User | jackhuang2024 |
Upload Date | September 20 2024 09:16 PM |
Views | 6 |
AI Information | |
---|---|
Framework | Core ML |
Backend | Neural Engine |
Device | Apple M3 Pro |
System Information | |
---|---|
Operating System | macOS 14.5 (Build 23F79) |
Model | MacBook Pro (16-inch, Nov 2023) |
Model ID | Mac15,7 |
Motherboard | Mac15,7 |
CPU Information | |
---|---|
Name | Apple M3 Pro |
Topology | 1 Processor, 12 Cores |
Identifier | Apple M3 Pro |
Base Frequency | 4.05 GHz |
Cluster 1 | 6 Cores |
Cluster 2 | 6 Cores |
Memory Information | |
---|---|
Size | 18.00 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
1328
246.9 IPS |
|
Image Classification (HP)
|
100% |
7458
1.39 KIPS |
|
Image Classification (Q)
|
97% |
7702
1.44 KIPS |
|
Image Segmentation (SP)
|
100% |
846
13.7 IPS |
|
Image Segmentation (HP)
|
100% |
6698
108.6 IPS |
|
Image Segmentation (Q)
|
99% |
13057
211.7 IPS |
|
Pose Estimation (SP)
|
100% |
8498
9.92 IPS |
|
Pose Estimation (HP)
|
100% |
102392
119.5 IPS |
|
Pose Estimation (Q)
|
95% |
103552
121.4 IPS |
|
Object Detection (SP)
|
100% |
1497
118.8 IPS |
|
Object Detection (HP)
|
100% |
9896
784.9 IPS |
|
Object Detection (Q)
|
93% |
10546
841.5 IPS |
|
Face Detection (SP)
|
100% |
2463
29.3 IPS |
|
Face Detection (HP)
|
100% |
13354
158.7 IPS |
|
Face Detection (Q)
|
100% |
16021
190.4 IPS |
|
Depth Estimation (SP)
|
100% |
4863
37.5 IPS |
|
Depth Estimation (HP)
|
99% |
59021
454.7 IPS |
|
Depth Estimation (Q)
|
85% |
70959
554.8 IPS |
|
Style Transfer (SP)
|
100% |
12544
16.1 IPS |
|
Style Transfer (HP)
|
100% |
151476
194.7 IPS |
|
Style Transfer (Q)
|
96% |
141358
182.4 IPS |
|
Image Super-Resolution (SP)
|
100% |
4197
155.0 IPS |
|
Image Super-Resolution (HP)
|
100% |
21040
776.9 IPS |
|
Image Super-Resolution (Q)
|
99% |
26515
979.1 IPS |
|
Text Classification (SP)
|
100% |
549
733.0 IPS |
|
Text Classification (HP)
|
100% |
4254
5.68 KIPS |
|
Text Classification (Q)
|
93% |
4183
5.61 KIPS |
|
Machine Translation (SP)
|
100% |
2212
38.1 IPS |
|
Machine Translation (HP)
|
100% |
2790
48.1 IPS |
|
Machine Translation (Q)
|
98% |
2796
48.3 IPS |