User | bassiek |
Upload Date | September 03 2024 05:32 PM |
Views | 8 |
AI Information | |
---|---|
Framework | Core ML |
Backend | Neural Engine |
Device | Apple M1 Pro |
System Information | |
---|---|
Operating System | macOS 14.6.1 (Build 23G93) |
Model | MacBook Pro (14-inch, 2021) |
Model ID | MacBookPro18,3 |
Motherboard | MacBookPro18,3 |
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% |
948
176.3 IPS |
|
Image Classification (HP)
|
100% |
6977
1.30 KIPS |
|
Image Classification (Q)
|
99% |
7368
1.37 KIPS |
|
Image Segmentation (SP)
|
100% |
664
10.8 IPS |
|
Image Segmentation (HP)
|
100% |
3877
62.9 IPS |
|
Image Segmentation (Q)
|
100% |
3834
62.2 IPS |
|
Pose Estimation (SP)
|
100% |
10169
11.9 IPS |
|
Pose Estimation (HP)
|
100% |
68486
79.9 IPS |
|
Pose Estimation (Q)
|
94% |
65972
77.4 IPS |
|
Object Detection (SP)
|
100% |
1029
81.6 IPS |
|
Object Detection (HP)
|
99% |
7585
603.3 IPS |
|
Object Detection (Q)
|
93% |
7337
585.4 IPS |
|
Face Detection (SP)
|
100% |
1771
21.0 IPS |
|
Face Detection (HP)
|
100% |
10658
126.6 IPS |
|
Face Detection (Q)
|
100% |
12298
146.1 IPS |
|
Depth Estimation (SP)
|
100% |
3626
27.9 IPS |
|
Depth Estimation (HP)
|
99% |
46362
357.2 IPS |
|
Depth Estimation (Q)
|
97% |
49659
384.0 IPS |
|
Style Transfer (SP)
|
100% |
12031
15.5 IPS |
|
Style Transfer (HP)
|
100% |
118792
152.7 IPS |
|
Style Transfer (Q)
|
100% |
123214
158.4 IPS |
|
Image Super-Resolution (SP)
|
100% |
2528
93.3 IPS |
|
Image Super-Resolution (HP)
|
100% |
18960
700.1 IPS |
|
Image Super-Resolution (Q)
|
98% |
23163
858.2 IPS |
|
Text Classification (SP)
|
100% |
809
1.08 KIPS |
|
Text Classification (HP)
|
100% |
3416
4.56 KIPS |
|
Text Classification (Q)
|
93% |
3387
4.55 KIPS |
|
Machine Translation (SP)
|
100% |
1337
23.0 IPS |
|
Machine Translation (HP)
|
100% |
2185
37.6 IPS |
|
Machine Translation (Q)
|
98% |
2176
37.6 IPS |