User | dokidoki0802 |
Upload Date | September 29 2024 08:36 AM |
Views | 3 |
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% |
6099
1.13 KIPS |
|
Image Classification (HP)
|
100% |
6427
1.20 KIPS |
|
Image Classification (Q)
|
99% |
6428
1.20 KIPS |
|
Image Segmentation (SP)
|
100% |
7451
120.8 IPS |
|
Image Segmentation (HP)
|
100% |
10048
162.9 IPS |
|
Image Segmentation (Q)
|
100% |
10257
166.3 IPS |
|
Pose Estimation (SP)
|
100% |
45389
53.0 IPS |
|
Pose Estimation (HP)
|
100% |
48360
56.4 IPS |
|
Pose Estimation (Q)
|
97% |
44788
52.4 IPS |
|
Object Detection (SP)
|
100% |
5857
464.6 IPS |
|
Object Detection (HP)
|
100% |
6407
508.2 IPS |
|
Object Detection (Q)
|
91% |
5352
427.6 IPS |
|
Face Detection (SP)
|
100% |
16476
195.8 IPS |
|
Face Detection (HP)
|
100% |
21202
251.9 IPS |
|
Face Detection (Q)
|
100% |
15596
185.3 IPS |
|
Depth Estimation (SP)
|
100% |
27248
209.9 IPS |
|
Depth Estimation (HP)
|
99% |
30221
232.8 IPS |
|
Depth Estimation (Q)
|
97% |
4527
35.0 IPS |
|
Style Transfer (SP)
|
100% |
92212
118.5 IPS |
|
Style Transfer (HP)
|
100% |
106053
136.3 IPS |
|
Style Transfer (Q)
|
100% |
105963
136.2 IPS |
|
Image Super-Resolution (SP)
|
100% |
15114
558.1 IPS |
|
Image Super-Resolution (HP)
|
100% |
16205
598.4 IPS |
|
Image Super-Resolution (Q)
|
98% |
11845
438.8 IPS |
|
Text Classification (SP)
|
100% |
2750
3.67 KIPS |
|
Text Classification (HP)
|
100% |
4800
6.41 KIPS |
|
Text Classification (Q)
|
93% |
4706
6.32 KIPS |
|
Machine Translation (SP)
|
100% |
2270
39.1 IPS |
|
Machine Translation (HP)
|
100% |
2300
39.6 IPS |
|
Machine Translation (Q)
|
98% |
1927
33.3 IPS |