Keras is a minimalist, highly modular neural network library providing a high-level Python API that allows for rapid prototyping, and allows the use of one of several computational back-ends.

3
votes
1answer
511 views

ValueError at /image/ Tensor Tensor(“activation_5/Softmax:0”, shape=(?, 4), dtype=float32) is not an element of this graph

I am building an image processing classifier and this code is an API to predict the image class of the image the whole code is running except this line (pred=model.predict_classes(test_image)) this ...
54
votes
5answers
104k views

How do I install Keras and Theano in Anaconda Python on Windows?

I am trying to work on neural networks in Python using the following Keras packages:from keras.utils import np_utilsfrom keras.layers.core import Dense, Activation, Dropoutfrom keras.models import ...
22
votes
6answers
22k views

Keras, How to get the output of each layer?

I have trained a binary classification model with CNN, and here is my codemodel=Sequential()model.add(Convolution2D(nb_filters, kernel_size[0], kernel_size[1],border_mode=...
2
votes
2answers
148 views

ValueError: Error when checking target: expected model_2 to have shape (None, 252, 252, 1) but got array with shape (300, 128, 128, 3)

hi I am building a image classifier for one-class classification in which i've used autoencoder while running this model I am getting this error by this line (autoencoder_model.fit) (ValueError: Error ...
0
votes
1answer
226 views

Keras misinterprets training data shape

My training data has the form (?,15) where ? is a variable length.When creating my model I specify this:inp=Input(shape=(None,15))conv=Conv1D(32,3,padding='same',activation='relu')(inp)......
33
votes
6answers
25k views

Keras binary_crossentropy vs categorical_crossentropy performance?

I'm trying to train a CNN to categorize text by topic. When I use binary_crossentropy I get ~80% acc, with categorical_crossentrop I get ~50% acc.I don't understand why this is. It's a multiclass ...
6
votes
1answer
3k views

How do you create a custom activation function with Keras?

Sometimes the default standard activations like ReLU, tanh, softmax, ... and the advanced activations like LeakyReLU aren't enough. And it might also not be in keras-contrib.How do you create your ...
90
votes
1answer
10k views

Understanding Keras LSTMs

I am trying to reconcile my understand of LSTMs and pointed out here: http://colah.github.io/posts/2015-08-Understanding-LSTMs/ with the LSTM implemented in Keras. I am following the blog written http:...
22
votes
2answers
9k views

Neural Network LSTM input shape from dataframe

I am trying to implement an LSTM with Keras.I know that LSTM's in Keras require a 3D tensor with shape (nb_samples, timesteps, input_dim) as an input. However, I am not entirely sure how the input ...
8
votes
4answers
2k views

When does keras reset an LSTM state?

I read all sorts of texts about it, and none seem to answer this very basic question. It's always ambiguous:In a stateful=False LSTM layer, does keras reset states after:Each sequence; or ...
24
votes
1answer
5k views

Many to one and many to many LSTM examples in Keras

I try to understand LSTMs and how to build them with Keras. I found out, that there are principally the 4 modes to run a RNN (the 4 right ones in the picture)Now I wonder how a minimalistic code ...
5
votes
2answers
2k views

How to export Keras .h5 to tensorflow .pb?

I have fine-tuned inception model with a new dataset and saved it as ".h5" model in Keras. now my goal is to run my model on android Tensorflow which accepts ".pb" extension only. question is that is ...
2
votes
1answer
206 views

How does Keras evaluate the accuracy?

If there's a binary classification problem, and if label are 0 and 1i know the prediction is a float number because p is possibility of belonging to that class.But labels are 0 1.They're all not ...
4
votes
2answers
2k views

Tensorflow + Keras + Convolution2d: ValueError: Filter must not be larger than the input: Filter: (5, 5) Input: (3, 350)

I have been trying to run the code below which I got from here and even though I have changed almost nothing other than the image size (350,350 instead of 150, 150) is still cannot get it to work. I ...
3
votes
1answer
259 views

Layer conv2d_3 was called with an input that isn't a symbolic tensor

hi I am building a image classifier for one-class classification in which i've used autoencoder while running this model I am getting this error (ValueError: Layer conv2d_3 was called with an input ...

153050per page
angop.ao, elkhabar.com, noa.al, afghanpaper.com, bbc.com, time.com, cdc.gov, nih.gov, xnxx.com, github.com,