User | BengtW |
Upload Date | September 17 2024 10:48 AM |
Views | 3 |
AI Information | |
---|---|
Framework | Core ML |
Backend | GPU |
Device | Apple M2 |
System Information | |
---|---|
Operating System | macOS 15.0 (Build 24A335) |
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 | 3.48 GHz |
Cluster 1 | 4 Cores |
Cluster 2 | 4 Cores |
Memory Information | |
---|---|
Size | 8.00 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
3737
694.9 IPS |
|
Image Classification (HP)
|
100% |
3914
727.9 IPS |
|
Image Classification (Q)
|
97% |
2846
531.1 IPS |
|
Image Segmentation (SP)
|
100% |
3971
64.4 IPS |
|
Image Segmentation (HP)
|
100% |
5094
82.6 IPS |
|
Image Segmentation (Q)
|
99% |
5013
81.3 IPS |
|
Pose Estimation (SP)
|
100% |
24645
28.8 IPS |
|
Pose Estimation (HP)
|
100% |
26312
30.7 IPS |
|
Pose Estimation (Q)
|
95% |
24149
28.3 IPS |
|
Object Detection (SP)
|
100% |
3604
285.9 IPS |
|
Object Detection (HP)
|
100% |
3730
295.9 IPS |
|
Object Detection (Q)
|
91% |
2858
228.4 IPS |
|
Face Detection (SP)
|
100% |
10308
122.5 IPS |
|
Face Detection (HP)
|
100% |
11929
141.7 IPS |
|
Face Detection (Q)
|
100% |
8222
97.7 IPS |
|
Depth Estimation (SP)
|
100% |
16705
128.7 IPS |
|
Depth Estimation (HP)
|
99% |
17899
137.9 IPS |
|
Depth Estimation (Q)
|
85% |
13916
108.8 IPS |
|
Style Transfer (SP)
|
100% |
42429
54.5 IPS |
|
Style Transfer (HP)
|
100% |
48493
62.3 IPS |
|
Style Transfer (Q)
|
96% |
45272
58.4 IPS |
|
Image Super-Resolution (SP)
|
100% |
9856
363.9 IPS |
|
Image Super-Resolution (HP)
|
100% |
10194
376.4 IPS |
|
Image Super-Resolution (Q)
|
99% |
7816
288.6 IPS |
|
Text Classification (SP)
|
100% |
2214
2.96 KIPS |
|
Text Classification (HP)
|
100% |
3782
5.05 KIPS |
|
Text Classification (Q)
|
93% |
3722
5.00 KIPS |
|
Machine Translation (SP)
|
100% |
975
16.8 IPS |
|
Machine Translation (HP)
|
100% |
919
15.8 IPS |
|
Machine Translation (Q)
|
98% |
1047
18.1 IPS |