A tool to visualize convolutional, ReLU, and pooling layer activations on an input image. This is a PyTorch implementation of htoyryla's convis.

• PyTorch

After installing the dependencies, you'll need to run the following script to download the default VGG and NIN models:

python models/download_models.py

You can also place convis.py or convis_heatmap.py in your neural-style-pt directory, in order to more easily work with models and input images.

convis.py will create an output image for every channel in the specified layer:

python convis.py -input_image examples/inputs/tubingen.jpg -model_file models/vgg19-d01eb7cb.pth -layer conv2_2 -output_dir output

convis_heatmap.py will create a single output image composed of every channel in the specified layer:

python convis_heatmap.py -input_image examples/inputs/tubingen.jpg -model_file models/vgg19-d01eb7cb.pth -layer relu4_2

• -input_image: Path to the input image.
• -image_size: Maximum side length (in pixels) of the generated image. Default is 512.
• -layer: The target layer. Default is relu4_2
• -pooling: The type of pooling layers to use; one of max or avg. Default is max.
• -model_file: Path to the .pth file for the VGG or NIN model.
• -output_image: Name of the output image. Default is out.png.
• -output_dir: Name of the output image directory. Default is output.

The output files will be named like output/tubingen-conv3_2-69.png