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.

0
votes
2answers
18 views

Multiple Input types in a keras Neural Network

As an example, I'd like to train a neural network to predict the location of a picture(longitude, latitude) with the image, temperature, humidity and time of year as inputs into the model.My ...
-1
votes
1answer
13 views

Embedded-RNN with Keras - Issue with Concatenate

For audio classification, I would like to try a kind of embedded RNN. Based on the MFCC or the FFT of a 30 second samples, I would like to create a first output for every 1s subsample and then use the ...
0
votes
1answer
14 views

Keras model to predict probability distribution

We are trying to build a keras model to predict a vector with probablity rates from a vector of features. The output vector should be of probabilty rates which are between 0 and one and to sum to 1, ...
0
votes
0answers
16 views

Input and output in keras lstm

I am currently working on a speech to text project and I want to train a model using keras-LSTM framework. The questions are :How do I feed 3 feature vectors in the model ? I got 3 feature vectors ...
1
vote
0answers
17 views

In the tensorflow set to cuda Using a keras in tensorflow with cpu in python [duplicate]

I am run ML all the gpu in the cuda environment.And for other tasks, I need to operate tensorflow using cpu.When I run it without any settings, it runs as the GPU by default and causes the ...
0
votes
1answer
23 views

Implement CNN+LSTM model for OCR in keras

I want to create CNN+LSTM model for OCR, there are few examples OCR in tensorflow but I couldn't find any good examples on how to train it in keras. My dataset contains 200 images with maximum label ...
0
votes
1answer
19 views

Convert keras model from python3.6. to 3.5

I have a model trained in keras with python 3.6 and having a raspbian with python 3.5. When you load a model (or at least my model) trained with python 3.6 into python 3.6 you get an exception:...
-3
votes
0answers
22 views

Can anyone find the error?I was using keras and tensoflow?

Using TensorFlow backend.Traceback (most recent call last):File "app.py", line 32, in model, graph=init()File "/home/jitendra/cnn-hand-written-digit-master/model/load.py", line 12, in ...
0
votes
0answers
12 views

Auto_ML line 1147, in fit_grid_search scoring=self._scorer.score, AttributeError: 'NoneType' object has no attribute 'score'

I'm trying to use Auto_ml to generate a classifier and keep getting the following output/error:If you have any issues, or new feature ideas, let us know at http://auto.mlYou are running on version ...
-1
votes
0answers
13 views

Feature extraction in constitutional neural network [on hold]

helo guyz...i am going to build convolotional neural network for snake classification.in my country there are six venomous snakes.i need to detect them. my problem is how to create mask or filter to ...
1
vote
2answers
17 views

Can't use preprocess_input as preprocessing_function in ImageDataGenerator in Keras

When trying to provide preprocess_input imported from a CNN package (e.g. keras.applications.resnet) the model raises an error when trying to fit to the generated data: ‘JpegImageFile’ object is ...
0
votes
0answers
33 views

Python spyder + tensorflow cross validation freezes on Windows 10

On Windows 10, I have installed Anaconda and launched Spyder. I have also successfully installed Theano, Tensorflow and Keras, since when I execute import kerasthe console outputs Using ...
0
votes
1answer
30 views

Keras 'Tensor' object has no attribute 'ndim'

I am trying to implement a siamese network (by using triplet loss method). I just cannot make it train. After many tries, I guess that I have my problem in the generator (where I prepare the input ...
1
vote
1answer
21 views

Image preprocessing as a Keras lambda layer vs preprocessing on its own

I'm trying to apply preprocessing imported from a resnet50 module in Keras before propagating the images through the network. Since I got errors when trying to apply it in the generator object, I ...
1
vote
1answer
32 views

Using pretrained word embeddings to classify “pools” of words

I have seen many papers explaining the use of pretrained word embeddings (such as Word2Vec or Fasttext) on sentence sentiment classification using CNNs (like Yoon Kim's paper). However, these ...

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