User | Jaleelajmal |
Upload Date | September 22 2024 11:22 AM |
Views | 2 |
AI Information | |
---|---|
Framework | Core ML |
Backend | GPU |
Device | Apple M2 |
System Information | |
---|---|
Operating System | macOS 15.1 (Build 24B5046f) |
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 | 3.46 GHz |
Cluster 1 | 4 Cores |
Cluster 2 | 4 Cores |
Memory Information | |
---|---|
Size | 16.00 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
3574
664.6 IPS |
|
Image Classification (HP)
|
100% |
3661
680.8 IPS |
|
Image Classification (Q)
|
97% |
2966
553.5 IPS |
|
Image Segmentation (SP)
|
100% |
4014
65.1 IPS |
|
Image Segmentation (HP)
|
100% |
5000
81.0 IPS |
|
Image Segmentation (Q)
|
99% |
5088
82.5 IPS |
|
Pose Estimation (SP)
|
100% |
24713
28.8 IPS |
|
Pose Estimation (HP)
|
100% |
26298
30.7 IPS |
|
Pose Estimation (Q)
|
95% |
24445
28.7 IPS |
|
Object Detection (SP)
|
100% |
3442
273.0 IPS |
|
Object Detection (HP)
|
100% |
3517
279.0 IPS |
|
Object Detection (Q)
|
91% |
3035
242.5 IPS |
|
Face Detection (SP)
|
100% |
10360
123.1 IPS |
|
Face Detection (HP)
|
100% |
11962
142.1 IPS |
|
Face Detection (Q)
|
100% |
8387
99.7 IPS |
|
Depth Estimation (SP)
|
100% |
16597
127.9 IPS |
|
Depth Estimation (HP)
|
99% |
17804
137.2 IPS |
|
Depth Estimation (Q)
|
85% |
14614
114.2 IPS |
|
Style Transfer (SP)
|
100% |
42559
54.7 IPS |
|
Style Transfer (HP)
|
100% |
48410
62.2 IPS |
|
Style Transfer (Q)
|
96% |
45329
58.5 IPS |
|
Image Super-Resolution (SP)
|
100% |
10090
372.6 IPS |
|
Image Super-Resolution (HP)
|
100% |
10153
374.9 IPS |
|
Image Super-Resolution (Q)
|
99% |
7942
293.3 IPS |
|
Text Classification (SP)
|
100% |
2171
2.90 KIPS |
|
Text Classification (HP)
|
100% |
3622
4.83 KIPS |
|
Text Classification (Q)
|
93% |
3614
4.85 KIPS |
|
Machine Translation (SP)
|
100% |
942
16.2 IPS |
|
Machine Translation (HP)
|
100% |
924
15.9 IPS |
|
Machine Translation (Q)
|
98% |
961
16.6 IPS |