User | fo0barorg |
Upload Date | August 16 2024 06:39 AM |
Views | 1 |
AI Information | |
---|---|
Framework | Core ML |
Backend | GPU |
Device | Apple M1 |
System Information | |
---|---|
Operating System | macOS 15.0 (Build 24A5320a) |
Model | Mac mini (Late 2020) |
Model ID | Macmini9,1 |
Motherboard | Macmini9,1 |
CPU Information | |
---|---|
Name | Apple M1 |
Topology | 1 Processor, 8 Cores |
Identifier | Apple M1 |
Base Frequency | 3.07 GHz |
Cluster 1 | 4 Cores |
Cluster 2 | 4 Cores |
Memory Information | |
---|---|
Size | 16.00 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
1829
340.1 IPS |
|
Image Classification (HP)
|
100% |
2432
452.3 IPS |
|
Image Classification (Q)
|
99% |
2016
376.0 IPS |
|
Image Segmentation (SP)
|
100% |
2590
42.0 IPS |
|
Image Segmentation (HP)
|
100% |
3498
56.7 IPS |
|
Image Segmentation (Q)
|
100% |
3409
55.3 IPS |
|
Pose Estimation (SP)
|
100% |
16898
19.7 IPS |
|
Pose Estimation (HP)
|
100% |
18255
21.3 IPS |
|
Pose Estimation (Q)
|
97% |
16471
19.3 IPS |
|
Object Detection (SP)
|
100% |
2604
206.6 IPS |
|
Object Detection (HP)
|
100% |
2678
212.4 IPS |
|
Object Detection (Q)
|
91% |
2149
171.7 IPS |
|
Face Detection (SP)
|
100% |
6544
77.8 IPS |
|
Face Detection (HP)
|
100% |
8064
95.8 IPS |
|
Face Detection (Q)
|
100% |
5610
66.7 IPS |
|
Depth Estimation (SP)
|
100% |
11624
89.6 IPS |
|
Depth Estimation (HP)
|
99% |
13290
102.4 IPS |
|
Depth Estimation (Q)
|
97% |
1983
15.3 IPS |
|
Style Transfer (SP)
|
100% |
28597
36.8 IPS |
|
Style Transfer (HP)
|
100% |
34731
44.6 IPS |
|
Style Transfer (Q)
|
100% |
35060
45.1 IPS |
|
Image Super-Resolution (SP)
|
100% |
6420
237.1 IPS |
|
Image Super-Resolution (HP)
|
100% |
7184
265.3 IPS |
|
Image Super-Resolution (Q)
|
98% |
4965
183.9 IPS |
|
Text Classification (SP)
|
100% |
2217
2.96 KIPS |
|
Text Classification (HP)
|
100% |
3814
5.09 KIPS |
|
Text Classification (Q)
|
93% |
3704
4.97 KIPS |
|
Machine Translation (SP)
|
100% |
720
12.4 IPS |
|
Machine Translation (HP)
|
100% |
743
12.8 IPS |
|
Machine Translation (Q)
|
98% |
786
13.6 IPS |