User | andrewkendall |
Upload Date | August 15 2024 06:30 PM |
Views | 2 |
AI Information | |
---|---|
Framework | Core ML |
Backend | GPU |
Device | Apple M1 Pro |
System Information | |
---|---|
Operating System | macOS 14.6.1 (Build 23G93) |
Model | MacBook Pro (16-inch, 2021) |
Model ID | MacBookPro18,1 |
Motherboard | MacBookPro18,1 |
CPU Information | |
---|---|
Name | Apple M1 Pro |
Topology | 1 Processor, 10 Cores |
Identifier | Apple M1 Pro |
Base Frequency | 3.22 GHz |
Cluster 1 | 8 Cores |
Cluster 2 | 2 Cores |
Memory Information | |
---|---|
Size | 16.00 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
3729
693.4 IPS |
|
Image Classification (HP)
|
100% |
3770
701.0 IPS |
|
Image Classification (Q)
|
99% |
3257
607.4 IPS |
|
Image Segmentation (SP)
|
100% |
6028
97.7 IPS |
|
Image Segmentation (HP)
|
100% |
6157
99.8 IPS |
|
Image Segmentation (Q)
|
100% |
5928
96.1 IPS |
|
Pose Estimation (SP)
|
100% |
32913
38.4 IPS |
|
Pose Estimation (HP)
|
100% |
34350
40.1 IPS |
|
Pose Estimation (Q)
|
96% |
30568
35.8 IPS |
|
Object Detection (SP)
|
100% |
3761
298.3 IPS |
|
Object Detection (HP)
|
100% |
3926
311.4 IPS |
|
Object Detection (Q)
|
92% |
3042
242.8 IPS |
|
Face Detection (SP)
|
100% |
12536
149.0 IPS |
|
Face Detection (HP)
|
100% |
13387
159.1 IPS |
|
Face Detection (Q)
|
100% |
9148
108.7 IPS |
|
Depth Estimation (SP)
|
100% |
19844
152.9 IPS |
|
Depth Estimation (HP)
|
99% |
20151
155.3 IPS |
|
Depth Estimation (Q)
|
97% |
19969
154.4 IPS |
|
Style Transfer (SP)
|
100% |
53592
68.9 IPS |
|
Style Transfer (HP)
|
100% |
63277
81.3 IPS |
|
Style Transfer (Q)
|
100% |
63607
81.8 IPS |
|
Image Super-Resolution (SP)
|
100% |
11038
407.6 IPS |
|
Image Super-Resolution (HP)
|
100% |
11726
433.0 IPS |
|
Image Super-Resolution (Q)
|
98% |
8699
322.3 IPS |
|
Text Classification (SP)
|
100% |
1065
1.42 KIPS |
|
Text Classification (HP)
|
100% |
560
747.1 IPS |
|
Text Classification (Q)
|
93% |
437
586.2 IPS |
|
Machine Translation (SP)
|
100% |
1014
17.5 IPS |
|
Machine Translation (HP)
|
100% |
1050
18.1 IPS |
|
Machine Translation (Q)
|
98% |
1099
19.0 IPS |