User | tanqichou |
Upload Date | March 05 2025 10:21 AM |
Views | 6 |
AI Information | |
---|---|
Framework | ONNX |
Backend | DirectML |
Device | NVIDIA GeForce GTX 1050 Ti |
System Information | |
---|---|
Operating System | Microsoft Windows Server 2022 Datacenter (64-bit) |
Model | Timi TM1705 |
Motherboard | Timi Portable PC |
CPU Information | |
---|---|
Name | Intel Core i7-7920HQ |
Topology | 1 Processor, 4 Cores, 8 Threads |
Identifier | GenuineIntel Family 6 Model 158 Stepping 9 |
Base Frequency | 3.10 GHz |
Cluster 1 | 4 Cores |
Memory Information | |
---|---|
Size | 32.00 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
726
135.0 IPS |
|
Image Classification (HP)
|
100% |
1383
257.1 IPS |
|
Image Classification (Q)
|
99% |
684
127.6 IPS |
|
Image Segmentation (SP)
|
100% |
2214
35.9 IPS |
|
Image Segmentation (HP)
|
100% |
1938
31.4 IPS |
|
Image Segmentation (Q)
|
98% |
1832
29.8 IPS |
|
Pose Estimation (SP)
|
100% |
20808
24.3 IPS |
|
Pose Estimation (HP)
|
100% |
11457
13.4 IPS |
|
Pose Estimation (Q)
|
96% |
17149
20.1 IPS |
|
Object Detection (SP)
|
100% |
1046
83.0 IPS |
|
Object Detection (HP)
|
100% |
1743
138.3 IPS |
|
Object Detection (Q)
|
83% |
962
77.7 IPS |
|
Face Detection (SP)
|
100% |
2141
25.4 IPS |
|
Face Detection (HP)
|
100% |
3221
38.3 IPS |
|
Face Detection (Q)
|
97% |
1913
22.8 IPS |
|
Depth Estimation (SP)
|
100% |
7085
54.6 IPS |
|
Depth Estimation (HP)
|
99% |
6557
50.7 IPS |
|
Depth Estimation (Q)
|
78% |
5735
45.8 IPS |
|
Style Transfer (SP)
|
100% |
34102
43.8 IPS |
|
Style Transfer (HP)
|
100% |
20909
26.9 IPS |
|
Style Transfer (Q)
|
98% |
27122
35.0 IPS |
|
Image Super-Resolution (SP)
|
100% |
6633
244.9 IPS |
|
Image Super-Resolution (HP)
|
100% |
4981
183.9 IPS |
|
Image Super-Resolution (Q)
|
99% |
4565
169.0 IPS |
|
Text Classification (SP)
|
100% |
1218
1.63 KIPS |
|
Text Classification (HP)
|
100% |
1073
1.43 KIPS |
|
Text Classification (Q)
|
97% |
699
935.9 IPS |
|
Machine Translation (SP)
|
100% |
1771
30.5 IPS |
|
Machine Translation (HP)
|
96% |
1729
29.9 IPS |
|
Machine Translation (Q)
|
70% |
843
15.8 IPS |