# Questions tagged [keras-layer]

The keras-layer tag has no usage guidance.

**0**

votes

**0**answers

9 views

### how to get the real shape of batch_size which is none in keras

When implementing a custom layer in Keras, I need to know the real size of batch_size. my shape is (?,20).
questions:
1. What is the best way to change (?,20) to (batch_size,20).
I have looked into ...

**-1**

votes

**2**answers

30 views

### Accuracy for Regression

I am experementing molecular activity prediction as regression model in keras.
x_train.size=6252312
x_train.shape=(1452, 4306)
y_train.shape=(1452, 1)
y_train.size=1452
model = Sequential()
model....

**-3**

votes

**0**answers

17 views

### Need a description of theose instructions and the graph created by this code

Donnez une description des instructions ainsi que le graphe crée par ce code :
from keras.models import Sequential
from keras.layers import Convolution2D
from keras.layers import MaxPooling2D
from ...

**0**

votes

**1**answer

21 views

### how to see tensor value of a layer output in keras

I have a Seq2Seq model. I am interested to print out the matrix value of the output of the encoder per iteration.
So for example as the dimension of the matrix in the encoder is (?,20) and the epoch =...

**0**

votes

**1**answer

15 views

### Keras graph disconnected - but why?

Via Keras I create a functional API model based on VGG16 and some custom layers:
input_layer = layers.Input(shape=(150, 150, 3), name="model_input")
conv_base = VGG16(weights="imagenet", include_top=...

**0**

votes

**0**answers

27 views

### How to use metric with three inputs(GAP metric) in Keras while training?

This is GAP metric code from kaggle
def GAP(pred, conf, true):
x = pd.DataFrame({'pred': pred, 'conf': conf, 'true': true})
x.sort_values('conf', ascending=False, inplace=True, na_position='...

**0**

votes

**0**answers

17 views

### Is there a way to import a pretrained Keras embedding layer into Gensim word2vec?

I've trained a CNN model for sentence classification in Keras and now I want to load the trained embedding layer (input_dim=20000, output_dim=50, input_length=400) into a gensim word2vec model. I know ...

**0**

votes

**1**answer

30 views

### Keras Model for Molecular Activity

I am experimenting with the Merku molecular activity challenge and I have created the train and test dataset.
The shape of the data is the following:
x_train.shape=(1452, 4306)
y_train.shape=(1452, ...

**0**

votes

**0**answers

24 views

### CNN with Tf-Idf matrix as input, but without an embedding layer?

I'm trying to work on the airline tweets datasets, and I've explored several possibilities for that. I saw some other tutorials where people used a count matrix (from sklearn CountVectorizer) and then ...

**0**

votes

**1**answer

19 views

### Converting Keras to Tensorflow — Pruning + Probability

I have a code that mixes Tensorflow Probability (requires TF 2.00) with Keras Pruning, pruning weights of a first Dense Layer and providing inputs for TF probability, having both codes (Keras + TF) in ...

**0**

votes

**0**answers

20 views

### keras multi-input model: Expected to see 2 array(s), but instead got the following list of 1 arrays

I'm training a functional keras model on mnist dataset. There's a layer that requires 2 inputs - the traditional input tensor and a current batch of on-hot encoded labels. I think I've set up my model ...

**0**

votes

**0**answers

7 views

### How to make custom gaussian noise layer that imposing different stddev to each column of dataset in Keras?

I want to make gaussian noise layer of Keras that is imposing noise with different stddev level to each column of dataset. However, since I am not know much about coding stuffs, there is a big problem ...

**0**

votes

**1**answer

12 views

### Fine-tune InceptionV3 model not working as expected

Trying to use transfer learning (fine tuning) with InceptionV3, removing the last layer, keeping training for all the layers off, and adding a single dense layer. When I look at the summary again, I ...

**0**

votes

**2**answers

19 views

### Why does the last fully-connected/dense layer in a keras neural network expect to have 2 dim even if its input has more dimensions?

I'm trying neural networks with keras for the firs time, and am a bit confused with the dimensions it expects. I am sure that my X_train and y_train data are of the same dimension, and that the X_test ...

**0**

votes

**1**answer

25 views

### How to create Keras Model() from VGG layers

I have created a custom Keras model using the VGG16 base, which I train and save:
from keras.applications import VGG16
from keras import models
from keras import layers
conv_base = VGG16(weights="...

**1**

vote

**1**answer

27 views

### What does super achieve

This is the code for building custom keras layer
class MyLayer(Layer):
def __init__(self, output_dim, **kwargs):
self.output_dim = output_dim
super(MyLayer, self).__init__(**...

