keras-vis
keras-vis copied to clipboard
raghakot
Neural network visualization toolkit for keras
Im using the Keras VGG16 net with a custom top layer (4 class softmax) ``` Loaded model with layers: [u'input_2', u'block1_conv1', u'block1_conv2', u'block1_pool', u'block2_conv1', u'block2_conv2', u'block2_pool', u'block3_conv1', u'block3_conv2', u'block3_conv3', u'block3_pool',...
Hello everyone, I'm running into this issue ``` def getGradCAM(X, model, resize_factor=0, layer_maps=-4): # Create functions ---------- # GRAD - backprop # create function model = guided(model) saliency = K.gradients(K.sum(model.outputs[-1]),...
- [x] Check that you are up-to-date with the master branch of keras-vis. You can update with: pip install git+git://github.com/raghakot/keras-vis.git --upgrade --no-deps - [x] If running on TensorFlow, check that...
I have a conceptual question based on the mnist example usage notebook: https://github.com/raghakot/keras-vis/blob/master/examples/mnist/attention.ipynb. I am trying to understand why to use pre-activation output for computing standard saliency maps? This is...
ImportError Traceback (most recent call last) in 1 # Reshaping the training data ----> 2 from scipy.misc import imresize 3 4 #X_train_new = np.array([imresize(X_train[i],(200,200,3)) for i in range(0,len(X_train))]).astype('float32') 5 X_train_new...
Hi, try to use the visualization for Faster R-CNN or Mask R-CNN, but this does not seem so easy, any ideas? Best regards Patrick
Tensorflow version: 2.4.0 Issue: I tried to reproduce this [example code](https://github.com/raghakot/keras-vis/blob/master/examples/mnist/attention.ipynb) but results in an error (it works in Tensorflow version 2.2.0): `"TypeError: Cannot convert a symbolic Keras input/output to...
- [ ] Check that you are up-to-date with the master branch of keras-vis. You can update with: pip install git+git://github.com/raghakot/keras-vis.git --upgrade --no-deps - [ ] If running on TensorFlow,...
While importing `visualize_activation` from `vis.visualization` I got this error `from vis.visualization import visualize_activation ` ``` ImportError Traceback (most recent call last) in () ----> 1 from vis.visualization import visualize_activation 2...
