information | |
---|---|
Size | 16.00 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
1379
256.5 IPS |
|
Image Classification (HP)
|
100% |
14641
2.72 KIPS |
|
Image Classification (Q)
|
96% |
17319
3.23 KIPS |
|
Image Segmentation (SP)
|
100% |
1720
27.9 IPS |
|
Image Segmentation (HP)
|
100% |
19411
314.7 IPS |
|
Image Segmentation (Q)
|
99% |
24278
393.6 IPS |
|
Pose Estimation (SP)
|
100% |
12698
14.8 IPS |
|
Pose Estimation (HP)
|
100% |
107215
125.1 IPS |
|
Pose Estimation (Q)
|
95% |
105059
123.1 IPS |
|
Object Detection (SP)
|
100% |
1671
132.5 IPS |
|
Object Detection (HP)
|
99% |
15516
1.23 KIPS |
|
Object Detection (Q)
|
91% |
17075
1.36 KIPS |
|
Face Detection (SP)
|
100% |
3641
43.3 IPS |
|
Face Detection (HP)
|
100% |
33397
396.8 IPS |
|
Face Detection (Q)
|
100% |
43452
516.3 IPS |
|
Depth Estimation (SP)
|
100% |
6368
49.1 IPS |
|
Depth Estimation (HP)
|
99% |
87872
677.0 IPS |
|
Depth Estimation (Q)
|
85% |
109995
859.6 IPS |
|
Style Transfer (SP)
|
100% |
25120
32.3 IPS |
|
Style Transfer (HP)
|
100% |
205798
264.6 IPS |
|
Style Transfer (Q)
|
96% |
193475
249.7 IPS |
|
Image Super-Resolution (SP)
|
100% |
5070
187.2 IPS |
|
Image Super-Resolution (HP)
|
100% |
41933
1.55 KIPS |
|
Image Super-Resolution (Q)
|
99% |
50571
1.87 KIPS |
|
Text Classification (SP)
|
100% |
2319
3.10 KIPS |
|
Text Classification (HP)
|
100% |
3945
5.27 KIPS |
|
Text Classification (Q)
|
93% |
3912
5.25 KIPS |
|
Machine Translation (SP)
|
100% |
4300
74.1 IPS |
|
Machine Translation (HP)
|
100% |
4021
69.3 IPS |
|
Machine Translation (Q)
|
98% |
4234
73.2 IPS |