**1**

vote

**2**answers

38 views

### Get (input) layer of Keras model after saving and re-loading it from disk

I have loaded, extended, trained a VGG16 network via Keras, then saved it to disk:
from keras.applications import VGG16
from keras import models
conv_base = VGG16(weights="imagenet", include_top=...

**1**

vote

**1**answer

65 views

### How to split a Keras model, with a non-sequential architecture like ResNet, into sub-models?

My model is a resnet-152 i wanna cutting it into two submodels and the problem is with the second one i can't figure out how to build a model from an intermediate layer to the output
I tried this ...

**0**

votes

**1**answer

21 views

### How to loop through 2D matrices of a 4D (None, x, y, z) activation tensor from a resnet layer?

I wanna loop through 2D matrices of a 4D tensor which is the output of a resnet layer (activation map or feature map) in order to modify it a bit at test time
NB: am using keras
I tried converting ...

**0**

votes

**0**answers

14 views

### How can I fix “Unknown layer: DenseFeatures” while importing pre-trained keras model?

I was following the tutorial for classifying structured data from here. I trained the model as described with my data which only comprised of numeric data.
I have trained and optimised my model on ...

**0**

votes

**0**answers

13 views

### keras sub layer function with training weight

I have a custom layer with a function in this. function has a w training weight. How can I working with this in below code.
class ConvCaps(tf.keras.layers.Layer):
"""This constructs a convolution ...

**0**

votes

**0**answers

14 views

### Autoencoder accuracy not improving using keras

I am trying to create a convolutional autoencoder with keras for expression classification but the accuracy gets stuck after 2-3 epochs at 0.10 (10% max) during training. Is this because of problem in ...

**-1**

votes

**0**answers

29 views

### Can't add custom layers to topless VGG

I am implementing an algorithm called "IMPROVED BILINEAR POOLING". It consists of taking a VGG or without the FC layers. On top of that, I have added 4 custom layers: the 1st performs the outer ...

**-2**

votes

**0**answers

22 views

### Why Keras cannot achieve intermediate layers' model and outputs from the trained model directly

This is a question about the API design of Keras. For a trained DNN model defined in Keras, if I want to achieve the intermediate models and outputs of its layers, I have to create a new model.
from ...

**0**

votes

**1**answer

24 views

### AttributeError: 'NoneType' object has no attribute '_inbound_nodes' in Keras

I want to define my own Lstm model as follows:
from keras import backend as K
from keras.callbacks import ModelCheckpoint
from keras.layers.core import Dense, Activation, Flatten, Dropout
from keras....

**0**

votes

**0**answers

23 views

### How to get word embedding of input sequence of words to embedding layer in keras

I wanted to know If the code I have below correctly gives me the word embeddings of the input.
model = Sequential()
model.add(Embedding(20, 10, input_length = 15, name ="Embedding1"))
...

**0**

votes

**2**answers

23 views

### Linear activation layer vs no activation layer

I'm playing with Keras a little bit and I'm thinking about what is the difference between linear activation layer and no activation layer at all? Doesn't it have the same behavior? If so, what's the ...

**0**

votes

**1**answer

12 views

### Inconsistency in Keras Flatten() layer behavior using Theano Backend

I am trying to understand the behavior of the Flatten() layer in Keras with Theano backend. I have two different versions of Keras installed in two different Conda environments. The way a 4D tensor is ...

**1**

vote

**1**answer

44 views

### How to perform Virtual Batch Normalization (VBN) in keras

VBN is talked in This paper. And implemented Here, Here and Here. I donot want to go to core/full code. I just want to know, how to use VBN as keras layer, as i am not very expert tensorflow/keras ...

**0**

votes

**1**answer

24 views

### Keras - How to get GRU cell state?

For LSTM we can retrieve last output and last cell state as below
outputs, state_h, state_c= LSTM(lstm_dim, return_sequences=True, return_state=True)(inputs)
where state_h is the last sequence of ...

**0**

votes

**0**answers

52 views

### Elmo Embedding Layer by using Keras Layer

from keras.layers import Dense, Input, RepeatVector, Lambda, Permute, Multiply, Concatenate
from keras.engine import Layer
from keras.layers.convolutional import Conv1D
from keras.models import Model
...

**0**

votes

**1**answer

27 views

### Keras Function (K.function) not working with RNN (code provided)

I was trying to see the each of the layers' outputs on Keras, but I couldn't get to the correct code so I made a simple code where I was stuck at.
Question: How am I supposed to get the output of ...

**0**

votes

**1**answer

32 views

### Splitting a Keras model on an arbitrary layer

I'm trying to create a function that splits a Keras model on a user specified layer. I have the following code:
def return_split_models(model, layer):
model_f, model_h = Sequential(), Sequential()...

