User | amoudruz |
Upload Date | November 12 2024 04:08 PM |
Views | 6 |
AI Information | |
---|---|
Framework | Core ML |
Backend | Neural Engine |
Device | Apple M4 Pro |
System Information | |
---|---|
Operating System | macOS 15.1 (Build 24B2083) |
Model | Mac16,11 |
Model ID | Mac16,11 |
Motherboard | Mac16,11 |
CPU Information | |
---|---|
Name | Apple M4 Pro |
Topology | 1 Processor, 14 Cores |
Identifier | Apple M4 Pro |
Base Frequency | 4.50 GHz |
Cluster 1 | 10 Cores |
Cluster 2 | 4 Cores |
Memory Information | |
---|---|
Size | 64.00 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
2130
396.1 IPS |
|
Image Classification (HP)
|
100% |
18463
3.43 KIPS |
|
Image Classification (Q)
|
97% |
23593
4.40 KIPS |
|
Image Segmentation (SP)
|
100% |
2523
40.9 IPS |
|
Image Segmentation (HP)
|
100% |
23743
384.9 IPS |
|
Image Segmentation (Q)
|
99% |
33229
538.7 IPS |
|
Pose Estimation (SP)
|
100% |
18787
21.9 IPS |
|
Pose Estimation (HP)
|
100% |
123927
144.6 IPS |
|
Pose Estimation (Q)
|
95% |
233842
274.1 IPS |
|
Object Detection (SP)
|
100% |
2483
197.0 IPS |
|
Object Detection (HP)
|
100% |
21335
1.69 KIPS |
|
Object Detection (Q)
|
91% |
25913
2.07 KIPS |
|
Face Detection (SP)
|
100% |
4478
53.2 IPS |
|
Face Detection (HP)
|
100% |
45611
542.0 IPS |
|
Face Detection (Q)
|
100% |
58784
698.5 IPS |
|
Depth Estimation (SP)
|
100% |
8776
67.6 IPS |
|
Depth Estimation (HP)
|
99% |
110167
848.8 IPS |
|
Depth Estimation (Q)
|
85% |
183893
1.44 KIPS |
|
Style Transfer (SP)
|
100% |
35503
45.6 IPS |
|
Style Transfer (HP)
|
100% |
239781
308.2 IPS |
|
Style Transfer (Q)
|
96% |
307508
396.8 IPS |
|
Image Super-Resolution (SP)
|
100% |
7083
261.5 IPS |
|
Image Super-Resolution (HP)
|
100% |
48010
1.77 KIPS |
|
Image Super-Resolution (Q)
|
99% |
82386
3.04 KIPS |
|
Text Classification (SP)
|
100% |
2965
3.96 KIPS |
|
Text Classification (HP)
|
100% |
5718
7.63 KIPS |
|
Text Classification (Q)
|
93% |
5891
7.91 KIPS |
|
Machine Translation (SP)
|
100% |
5630
97.0 IPS |
|
Machine Translation (HP)
|
100% |
17237
296.9 IPS |
|
Machine Translation (Q)
|
98% |
17215
297.5 IPS |