Difference between revisions of "Deep Dream with Darknet"
Jump to navigation
Jump to search
| Line 14: | Line 14: | ||
*Go to the directory and type: | *Go to the directory and type: | ||
| − | |||
./darknet nightmare cfg/vgg-conv.cfg vgg-conv.weights data/eagle.jpg 13 | ./darknet nightmare cfg/vgg-conv.cfg vgg-conv.weights data/eagle.jpg 13 | ||
| − | |||
=== Generate a sequence of images with DeepDream === | === Generate a sequence of images with DeepDream === | ||
Revision as of 21:05, 9 January 2019
Installation
- Fist, we install OpenCV:
- OpenCV Installation
- Then, we need to install our modified version of Darknet:
- Darknet Installation
Generating an Image
- Using Deep Dream with Darknet (GPU + OpenCV). Tested on Ubuntu 16.04
wget http://pjreddie.com/media/files/vgg-conv.weights
Apply DeepDream to an image
- Go to the directory and type:
./darknet nightmare cfg/vgg-conv.cfg vgg-conv.weights data/eagle.jpg 13
Generate a sequence of images with DeepDream
- Go to the directory and run the detector for videos:
cd darknet ./darknet nightmare cfg/vgg-conv.cfg vgg-conv.weights data/eagle.jpg 13 -rounds 30 -zoom 0.8