User | dokidoki0802 |
Upload Date | October 09 2024 06:13 AM |
Views | 3 |
AI Information | |
---|---|
Framework | Core ML |
Backend | GPU |
Device | Apple M3 Pro |
System Information | |
---|---|
Operating System | macOS 15.1 (Build 24B5070a) |
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 | 36.00 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
6403
1.19 KIPS |
|
Image Classification (HP)
|
100% |
6708
1.25 KIPS |
|
Image Classification (Q)
|
99% |
6662
1.24 KIPS |
|
Image Segmentation (SP)
|
100% |
7304
118.4 IPS |
|
Image Segmentation (HP)
|
100% |
10099
163.7 IPS |
|
Image Segmentation (Q)
|
100% |
9993
162.0 IPS |
|
Pose Estimation (SP)
|
100% |
45715
53.3 IPS |
|
Pose Estimation (HP)
|
100% |
48570
56.7 IPS |
|
Pose Estimation (Q)
|
97% |
44964
52.7 IPS |
|
Object Detection (SP)
|
100% |
6146
487.5 IPS |
|
Object Detection (HP)
|
100% |
6560
520.3 IPS |
|
Object Detection (Q)
|
91% |
5492
438.9 IPS |
|
Face Detection (SP)
|
100% |
16946
201.4 IPS |
|
Face Detection (HP)
|
100% |
21832
259.4 IPS |
|
Face Detection (Q)
|
100% |
15938
189.4 IPS |
|
Depth Estimation (SP)
|
100% |
27426
211.3 IPS |
|
Depth Estimation (HP)
|
99% |
31102
239.6 IPS |
|
Depth Estimation (Q)
|
97% |
4536
35.1 IPS |
|
Style Transfer (SP)
|
100% |
92489
118.9 IPS |
|
Style Transfer (HP)
|
100% |
106616
137.1 IPS |
|
Style Transfer (Q)
|
100% |
106820
137.3 IPS |
|
Image Super-Resolution (SP)
|
100% |
15329
566.0 IPS |
|
Image Super-Resolution (HP)
|
100% |
16589
612.6 IPS |
|
Image Super-Resolution (Q)
|
98% |
12105
448.5 IPS |
|
Text Classification (SP)
|
100% |
2782
3.71 KIPS |
|
Text Classification (HP)
|
100% |
4806
6.41 KIPS |
|
Text Classification (Q)
|
93% |
4793
6.43 KIPS |
|
Machine Translation (SP)
|
100% |
2333
40.2 IPS |
|
Machine Translation (HP)
|
100% |
2158
37.2 IPS |
|
Machine Translation (Q)
|
98% |
1953
33.8 IPS |