Questions tagged [tensorflow]

A Python library for deep learning developed by Google. Use this tag for any on-topic question that (a) involves tensorflow either as a critical part of the question or expected answer, & (b) is not just about how to use tensorflow.

Filter by
Sorted by
Tagged with
3
votes
3answers
336 views

classification imbalance data - bias and class weight

This page shows a classification problem. They have used bias as well as bias along with class weights. What is the difference between bias and weights? In some other techniques such as Random ...
0
votes
0answers
27 views

Sequence to Sequence model not training

I am working on a sequence to sequence chatbot model based on the Tensorflow NMT tutorial for a project. I have a database of about 15 million replies and around 3 million individual words. It is an ...
1
vote
0answers
50 views

How to maximize subset accuracy for multilabel multiclass image classification

I working on multi-label multi-class image classification. I am using TensorFlow. Currently I am using sigmoid on output layer with binary_crossentrpy. Model is ...
0
votes
0answers
16 views

How can i define a range of correct answers for an neural network, that predicts a continous value?

Take for example a NN that predicts the height of an animal. If the NN predicts a height within +/- 1 cm of the actual height the answer would be correct. I can not find options for this in e.g. Keras....
0
votes
1answer
1k views

Activation function between LSTM layers

I'm aware the LSTM cell uses both sigmoid and tanh activation functions internally, however when creating a stacked LSTM architecture does it make sense to pass their outputs through an activation ...
0
votes
0answers
7 views

How to test ssd inference using tensorflow

I am trying to test a particular network (ssd_inception_v2) using Tensorflow. I can train it, but I am not sure how to test the inference using the feed from my camera. I searched on the Tensorflow ...
1
vote
0answers
28 views

How is convolution process done with 4D kernel?

Applying convolution with kernel of shape (1, 1, 4, 6)to a tensor of shape (2, 3, 2, 4) the result will be (2, 3, 2, 6). ...
6
votes
1answer
131 views

Differentiable programming for general Bayesian decision theory

It is my understanding that differentiable programming and thus libraries like TensorFlow (e.g. TFP) and JAX can be used to solve Bayesian decision theory problems where e.g. we have a probabilistic ...
1
vote
0answers
60 views

Tensorboard: Why does validation loss get evaluated after training loss stops?

When I monitor my model through Tensorboard, I notice that Tensorboard stops plotting the training loss but not the validation loss. Since the early stopping module, as I set it up below, is ...
1
vote
1answer
38 views

Training a neural network, I can't figure out my learning curves [closed]

I am cross validating a model, splitted in 5. Then I plotted for each split, the loss and the val_loss by epochs. I get something like that: I found this plot disturbing. Only the first one seems "...
0
votes
0answers
39 views

Using label encoder on a categorical feature that we want to embed

I have a dataset with feature that have very high cardinality, doing one-hot encoding is not an option because of memory limitations, so I am currently label encoding this feature and then I feed that ...
0
votes
0answers
114 views

keras mse adam val_loss much lower than nrmse?

I'm trying to make sense of the keras.models.Sequential reported val_loss. It is a much better ...
0
votes
1answer
148 views

is this way of applying data augmentation correct [closed]

I'm training a CNN and want to apply some data augmentation to my input images. I combined some code from tensorflow tutorials and have the following workflow: I have a dataset containing all ...
0
votes
1answer
1k views

imbalanced dataset - class weight vs weighted loss function

I'm working on a classification problem with a very imbalanced dataset. Many papers mention a "weighted cross-entropy loss function" or "focal loss with balancing weights". I can't find any of those ...
1
vote
0answers
34 views

Tensorflow - simple multilayer perceptron not stabilizing around mean of normally distributed y-values

I'm building an FX trading model where I'm trying to predict the +/- movement of a currency pair 5 minutes into the future. I've had some promising results adapting the model as a classifier (i.e., ...
2
votes
1answer
106 views

How to feed multivariate spatio-temporal data into cnn?

After trying to find an example for quite a while, I finally came to ask my question here: What I have: I have a temporal sequence of 2d spatial data with 100 cells(or pixels) in longitude and 30 ...
0
votes
0answers
18 views

tf sumpooling layer 1d vs 2d

I am currently working on a paper by Sturm et al. (2016) published in the Journal of Neuroscience trying to replicate their results using python and TensorFlow, Keras libraries. I have strong doubts ...
1
vote
1answer
201 views

Why can't this autoencoder reach zero loss?

I'm building an autoencoder and was wondering why the loss didn't converge to zero after 500 iterations. So I created this "illustrative" autoencoder with encoding dimension equals to the input ...
0
votes
1answer
38 views

Keras--variational auto-encoder in R studio, which part is defined as Encoder?

This is the example given on VAE, the circle part is something I do not understand. It defined the encoder part as from (X to Z_mean), but my understanding is from(x to Z). Or it just simply does not ...
0
votes
1answer
431 views

What's the difference between Hidden layer and fully connected layer?

