mmr/tkDNN
Archived
1
0
Fork 0
Code Issues 46 Pull Requests 12 Releases 4 Activity

Update README.md for INT8 inference

Browse Source 
Signed-off-by: Davide Sapienza <sapienza.dav@gmail.com>
This commit is contained in:
Davide Sapienza
2020-04-06 20:27:59 +02:00
parent 26dcb7b8c9
commit ae876e22ee
1 changed files with 4 additions and 2 deletions
Download Patch File Download Diff File Expand all files Collapse all files
README.md
+4 -2
View File
@@ -151,9 +151,11 @@ rm yolo3_INT8.rt # be sure to delete(or move) old tensorRT files
./test_yolo3 # run the yolo test (is slow)
./demo yolo3_INT8.rt ../demo/yolo_test.mp4 y
```
N.b. Using INT8 inference will lead to some errors in the results (first or second decimal).
N.b. Using INT8 inference will lead to some errors in the results.
N.b. The network test script is very slow: it call the INT8 calibrator.
N.b. The test will be slower: this is due to the INT8 calibration, which may take some time to complete.
N.b. INT8 calibration requires TensorRT version greater than or equal to 6.0
## mAP demo