User | HJD |
Upload Date | November 13 2024 01:25 AM |
Views | 6 |
AI Information | |
---|---|
Framework | Core ML |
Backend | Neural Engine |
Device | Apple M1 Pro |
System Information | |
---|---|
Operating System | macOS 15.1 (Build 24B83) |
Model | MacBook Pro (14-inch, 2021) |
Model ID | MacBookPro18,3 |
Motherboard | MacBookPro18,3 |
CPU Information | |
---|---|
Name | Apple M1 Pro |
Topology | 1 Processor, 8 Cores |
Identifier | Apple M1 Pro |
Base Frequency | 3.22 GHz |
Cluster 1 | 6 Cores |
Cluster 2 | 2 Cores |
Memory Information | |
---|---|
Size | 16.00 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
1318
245.2 IPS |
|
Image Classification (HP)
|
100% |
6814
1.27 KIPS |
|
Image Classification (Q)
|
96% |
6597
1.23 KIPS |
|
Image Segmentation (SP)
|
100% |
1595
25.9 IPS |
|
Image Segmentation (HP)
|
100% |
9695
157.2 IPS |
|
Image Segmentation (Q)
|
99% |
10284
166.7 IPS |
|
Pose Estimation (SP)
|
100% |
11188
13.1 IPS |
|
Pose Estimation (HP)
|
100% |
70578
82.4 IPS |
|
Pose Estimation (Q)
|
95% |
66041
77.4 IPS |
|
Object Detection (SP)
|
100% |
1581
125.4 IPS |
|
Object Detection (HP)
|
99% |
7932
631.0 IPS |
|
Object Detection (Q)
|
91% |
7447
595.1 IPS |
|
Face Detection (SP)
|
100% |
3194
38.0 IPS |
|
Face Detection (HP)
|
100% |
15844
188.3 IPS |
|
Face Detection (Q)
|
100% |
14977
178.0 IPS |
|
Depth Estimation (SP)
|
100% |
5865
45.2 IPS |
|
Depth Estimation (HP)
|
99% |
50964
392.6 IPS |
|
Depth Estimation (Q)
|
85% |
53705
419.7 IPS |
|
Style Transfer (SP)
|
100% |
22569
29.0 IPS |
|
Style Transfer (HP)
|
100% |
120595
155.0 IPS |
|
Style Transfer (Q)
|
96% |
116607
150.5 IPS |
|
Image Super-Resolution (SP)
|
100% |
4347
160.5 IPS |
|
Image Super-Resolution (HP)
|
100% |
26031
961.2 IPS |
|
Image Super-Resolution (Q)
|
99% |
28150
1.04 KIPS |
|
Text Classification (SP)
|
100% |
2284
3.05 KIPS |
|
Text Classification (HP)
|
100% |
3938
5.26 KIPS |
|
Text Classification (Q)
|
93% |
3977
5.34 KIPS |
|
Machine Translation (SP)
|
100% |
3315
57.1 IPS |
|
Machine Translation (HP)
|
100% |
3865
66.6 IPS |
|
Machine Translation (Q)
|
98% |
3966
68.5 IPS |