**1**

vote

**1**answer

38 views

### How to use Keras LSTM batch_input_size properly

I'm using Keras framework to build a stacked LSTM model as follows:
model.add(layers.LSTM(units=32,
batch_input_shape=(1, 100, 64),
stateful=True,
...

**0**

votes

**2**answers

46 views

### How to write a keras lambda layer to turn a 'vector' input layer into a 'image' layer with keras backend?

I have two inputs to the model:
input_img = Input(shape=(self.img_rows, self.img_cols, self.channels,))
input_cond = Input(shape=(self.cond_dim,))
Their shapes are different, I want to expand each ...

**1**

vote

**1**answer

50 views

### trainable_variables attribute of the custom layer in Keras returns empty list

I tried to build my own custom layer in tensorflow/keras that enforces the layer to be symmetric and what I ended up with is the following:
import tensorflow as tf
from tensorflow.python.framework....

**0**

votes

**0**answers

24 views

### How to use the dot merge in keras 2.0?

I am building a recommender system using deep learning. When defining my model I get the following error:
ValueError: Layer dot_1 was called with an input that isn't a symbolic tensor. Received ...

**0**

votes

**1**answer

28 views

### how do I feed the inputs of network if it has not fed by model.fit?

I have a simple network in keras and I define a custom layer which does some operations on input tensor and then returns it to the network, but when I want to implement it, it produces the following ...

**1**

vote

**1**answer

36 views

### Where do the parameters in keras layers apply?

I'm trying to get to grips with the basics of neural networks and am struggling to understand keras layers.
Take the following code from tensorflow's tutorials:
model = keras.Sequential([
keras....

**0**

votes

**0**answers

14 views

### How to define a morphology operation in a Neural Network as an activation function?

I recently completed a task to study how to use morphological operation as an activation function for neural networks. But I had no idea and didn't know how to use keras for custom functionality. Can ...

**0**

votes

**0**answers

9 views

### ValueError: Error when checking target: expected dense_1 to have 4 dimensions, but got array with shape (5, 1)

train_datagen = ImageDataGenerator(rescale=1./255)
test_datagen = ImageDataGenerator(rescale=1./255)
train_generator = train_datagen.flow_from_directory(
'dataset/train',
target_size=...

**1**

vote

**1**answer

38 views

### How to create a custom keras layer “min pooling” but ignore zeros?

I am working on neural networks with keras and tensorflow backend.
Usually it is built up with convolutional and max pooling layers like it's done in vgg16 for example. For my neural network I would ...

**0**

votes

**0**answers

28 views

### Error when checking target: expected dense_13 to have shape (39,) but got array with shape (1,)

I am working on model in Keras, on a 3 classes subset , and encountered the following error:
TypeError: __init__() missing 1 required positional argument: 'units'
I read multiple similar issues ...

**0**

votes

**1**answer

13 views

### Expand Model layer

I have a pretained model with summary:
Layer (type) Output Shape Param #
=================================================================
vgg19 (Model) ...

**0**

votes

**0**answers

36 views

### How to explain get_weight with autoencoder in keras?

I built an autoencoder model of three layers with 9 5 9.
Input dim =9, encoder dim =5, output dim=9
When I get the model weights,
weight1=autoencoder.layers[1].get_weights()
weight2=autoencoder....

**1**

vote

**1**answer

37 views

### Keras 2: Using lambda function in “Merge” layers

I am trying to implement this merge layer:
policy = merge([out1, out2], mode = lambda x: x[0]-K.mean(x[0])+x[1], output_shape = (out_node,))
However, "merge" is no longer present in Keras 2. You can ...

**-1**

votes

**0**answers

28 views

### Loss is not reducing while training a binary classifier

Am trying to build the binary classifier model, which helps to predict the given number is even/dd.
Created 50k samples to train the modal, after three epochs the loss rate is not reducing below 0.6. ...

**3**

votes

**1**answer

37 views

### Dynamic Activation Function in Keras

I'm working on a research project which involves replacing certain ReLu activations with polynomial activations. The code I inherited is using Keras with TensorFlow backend - something I have little ...

**1**

vote

**0**answers

159 views

### Keras - The added layer must be an instance of class Layer. Found: Tensor

I'm trying to implement skip-gram using keras. Getting error while adding the Dot() layer. The below implementation is inspired by Dipanjan code. I have done some modification related to different ...

**0**

votes

**0**answers

13 views

### Keras, try to backprop from the layer step + 1 of the output layer

While I was trying to reimplement keras seq2seq as from the official website.
https://keras.io/examples/lstm_seq2seq/
Cause:
The problem is that some of the languages contain too many characters so ...