I am trying to visualise custom model trained on Ciphar-10 dataset.
My network is like below given-
`Model: "sequential"
Layer (type) Output Shape Param #
conv2d (Conv2D) (None, 30, 30, 32) 896
max_pooling2d (MaxPooling2D) (None, 15, 15, 32) 0
conv2d_1 (Conv2D) (None, 13, 13, 64) 18496
max_pooling2d_1 (MaxPooling2 (None, 6, 6, 64) 0
conv2d_2 (Conv2D) (None, 4, 4, 64) 36928
flatten (Flatten) (None, 1024) 0
dense (Dense) (None, 64) 65600
preds (Dense) (None, 10) 650
Total params: 122,570
Trainable params: 122,570
Non-trainable params: 0`
I have tried attention.ipyb script given in example/vgg folder as it is for RGB model.
But I am getting this error- InvalidArgumentError: conv2d_input_1:0 is both fed and fetched.
when I run code
from vis.visualization import visualize_saliency, overlay from vis.utils import utils from tensorflow.keras import activations layer_idx = utils.find_layer_idx(model, 'preds') f, ax = plt.subplots(1, 2) for i, img in enumerate([img1, img2]): grads = visualize_saliency(model, layer_idx, filter_indices=3, seed_input=img) ax[i].imshow(grads, cmap='jet')
Hi Geek's
I am trying to visualise custom model trained on Ciphar-10 dataset. My network is like below given- `Model: "sequential"
Layer (type) Output Shape Param #
conv2d (Conv2D) (None, 30, 30, 32) 896
max_pooling2d (MaxPooling2D) (None, 15, 15, 32) 0
conv2d_1 (Conv2D) (None, 13, 13, 64) 18496
max_pooling2d_1 (MaxPooling2 (None, 6, 6, 64) 0
conv2d_2 (Conv2D) (None, 4, 4, 64) 36928
flatten (Flatten) (None, 1024) 0
dense (Dense) (None, 64) 65600
preds (Dense) (None, 10) 650
Total params: 122,570 Trainable params: 122,570 Non-trainable params: 0`
I have tried
attention.ipybscript given in example/vgg folder as it is for RGB model. But I am getting this error-InvalidArgumentError: conv2d_input_1:0 is both fed and fetched.when I run code
from vis.visualization import visualize_saliency, overlay from vis.utils import utils from tensorflow.keras import activations layer_idx = utils.find_layer_idx(model, 'preds') f, ax = plt.subplots(1, 2) for i, img in enumerate([img1, img2]): grads = visualize_saliency(model, layer_idx, filter_indices=3, seed_input=img) ax[i].imshow(grads, cmap='jet')Keras version : 2.3.1 Tensorflow version : 1.14.0Please suggest some way. Thanks!!