User | afisch |
Upload Date | August 18 2024 07:29 AM |
Views | 2 |
AI Information | |
---|---|
Framework | Core ML |
Backend | Neural Engine |
Device | Apple M1 Pro |
System Information | |
---|---|
Operating System | macOS 15.1 (Build 24B5024e) |
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 | 2.44 GHz |
Cluster 1 | 6 Cores |
Cluster 2 | 2 Cores |
Memory Information | |
---|---|
Size | 16.00 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
1163
216.2 IPS |
|
Image Classification (HP)
|
100% |
6269
1.17 KIPS |
|
Image Classification (Q)
|
99% |
6611
1.23 KIPS |
|
Image Segmentation (SP)
|
100% |
1398
22.7 IPS |
|
Image Segmentation (HP)
|
100% |
5627
91.2 IPS |
|
Image Segmentation (Q)
|
100% |
5651
91.6 IPS |
|
Pose Estimation (SP)
|
100% |
9320
10.9 IPS |
|
Pose Estimation (HP)
|
100% |
67960
79.3 IPS |
|
Pose Estimation (Q)
|
94% |
63362
74.3 IPS |
|
Object Detection (SP)
|
100% |
1381
109.6 IPS |
|
Object Detection (HP)
|
99% |
6635
527.8 IPS |
|
Object Detection (Q)
|
91% |
6717
536.7 IPS |
|
Face Detection (SP)
|
100% |
2893
34.4 IPS |
|
Face Detection (HP)
|
100% |
10882
129.3 IPS |
|
Face Detection (Q)
|
100% |
12061
143.3 IPS |
|
Depth Estimation (SP)
|
100% |
5031
38.8 IPS |
|
Depth Estimation (HP)
|
99% |
43729
336.9 IPS |
|
Depth Estimation (Q)
|
97% |
46616
360.4 IPS |
|
Style Transfer (SP)
|
100% |
19481
25.0 IPS |
|
Style Transfer (HP)
|
100% |
113850
146.4 IPS |
|
Style Transfer (Q)
|
100% |
118976
152.9 IPS |
|
Image Super-Resolution (SP)
|
100% |
3865
142.7 IPS |
|
Image Super-Resolution (HP)
|
100% |
24444
902.6 IPS |
|
Image Super-Resolution (Q)
|
98% |
25835
957.2 IPS |
|
Text Classification (SP)
|
100% |
1888
2.52 KIPS |
|
Text Classification (HP)
|
100% |
3419
4.56 KIPS |
|
Text Classification (Q)
|
93% |
3105
4.17 KIPS |
|
Machine Translation (SP)
|
100% |
3000
51.7 IPS |
|
Machine Translation (HP)
|
100% |
1831
31.5 IPS |
|
Machine Translation (Q)
|
98% |
1813
31.3 IPS |