User | tlonergan02 |
Upload Date | November 04 2024 05:17 AM |
Views | 12 |
AI Information | |
---|---|
Framework | Core ML |
Backend | GPU |
Device | Apple M3 Pro |
System Information | |
---|---|
Operating System | macOS 15.2 (Build 24C5057p) |
Model | MacBook Pro (14-inch, Nov 2023) |
Model ID | Mac15,6 |
Motherboard | Mac15,6 |
CPU Information | |
---|---|
Name | Apple M3 Pro |
Topology | 1 Processor, 11 Cores |
Identifier | Apple M3 Pro |
Base Frequency | 4.05 GHz |
Cluster 1 | 5 Cores |
Cluster 2 | 6 Cores |
Memory Information | |
---|---|
Size | 18.00 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
5293
984.3 IPS |
|
Image Classification (HP)
|
100% |
5695
1.06 KIPS |
|
Image Classification (Q)
|
97% |
4734
883.4 IPS |
|
Image Segmentation (SP)
|
100% |
6733
109.2 IPS |
|
Image Segmentation (HP)
|
100% |
8588
139.2 IPS |
|
Image Segmentation (Q)
|
99% |
8875
143.9 IPS |
|
Pose Estimation (SP)
|
100% |
34810
40.6 IPS |
|
Pose Estimation (HP)
|
100% |
36698
42.8 IPS |
|
Pose Estimation (Q)
|
95% |
33826
39.6 IPS |
|
Object Detection (SP)
|
100% |
5466
433.6 IPS |
|
Object Detection (HP)
|
100% |
5669
449.6 IPS |
|
Object Detection (Q)
|
91% |
4943
395.0 IPS |
|
Face Detection (SP)
|
100% |
14975
177.9 IPS |
|
Face Detection (HP)
|
100% |
19103
227.0 IPS |
|
Face Detection (Q)
|
100% |
13597
161.6 IPS |
|
Depth Estimation (SP)
|
100% |
22919
176.6 IPS |
|
Depth Estimation (HP)
|
99% |
24009
185.0 IPS |
|
Depth Estimation (Q)
|
85% |
21005
164.2 IPS |
|
Style Transfer (SP)
|
100% |
75330
96.8 IPS |
|
Style Transfer (HP)
|
100% |
84145
108.2 IPS |
|
Style Transfer (Q)
|
96% |
79971
103.2 IPS |
|
Image Super-Resolution (SP)
|
100% |
13274
490.1 IPS |
|
Image Super-Resolution (HP)
|
100% |
14615
539.7 IPS |
|
Image Super-Resolution (Q)
|
99% |
11344
418.9 IPS |
|
Text Classification (SP)
|
100% |
2751
3.67 KIPS |
|
Text Classification (HP)
|
100% |
4760
6.35 KIPS |
|
Text Classification (Q)
|
93% |
4704
6.31 KIPS |
|
Machine Translation (SP)
|
100% |
2042
35.2 IPS |
|
Machine Translation (HP)
|
100% |
2126
36.6 IPS |
|
Machine Translation (Q)
|
98% |
1854
32.0 IPS |