User | JaniPhilippi |
Upload Date | December 22 2024 06:38 AM |
Views | 2 |
AI Information | |
---|---|
Framework | Core ML |
Backend | GPU |
Device | Apple M2 |
System Information | |
---|---|
Operating System | macOS 14.6.1 (Build 23G93) |
Model | Mac mini (2023) |
Model ID | Mac14,3 |
Motherboard | Mac14,3 |
CPU Information | |
---|---|
Name | Apple M2 |
Topology | 1 Processor, 8 Cores |
Identifier | Apple M2 |
Base Frequency | 3.47 GHz |
Cluster 1 | 4 Cores |
Cluster 2 | 4 Cores |
Memory Information | |
---|---|
Size | 8.00 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
3531
656.6 IPS |
|
Image Classification (HP)
|
100% |
3548
659.8 IPS |
|
Image Classification (Q)
|
97% |
2655
495.5 IPS |
|
Image Segmentation (SP)
|
100% |
3935
63.8 IPS |
|
Image Segmentation (HP)
|
100% |
4908
79.6 IPS |
|
Image Segmentation (Q)
|
99% |
4835
78.4 IPS |
|
Pose Estimation (SP)
|
100% |
24511
28.6 IPS |
|
Pose Estimation (HP)
|
100% |
26129
30.5 IPS |
|
Pose Estimation (Q)
|
97% |
23747
27.8 IPS |
|
Object Detection (SP)
|
100% |
3543
281.0 IPS |
|
Object Detection (HP)
|
100% |
3599
285.5 IPS |
|
Object Detection (Q)
|
92% |
2842
226.9 IPS |
|
Face Detection (SP)
|
100% |
9814
116.6 IPS |
|
Face Detection (HP)
|
100% |
11382
135.2 IPS |
|
Face Detection (Q)
|
100% |
7732
91.9 IPS |
|
Depth Estimation (SP)
|
100% |
16630
128.1 IPS |
|
Depth Estimation (HP)
|
99% |
17755
136.8 IPS |
|
Depth Estimation (Q)
|
1% |
0
108.4 IPS |
|
Style Transfer (SP)
|
100% |
42247
54.3 IPS |
|
Style Transfer (HP)
|
100% |
48335
62.1 IPS |
|
Style Transfer (Q)
|
96% |
45027
58.1 IPS |
|
Image Super-Resolution (SP)
|
100% |
9526
351.8 IPS |
|
Image Super-Resolution (HP)
|
100% |
10639
392.9 IPS |
|
Image Super-Resolution (Q)
|
99% |
7871
290.6 IPS |
|
Text Classification (SP)
|
100% |
1245
1.66 KIPS |
|
Text Classification (HP)
|
100% |
788
1.05 KIPS |
|
Text Classification (Q)
|
93% |
783
1.05 KIPS |
|
Machine Translation (SP)
|
100% |
1487
25.6 IPS |
|
Machine Translation (HP)
|
100% |
1533
26.4 IPS |
|
Machine Translation (Q)
|
98% |
1438
24.8 IPS |