User | amoudruz |
Upload Date | December 03 2024 12:51 PM |
Views | 5 |
AI Information | |
---|---|
Framework | Core ML |
Backend | Neural Engine |
Device | Apple M4 Pro |
System Information | |
---|---|
Operating System | macOS 15.1.1 (Build 24B2091) |
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 | 3.87 GHz |
Cluster 1 | 10 Cores |
Cluster 2 | 4 Cores |
Memory Information | |
---|---|
Size | 64.00 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
2098
390.2 IPS |
|
Image Classification (HP)
|
100% |
18946
3.52 KIPS |
|
Image Classification (Q)
|
97% |
24345
4.54 KIPS |
|
Image Segmentation (SP)
|
100% |
2361
38.3 IPS |
|
Image Segmentation (HP)
|
100% |
23341
378.4 IPS |
|
Image Segmentation (Q)
|
99% |
32670
529.6 IPS |
|
Pose Estimation (SP)
|
100% |
17815
20.8 IPS |
|
Pose Estimation (HP)
|
100% |
121559
141.8 IPS |
|
Pose Estimation (Q)
|
95% |
227323
266.4 IPS |
|
Object Detection (SP)
|
100% |
2400
190.4 IPS |
|
Object Detection (HP)
|
100% |
20850
1.65 KIPS |
|
Object Detection (Q)
|
91% |
26206
2.09 KIPS |
|
Face Detection (SP)
|
100% |
4180
49.7 IPS |
|
Face Detection (HP)
|
100% |
41769
496.3 IPS |
|
Face Detection (Q)
|
100% |
62374
741.1 IPS |
|
Depth Estimation (SP)
|
100% |
8179
63.0 IPS |
|
Depth Estimation (HP)
|
99% |
111227
856.9 IPS |
|
Depth Estimation (Q)
|
85% |
179786
1.41 KIPS |
|
Style Transfer (SP)
|
100% |
32587
41.9 IPS |
|
Style Transfer (HP)
|
100% |
235608
302.9 IPS |
|
Style Transfer (Q)
|
96% |
303564
391.7 IPS |
|
Image Super-Resolution (SP)
|
100% |
6797
251.0 IPS |
|
Image Super-Resolution (HP)
|
100% |
48543
1.79 KIPS |
|
Image Super-Resolution (Q)
|
99% |
83529
3.08 KIPS |
|
Text Classification (SP)
|
100% |
2818
3.76 KIPS |
|
Text Classification (HP)
|
100% |
6047
8.07 KIPS |
|
Text Classification (Q)
|
93% |
5921
7.95 KIPS |
|
Machine Translation (SP)
|
100% |
5070
87.3 IPS |
|
Machine Translation (HP)
|
100% |
17148
295.4 IPS |
|
Machine Translation (Q)
|
98% |
17346
299.8 IPS |