User | edoardo_scarpel |
Upload Date | August 18 2024 02:31 PM |
Views | 6 |
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% |
3740
695.5 IPS |
|
Image Classification (Q)
|
99% |
3277
611.2 IPS |
|
Image Segmentation (SP)
|
100% |
5998
97.2 IPS |
|
Image Segmentation (HP)
|
100% |
6143
99.6 IPS |
|
Image Segmentation (Q)
|
100% |
5973
96.8 IPS |
|
Pose Estimation (SP)
|
100% |
32987
38.5 IPS |
|
Pose Estimation (HP)
|
100% |
34358
40.1 IPS |
|
Pose Estimation (Q)
|
96% |
30518
35.8 IPS |
|
Object Detection (SP)
|
100% |
3720
295.1 IPS |
|
Object Detection (HP)
|
100% |
3908
309.9 IPS |
|
Object Detection (Q)
|
92% |
3016
240.7 IPS |
|
Face Detection (SP)
|
100% |
12592
149.6 IPS |
|
Face Detection (HP)
|
100% |
13061
155.2 IPS |
|
Face Detection (Q)
|
100% |
8763
104.1 IPS |
|
Depth Estimation (SP)
|
100% |
19729
152.0 IPS |
|
Depth Estimation (HP)
|
99% |
20009
154.2 IPS |
|
Depth Estimation (Q)
|
97% |
19955
154.3 IPS |
|
Style Transfer (SP)
|
100% |
53747
69.1 IPS |
|
Style Transfer (HP)
|
100% |
63183
81.2 IPS |
|
Style Transfer (Q)
|
100% |
63702
81.9 IPS |
|
Image Super-Resolution (SP)
|
100% |
11015
406.7 IPS |
|
Image Super-Resolution (HP)
|
100% |
11766
434.5 IPS |
|
Image Super-Resolution (Q)
|
98% |
8590
318.2 IPS |
|
Text Classification (SP)
|
100% |
723
965.6 IPS |
|
Text Classification (HP)
|
100% |
385
513.5 IPS |
|
Text Classification (Q)
|
93% |
447
599.5 IPS |
|
Machine Translation (SP)
|
100% |
717
12.3 IPS |
|
Machine Translation (HP)
|
100% |
732
12.6 IPS |
|
Machine Translation (Q)
|
98% |
999
17.3 IPS |