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

Update README.md

Browse Source
This commit is contained in:
Francesco Gatti
2020-04-29 13:07:26 +02:00
committed by GitHub
parent 986ec5d00c
commit 3e2d0630b7
1 changed files with 2 additions and 2 deletions
Download Patch File Download Diff File Expand all files Collapse all files
README.md
+2 -2
View File
@@ -69,10 +69,10 @@ Weights are essential for any network to run inference. For each test a folder o
Therefore, once the weights have been exported, the folders layers and debug should be placed in the corresponding test. Therefore, once the weights have been exported, the folders layers and debug should be placed in the corresponding test.
### 1)Export weights from darknet ### 1)Export weights from darknet
To export weights for NNs that are defined in darknet framework, use [this](https://github.com/ceccocats/darknet) fork of darknet and follow these steps to obtain a correct debug and layers folder, ready for tkDNN. To export weights for NNs that are defined in darknet framework, use [this](https://git.hipert.unimore.it/fgatti/darknet.git) fork of darknet and follow these steps to obtain a correct debug and layers folder, ready for tkDNN.
``` ```
git clone https://github.com/ceccocats/darknet git clone https://git.hipert.unimore.it/fgatti/darknet.git
cd darknet cd darknet
make make
mkdir layers debug mkdir layers debug