Problem with custom CNN VGG16 (unsupported operand type(s) for *: 'int' and 'NoneType')

[ruvsv]

• [* ] 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, check that you are up-to-date with the latest version. The installation instructions can be found here.

Everything works on the pretrained vgg16 keras model. The one below does not work. What are the ways to calculate gradients for the multiple model?

tensorboard 1.15.0 tensorflow 1.15.2 tensorflow-estimator 1.15.1 Keras 2.3.1 Keras-Applications 1.0.8 Keras-Preprocessing 1.1.0 keras-vis 0.5.0 Keras 2.3.1 Keras-Applications 1.0.8 Keras-Preprocessing 1.1.0 keras-vis 0.5.0 scipy 1.1.0

`--------------------------------------------------------------------------- TypeError Traceback (most recent call last)

in 6 max_iter = 100, 7 verbose = True, ----> 8 filter_indices = None) 9 print(activation_max.shape) 10 plt.imshow(activation_max) ~/anaconda3/lib/python3.6/site-packages/vis/visualization/activation_maximization.py in visualize_activation(model, layer_idx, filter_indices, wrt_tensor, seed_input, input_range, backprop_modifier, grad_modifier, act_max_weight, lp_norm_weight, tv_weight, **optimizer_params) 110 111 return visualize_activation_with_losses(model.input, losses, wrt_tensor, --> 112 seed_input, input_range, **optimizer_params) ~/anaconda3/lib/python3.6/site-packages/vis/visualization/activation_maximization.py in visualize_activation_with_losses(input_tensor, losses, wrt_tensor, seed_input, input_range, **optimizer_params) 40 }, **optimizer_params) 41 ---> 42 opt = Optimizer(input_tensor, losses, input_range, wrt_tensor=wrt_tensor) 43 img = opt.minimize(**optimizer_params)[0] 44 ~/anaconda3/lib/python3.6/site-packages/vis/optimizer.py in __init__(self, input_tensor, losses, input_range, wrt_tensor, norm_grads) 50 # Perf optimization. Don't build loss function with 0 weight. 51 if weight != 0: ---> 52 loss_fn = weight * loss.build_loss() 53 overall_loss = loss_fn if overall_loss is None else overall_loss + loss_fn 54 self.loss_names.append(loss.name) ~/anaconda3/lib/python3.6/site-packages/vis/regularizers.py in build_loss(self) 99 value = K.pow(K.sum(K.pow(K.abs(self.img), self.p)), 1. / self.p) 100 --> 101 return normalize(self.img, value) ~/anaconda3/lib/python3.6/site-packages/vis/regularizers.py in normalize(input_tensor, output_tensor) 22 """ 23 image_dims = utils.get_img_shape(input_tensor)[1:] ---> 24 return output_tensor / np.prod(image_dims) 25 26 <__array_function__ internals> in prod(*args, **kwargs) ~/anaconda3/lib/python3.6/site-packages/numpy/core/fromnumeric.py in prod(a, axis, dtype, out, keepdims, initial, where) 2960 """ 2961 return _wrapreduction(a, np.multiply, 'prod', axis, dtype, out, -> 2962 keepdims=keepdims, initial=initial, where=where) 2963 2964 ~/anaconda3/lib/python3.6/site-packages/numpy/core/fromnumeric.py in _wrapreduction(obj, ufunc, method, axis, dtype, out, **kwargs) 88 return reduction(axis=axis, out=out, **passkwargs) 89 ---> 90 return ufunc.reduce(obj, axis, dtype, out, **passkwargs) 91 92 TypeError: unsupported operand type(s) for *: 'int' and 'NoneType'`