综合技术

FeatVis — A GUI for visualisation of the Feature Maps Learned by a CNN

微信扫一扫,分享到朋友圈

FeatVis — A GUI for visualisation of the Feature Maps Learned by a CNN
0

When training convolutional neural network (CNN), we mostly rely on training and validation loss to assess the performance of the trained model.

Often the need to visualise the feature maps learned by the trained CNN is overlooked. Probably because it is easier to retrain a network with new parameters rather than looking at each individual feature map.

To make the visualisation of the feature maps an easier task I am going to show the usage of a GUI toolbox. Once setup, it is extremely easy to visualise the features maps using this toolbox. The tool is available at Github to visualise models trained in Keras.

Once setup, to start the GUI interface simply run:

python startGUI.py

This will pop up a GUI interface:

Simple GUI interface for visualisation of the features for a given image

The first step is to select the Keras trained model file (*h5/*hdf5) using browse option in GUI

Note: You can save pertained models from keras application to hdf5/h5 format as:

from keras.applications.vgg16 import VGG16
model = VGG16(include_top=False, weights=’imagenet’)
model.save(‘model-vgg16.hdf5’)

Once model is selected click ‘Parse Model’ button. This will save the model flowchart as PNG file in the current working directory and you will be able to see all the layer names in the ‘choose a Layer’ drop down menu. Select a layer for which you want to visualise features maps, then select an input image using the ‘input Image’ button.

Click on ‘Compute Feature’ button, which will compute all the feature maps for the selected layer in the background. Wait for few seconds to finish computation, the wait time will depend on the complexity of the model.

Once finished computation of the feature map you can visualise feature map using the ‘Display’ button.

Many options are available to visualise feature maps such as numerous colormaps from the ‘Display colormap’ menu and the number of images to display per panel can be selected from the drop down menus as well.

Some of the feature maps visualised using the GUI for VGG16 are shown below, it is very easy to to visualise the feature maps using this GUI just select the layer name from the drop down menu.

Input image to the VGG16

First 12 features of the selected layer

Next 12 features

The currently supported input image formats are JPEG, PNG, TIFF, and BMP. Options are available to load any arbitrary image format and additional preprocessing steps can be added. Visit authors Github for more info.

阅读原文...


mc.ai

苹果:iOS13取消3DTouch是BUG 下一测试版将修复

上一篇

Do GANs Dream of Fake Images?

下一篇

您也可能喜欢

评论已经被关闭。

插入图片
FeatVis — A GUI for visualisation of the Feature Maps Learned by a CNN

长按储存图像,分享给朋友