Unanswered Questions
858 questions with no upvoted or accepted answers
12
votes
0
answers
212
views
Training value neural network AlphaGo style
I have been trying to replicate the results obtained by AlphaGo following their supervise learning protocol. The papers specify that they use a network that has two heads: a value head that predicts ...
- 783
8
votes
0
answers
3k
views
Tensorflow v1 Dataset API AttributeError with ndim
I'd like to make pipeline for optimizing Gpu and Cpu.
Dataset
It's about 10000 datapoint and 4 description variables for the regression problem.
...
- 201
8
votes
0
answers
2k
views
Using the Python Keras multi_gpu_model with LSTM / GRU to predict Timeseries data
I'm having an issue with python keras LSTM / GRU layers with multi_gpu_model for machine learning.
When I use a single GPU, the predictions work correctly ...
- 181
7
votes
0
answers
169
views
Unable to transform (greatly performing) Autoencoder into Variational Autoencoder
Following the procedure described in this SO question, I am trying to transform my (greatly performing) convolutional Autoencoder into a Variational version of the same Autoencoder. As explained in ...
- 71
6
votes
1
answer
8k
views
Keras - Implementation of custom loss function with multiple outputs
I am trying to replicate (a way smaller version) the AlphaGo Zero system. However, in the network model, I am having a problem. The loss function I am supposed to implement is the following:
$$l = (z -...
CommunityBot
- 1
6
votes
0
answers
361
views
Optimal implementation of vanilla DQN loss in Keras
I've implemented vanilla DQN for continuous/non-images (no CNN) states in keras. But, I'm not sure if my implementation of the loss computation is optimal.
For reminder the loss is defined as : $loss=...
- 24.8k
6
votes
0
answers
250
views
Connect output node to next hidden node in RNN
I'm trying to build a neural network with an unconventional architecture and a having trouble figuring out how. Usually we have connections like so, where $X=$ input, $H=$ hidden layer, $Y=$ output ...
- 2,298
6
votes
0
answers
1k
views
Keras objective function shared between outputs
Is there any way to implement a loss function that is shared between outputs? I have a 2D image output and scalar classification that are both used by a single loss function.
I have attempted writing ...
- 161
5
votes
0
answers
1k
views
Tensorflow, Optimizer.apply_gradient: 'NoneType' object has no attribute 'merge_call'
My program gives the following error message:
...
- 972
5
votes
2
answers
5k
views
Autoencoders for the compression of time series
I am trying to use autoencoder (simple, convolutional, LSTM) to compress time series.
Here are the models I tried.
Simple autoencoder:
...
CommunityBot
- 1
4
votes
1
answer
121
views
Training Machine Learning Model - Neural Network - Islands Problem
I was working on the following leetcode problem:
Given a 2d grid map of '1's (land) and '0's (water), count the number
of islands. An island is surrounded by water and is formed by
connecting ...
CommunityBot
- 1
4
votes
2
answers
7k
views
Saving and loading keras.callbacks.History object with np.save and np.load
I have been saving my training history in keras as follows:
...
CommunityBot
- 1
4
votes
0
answers
684
views
Embedding variable length "multi-hot-encoded" features
How can I implement an embedding layer in Keras that takes in an input that could have a variable length? For instance, if the vocabulary was 10-long I could have inputs like:
...
CommunityBot
- 1
4
votes
2
answers
264
views
Benefits of using Deep Learning-specific hyperparameter optimization tools vs. sklearn?
There are quite a few library for hyperparameter optimization that are specific to Keras or other Deep Learning libraries, like Hyperas or Talos.
My question is, what's the main benefit of using ...
CommunityBot
- 1
4
votes
3
answers
1k
views
How to determine the number of the training images in Keras after data augmentaion?
I want to create a CNN model and I am using data augmentation. I want know the number of augmented images in Keras.
How to determine the number of the training images in Keras after data augmentation?...
CommunityBot
- 1