Upload Date | September 18 2024 02:32 AM |
Views | 3 |
AI Information | |
---|---|
Framework | Core ML |
Backend | CPU |
Device | Apple M2 Pro |
System Information | |
---|---|
Operating System | macOS 14.6.1 (Build 23G93) |
Model | MacBook Pro (16-inch, 2023) |
Model ID | Mac14,10 |
Motherboard | Mac14,10 |
CPU Information | |
---|---|
Name | Apple M2 Pro |
Topology | 1 Processor, 12 Cores |
Identifier | Apple M2 Pro |
Base Frequency | 2.69 GHz |
Cluster 1 | 8 Cores |
Cluster 2 | 4 Cores |
Memory Information | |
---|---|
Size | 16.00 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
1254
233.2 IPS |
|
Image Classification (HP)
|
100% |
1532
284.8 IPS |
|
Image Classification (Q)
|
96% |
1124
209.9 IPS |
|
Image Segmentation (SP)
|
100% |
1094
17.7 IPS |
|
Image Segmentation (HP)
|
100% |
1048
17.0 IPS |
|
Image Segmentation (Q)
|
99% |
1491
24.2 IPS |
|
Pose Estimation (SP)
|
100% |
5244
6.12 IPS |
|
Pose Estimation (HP)
|
100% |
12464
14.5 IPS |
|
Pose Estimation (Q)
|
95% |
10789
12.6 IPS |
|
Object Detection (SP)
|
100% |
1349
107.0 IPS |
|
Object Detection (HP)
|
97% |
1889
150.4 IPS |
|
Object Detection (Q)
|
94% |
1430
114.0 IPS |
|
Face Detection (SP)
|
100% |
2482
29.5 IPS |
|
Face Detection (HP)
|
100% |
3705
44.0 IPS |
|
Face Detection (Q)
|
100% |
2371
28.2 IPS |
|
Depth Estimation (SP)
|
100% |
4685
36.1 IPS |
|
Depth Estimation (HP)
|
97% |
7278
56.3 IPS |
|
Depth Estimation (Q)
|
86% |
5411
42.2 IPS |
|
Style Transfer (SP)
|
100% |
13919
17.9 IPS |
|
Style Transfer (HP)
|
100% |
21684
27.9 IPS |
|
Style Transfer (Q)
|
96% |
18618
24.0 IPS |
|
Image Super-Resolution (SP)
|
100% |
3224
119.1 IPS |
|
Image Super-Resolution (HP)
|
100% |
3920
144.7 IPS |
|
Image Super-Resolution (Q)
|
99% |
3084
113.9 IPS |
|
Text Classification (SP)
|
100% |
2005
2.68 KIPS |
|
Text Classification (HP)
|
100% |
2795
3.73 KIPS |
|
Text Classification (Q)
|
93% |
2766
3.71 KIPS |
|
Machine Translation (SP)
|
100% |
1934
33.3 IPS |
|
Machine Translation (HP)
|
98% |
3985
68.9 IPS |
|
Machine Translation (Q)
|
98% |
3932
67.9 IPS |