User | dokidoki0802 |
Upload Date | October 02 2024 06:45 AM |
Views | 4 |
AI Information | |
---|---|
Framework | Core ML |
Backend | GPU |
Device | Apple M3 Pro |
System Information | |
---|---|
Operating System | macOS 15.1 (Build 24B5055e) |
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% |
5849
1.09 KIPS |
|
Image Classification (HP)
|
100% |
6359
1.18 KIPS |
|
Image Classification (Q)
|
99% |
6325
1.18 KIPS |
|
Image Segmentation (SP)
|
100% |
7174
116.3 IPS |
|
Image Segmentation (HP)
|
100% |
10000
162.1 IPS |
|
Image Segmentation (Q)
|
100% |
9845
159.6 IPS |
|
Pose Estimation (SP)
|
100% |
44740
52.2 IPS |
|
Pose Estimation (HP)
|
100% |
48248
56.3 IPS |
|
Pose Estimation (Q)
|
97% |
44662
52.3 IPS |
|
Object Detection (SP)
|
100% |
5929
470.3 IPS |
|
Object Detection (HP)
|
100% |
6471
513.3 IPS |
|
Object Detection (Q)
|
91% |
5397
431.2 IPS |
|
Face Detection (SP)
|
100% |
16571
196.9 IPS |
|
Face Detection (HP)
|
100% |
21030
249.9 IPS |
|
Face Detection (Q)
|
100% |
15596
185.3 IPS |
|
Depth Estimation (SP)
|
100% |
26907
207.3 IPS |
|
Depth Estimation (HP)
|
99% |
29532
227.5 IPS |
|
Depth Estimation (Q)
|
97% |
4529
35.0 IPS |
|
Style Transfer (SP)
|
100% |
91486
117.6 IPS |
|
Style Transfer (HP)
|
100% |
104777
134.7 IPS |
|
Style Transfer (Q)
|
100% |
106353
136.7 IPS |
|
Image Super-Resolution (SP)
|
100% |
16398
605.5 IPS |
|
Image Super-Resolution (HP)
|
100% |
17436
643.8 IPS |
|
Image Super-Resolution (Q)
|
98% |
12673
469.5 IPS |
|
Text Classification (SP)
|
100% |
2656
3.54 KIPS |
|
Text Classification (HP)
|
100% |
4819
6.43 KIPS |
|
Text Classification (Q)
|
93% |
4835
6.49 KIPS |
|
Machine Translation (SP)
|
100% |
2344
40.4 IPS |
|
Machine Translation (HP)
|
100% |
2020
34.8 IPS |
|
Machine Translation (Q)
|
98% |
1911
33.0 IPS |