Upload Date | October 30 2024 05:33 PM |
Views | 17 |
AI Information | |
---|---|
Framework | Core ML |
Backend | CPU |
Device | Intel Xeon E5-1650 v2 |
System Information | |
---|---|
Operating System | macOS 15.1 (Build 24B83) |
Model | Mac Pro (Late 2013) |
Model ID | MacPro6,1 |
Motherboard | Apple Inc. Mac-F60DEB81FF30ACF6 MacPro6,1 |
CPU Information | |
---|---|
Name | Intel Xeon E5-1650 v2 |
Topology | 1 Processor, 6 Cores, 12 Threads |
Identifier | GenuineIntel Family 6 Model 62 Stepping 4 |
Base Frequency | 3.50 GHz |
Cluster 1 | 6 Cores |
Memory Information | |
---|---|
Size | 16.00 GB |
Transfer Rate | 1866 MT/s |
Type | DDR3 |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
261
48.5 IPS |
|
Image Classification (HP)
|
100% |
195
36.2 IPS |
|
Image Classification (Q)
|
96% |
52
9.63 IPS |
|
Image Segmentation (SP)
|
100% |
309
5.01 IPS |
|
Image Segmentation (HP)
|
100% |
148
2.39 IPS |
|
Image Segmentation (Q)
|
99% |
73
1.18 IPS |
|
Pose Estimation (SP)
|
100% |
1402
1.64 IPS |
|
Pose Estimation (HP)
|
100% |
338
0.39 IPS |
|
Pose Estimation (Q)
|
96% |
269
0.32 IPS |
|
Object Detection (SP)
|
100% |
249
19.7 IPS |
|
Object Detection (HP)
|
100% |
201
15.9 IPS |
|
Object Detection (Q)
|
92% |
60
4.80 IPS |
|
Face Detection (SP)
|
100% |
628
7.46 IPS |
|
Face Detection (HP)
|
100% |
409
4.86 IPS |
|
Face Detection (Q)
|
100% |
81
0.96 IPS |
|
Depth Estimation (SP)
|
100% |
712
5.49 IPS |
|
Depth Estimation (HP)
|
99% |
338
2.60 IPS |
|
Depth Estimation (Q)
|
85% |
171
1.34 IPS |
|
Style Transfer (SP)
|
100% |
1937
2.49 IPS |
|
Style Transfer (HP)
|
100% |
934
1.20 IPS |
|
Style Transfer (Q)
|
96% |
623
0.80 IPS |
|
Image Super-Resolution (SP)
|
100% |
697
25.7 IPS |
|
Image Super-Resolution (HP)
|
100% |
219
8.09 IPS |
|
Image Super-Resolution (Q)
|
99% |
99
3.66 IPS |
|
Text Classification (SP)
|
100% |
251
334.8 IPS |
|
Text Classification (HP)
|
29% |
9
154.5 IPS |
|
Text Classification (Q)
|
29% |
9
153.8 IPS |
|
Machine Translation (SP)
|
100% |
246
4.24 IPS |
|
Machine Translation (HP)
|
0% |
0
0.47 IPS |
|
Machine Translation (Q)
|
0% |
0
0.49 IPS |