User | pixelbrett |
Upload Date | August 26 2024 05:50 AM |
Views | 3 |
System Information | |
---|---|
Operating System | Ubuntu 22.04.4 LTS |
Model | ASUS System Product Name |
Motherboard | ASUSTeK COMPUTER INC. ROG ZENITH EXTREME |
CPU Information | |
---|---|
Name | AMD Ryzen Threadripper 1950X |
Topology | 1 Processor, 16 Cores, 32 Threads |
Identifier | AuthenticAMD Family 23 Model 1 Stepping 1 |
Base Frequency | 3.75 GHz |
Cluster 1 | 0 Cores |
L1 Instruction Cache | 64.0 KB x 16 |
L1 Data Cache | 32.0 KB x 16 |
L2 Cache | 512 KB x 16 |
L3 Cache | 8.00 MB x 4 |
Memory Information | |
---|---|
Size | 94.13 GB |
Inference Information | |
---|---|
Framework | TensorFlow Lite |
Backend | CPU |
Device | Default |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (F32)
|
100% |
522
97.7 IPS |
|
Image Classification (F16)
|
100% |
513
96.1 IPS |
|
Image Classification (I8)
|
99% |
445
83.2 IPS |
|
Image Segmentation (F32)
|
100% |
955
16.0 IPS |
|
Image Segmentation (F16)
|
100% |
973
16.2 IPS |
|
Image Segmentation (I8)
|
98% |
635
10.6 IPS |
|
Pose Estimation (F32)
|
100% |
1376
1.67 IPS |
|
Pose Estimation (F16)
|
100% |
1371
1.66 IPS |
|
Pose Estimation (I8)
|
100% |
2099
2.54 IPS |
|
Object Detection (F32)
|
100% |
640
47.8 IPS |
|
Object Detection (F16)
|
100% |
628
46.9 IPS |
|
Object Detection (I8)
|
65% |
565
42.2 IPS |
|
Face Detection (F32)
|
100% |
888
10.6 IPS |
|
Face Detection (F16)
|
100% |
888
10.6 IPS |
|
Face Detection (I8)
|
87% |
850
10.1 IPS |
|
Depth Estimation (F32)
|
100% |
942
7.31 IPS |
|
Depth Estimation (F16)
|
100% |
937
7.27 IPS |
|
Depth Estimation (I8)
|
95% |
1151
8.93 IPS |
|
Style Transfer (F32)
|
100% |
1804
2.37 IPS |
|
Style Transfer (F16)
|
100% |
1746
2.30 IPS |
|
Style Transfer (I8)
|
98% |
3353
4.41 IPS |
|
Image Super-Resolution (F32)
|
100% |
593
21.2 IPS |
|
Image Super-Resolution (F16)
|
100% |
500
17.9 IPS |
|
Image Super-Resolution (I8)
|
98% |
639
22.8 IPS |
|
Text Classification (F32)
|
100% |
499
717.0 IPS |
|
Text Classification (F16)
|
100% |
496
713.5 IPS |
|
Text Classification (I8)
|
92% |
294
422.8 IPS |
|
Machine Translation (F32)
|
100% |
814
15.0 IPS |
|
Machine Translation (F16)
|
100% |
866
15.9 IPS |
|
Machine Translation (I8)
|
62% |
422
7.77 IPS |