keras with a new API.
Keras API will now become available directly as part of tensorflow
Questions tagged [keras-2]
264 questions
0
votes
1 answer
Error in removing the first layer of keras model
import numpy as np
from keras.applications.vgg19 import decode_predictions
from prettytable import PrettyTable
import time
from keras import backend as K
from tensorflow import keras
from tensorflow.python import keras
from keras import models,…
user11549734
0
votes
1 answer
Keras stops after fit_generator with no error
I am playing around with Resnet architectures to compare performance with a CNN. I used this Resnet for my first test. I am reusing my code to load and prepare data for the network and it works just fine. The rest of the script seems to also work…
Robi Sen
- 162
- 1
- 8
0
votes
2 answers
Migrate Convolutional2D dim_ordering parameter to Conv2D in tf.keras
I'm newbie with Tensorflow and Keras, and I'm migrating the following code:
Convolution2D(64, 5, 5, activation='relu', border_mode='same', dim_ordering='tf', name='conv1_1')(inputs)
The interpreter suggest me this code:
Conv2D(64, (5, 5),…
VansFannel
- 45,055
- 107
- 359
- 626
0
votes
0 answers
Tensorflow 2.0 custom gradient function
I am trying to build a custom gradient for A piece-wise continuous function that I found in the paper
A continuum among logarithmic, linear, and exponential functions, and its potential to improve generalization in neural networks - Godfrey
Current…
zwep
- 1,207
- 12
- 26
0
votes
1 answer
Keras fit_generator incorrect input shapes
I'm using an ImageDataGenerator to input batches of images to a neural network, but can't work out the correct way to feed it. Running the following:
train_datagen = ImageDataGenerator(rescale=1./255, shear_range=0.2, zoom_range=0.2,…
John Milton
- 33
- 4
0
votes
1 answer
Supressing the output when fitting a Keras model
I have designed a NN with Keras and the code after defining the model are the following:
model.compile(optimizer= 'Adam',loss='mean_squared_error')
##callbacks
cb_checkpoint = ModelCheckpoint("model.h5", monitor='val_loss',…
user8270077
- 4,621
- 17
- 75
- 140
0
votes
0 answers
How to should I divide the preprocessing arguments of Keras' ImageDataGenerator from the data augmentation arguments
I'm about to use Keras' ImageDataGenerator class (in keras/preprocessing/image.py) for training a neural net. I will have one generator for my training data, and another for my testing data. However, some of the arguments seem to apply to…
user1245262
- 6,968
- 8
- 50
- 77
0
votes
1 answer
how to use Merge in kerase>2.0?
word_model=Sequential() word_model.add(Embedding(vocab_size,embed_size, embeddings_initializer="glorot_uniform", input_length=1)) word_model.add(Reshape((embed_size,)))
context_model=Sequential()…
wwwxinyu
- 11
- 3
0
votes
1 answer
Runtime Error : Session Graph is Empty. Add Operations to Graph
# Build a graph.
a = tf.constant(5.0)
b = tf.constant(6.0)
c = a * b
# Launch the graph in a session.
sess = tf.compat.v1.Session()
# Evaluate the tensor `c`.
print(sess.run(c))
This above code is taken from tensorflow core r2.0 documentation
But…
Krishna Rohith
- 74
- 1
- 1
- 11
0
votes
1 answer
Simple keras dense model freezes while fitting
I am learning NLP with Keras and I am going through a tutorial. The code is the following:
import tensorflow_datasets as tfds
imdb, info = tfds.load("imdb_reviews", with_info=True, as_supervised=True)
import numpy as np
train_data, test_data =…
user8270077
- 4,621
- 17
- 75
- 140
0
votes
0 answers
How to record training and validation loss after each batch rather than epoch in Keras, Tensorflow 2.0
I am training a model which takes a long time to complete an epoch and I would like to be able to record and monitor during training the training and validation loss after each batch rather than epoch.
So currently this is what I get:
My callbacks…
user8270077
- 4,621
- 17
- 75
- 140
0
votes
1 answer
How to append images to a list inside a Keras network
I would like to append the images which are procurred by the ImageDataGenerators to two different lists. I believed I could do that with a lambda layer but I am getting an error message. For a toy example see the code below. You can use any set…
user8270077
- 4,621
- 17
- 75
- 140
0
votes
0 answers
Visualizing convoluational layers in autoencoder
I have built a variational autoencoder using 2D convolutions (Conv2D) in the encoder and decoder. I'm using Keras. In total I have 2 layers with 32 and 64 filters each and a a kernel size of 4x4 and stride 2x2 each. My input images are (64, 80, 1).…
machinery
- 5,972
- 12
- 67
- 118
0
votes
1 answer
Graph disconnected error when using skip connections in an autoencoder
I have implemented a simple variational autoencoder in Keras with 2 convolutional layers in the encoder and decoder. The code is shown below. Now, I have extended my implementation with two skip connections (similar to U-Net). The skip connections…
machinery
- 5,972
- 12
- 67
- 118
0
votes
1 answer
Padding in Conv2D gives wrong result?
I'm using the Conv2D method of Keras. In the documentation it is written that
padding: one of "valid" or "same" (case-insensitive). Note that "same"
is slightly inconsistent across backends with strides != 1, as
described here
As input I have…
machinery
- 5,972
- 12
- 67
- 118