I'm newer in the Deep learning domain, I would like to know what's the difference between a hidden layer and a fully connected layer? Are they the same thing? If no, How to create a hidden layer ...
2
votes
2answers
86 views

Class imbalance, Random Over/Undersampling and the use of Class Weights and bias

I was looking at the Tensorflow tutorial on "Classification on Imbalanced Data". Now they first show how to apply some approaches to deal with imbalance using model weights and a pre-initialized bias ...
0
votes
1answer
59 views

Reparametrization trick in VAE at Evaluation time

So I've been trying to implement the Variational Auto-Encoder model of Kigma et.al, but something has been bugging me. While I understand the need for reparametrization trick at training time, the ...
0
votes
0answers
32 views

Tensorflow - keras: bad performance for simple curve fitting task [duplicate]

I'm trying to implement a very simple one layered MLP for a toy regression problem with one variable (dimension = 1) and one target (dimension = 1). It's a simple curve fitting problem with zero noise....
0
votes
0answers
179 views

Calculating EER with anomaly detection using LSTM in python

I have dataset features evaluated from the touch screen and built-in sensors on smartphones. I want to implement an anomaly detection code using LSTM autoencoder in python to compute EER value (Equal ...
0
votes
0answers
32 views

Help in converting Tensoflow network to Keras network

The following code is creating a CNN using Tensorflow (imported as tf): ...
0
votes
0answers
347 views

VRNN (Variational Recurrent Neural Network) code with Variable Input Lengths on Tensorflow

I have been trying to write VRNN (Variational Recurrent Neural Network: A recurrent latent variable model for sequential data (NIPS 2015)) with variable input data length. My problem is that it is ...
0
votes
0answers
8 views

Performance Statistics Of Each Class in ML Classification problem

I am comparing the performance of two neural network architectures for a classification problem with three possible outputs. I am able to track the overall progress (validation accuracy/loss) of ...
0
votes
0answers
17 views

Keras - Neural Network learns correctly trend of data, but not amplitude

I built a Neural Network in Keras to learn a mapping between 4 coordinates x,y,z,d (with d=sqrt(x**2+y**2+z**2)) and a scalar ...
1
vote
1answer
27 views

Why do my training losses go up?

I am new to Machine Learning and Tensorflow. For one of my courses, I need to train an MLP for the xor gate. But my losses somehow go up each epoch, which confuses me and I must admit that I ran out ...
0
votes
0answers
20 views

Correcting Keras metrics for zero-padding in final time distributed layer

python=3.7 tensorflow=1.14 keras=2.3.1 I have trained a keras model to categorize each element of a sequence of variable ...
0
votes
0answers
144 views

What input for joint word and character embeddings

I'm implementing a neural network that classifies Tweets (positive/neutral/negative). I'm using GloVe Twitter word embeddings (200dim) but since I have a lot of OOV words I'd like to add to each ...
1
vote
1answer
38 views

What materials are a starting point for developing deep learning architectures?

So some background on my existing knowledge. I have my masters in statistics where I spent a good amount of time understanding how machine learning algorithms work, but I was always allowed to use ...
0
votes
0answers
121 views

How to add example ID to tf.keras.utils.Sequence?

I am using tf.keras.utils.Sequence to build a dataset and then model.fit() to train a model (similar to how it is done in this ...
0
votes
0answers
7 views

Identifying specific activation scores for certain classes in keras in multi-label classification

I have a question i am hoping somebody might be able to help with. I have trained a sequential model (keras) that attempts to understand multiple labels in a data set. There are hundreds of samples (...
0
votes
0answers
28 views

Best Method to Find Embedding Similarity Between Array of Items to One Single Item

Say I have an array of items purchased together and I have different attributes of these products purchased together. ...
1
vote
0answers
37 views

autoencoding spiky time series - better loss function?

I am experimenting with convolutional autoencoders for time series. My first network architectures work quite well. However, the autoencoder has a tendency to soften the spikes in the time series. And ...
0
votes
0answers
23 views

Setting seeds despite repeated training of CNNs?

I would like to compare the classification performance (like accuracy, precision, recall etc.) of different CNN architectures. I'm using Google Colab (GPU support), Tensorflow and Keras. Since it is ...
0
votes
1answer
63 views

Is there a difference between training with multiple objects in a single image and multiple objects in a different images?

I'm trying to generate data for my object detection network (which will be used for TensorFlow: ResNet). What I'm currently curious about is this: if I have the same total amount of data (each data ...
1
vote
1answer
40 views

Accuracy converging to one in neural network (tensorflow.keras)

I was wondering if somebody would be able to shine a light on accuracy converging to 1 relatively quickly during training. I am working on some new data and this is the first time i have seen this. ...
0
votes
0answers
8 views

Combining two structurally similar datasets from different sources

I am working with a text summarization problem, and I am trying to use the following architecture [Pointer Generator] (https://github.com/abisee/pointer-generator). My data set is VERY small (225 ...
0
votes
1answer
397 views

How to compare CNN models with non-reproducible results?

I try to compare different CNN models. I use Keras and for training, I use a GPU, Google Colab with Tensorflow backend. Unfortunately I'm not able to create the same initial conditions for the CNNs (...
0
votes
1answer
75 views

Is skip-gram model of word embedding actually a multi-class task not a multi-label task, right?

So curious about this question, that I can't describe it in short. Please forgive me. Description: From multiclass and multilabel algorithms, we can get the definition of the multi-class and multi-...
0
votes
0answers
97 views

Why does Dice loss neglect to predict a random subset of classes?

I implemented Dice loss for a semantic segmentation problem (with a severe class imbalance in my dataset) as follows: ...
0
votes
2answers
52 views

What does it means when MSE almost equal with labels' variance?

I did a training for my dataset of 6000 images. running np.var(train_data), I get 2435. After training of enough epochs, my MSE is nearly 2415+-. Is this means, that the model is unable to find any ...
0
votes
0answers
30 views

Teaching movie recommendation network to avoid duplicates

I'm trying to implement a simple movie recommender using a neural network and collaborative filtering, i.e. given a list of movies the user has watched, what is a good movie recommendation. Results ...
0
votes
0answers
216 views

How can I coumpute Policy Gradient LOSS in tensorflow

I am self-studying RL and currently doing hw2 from Berkeley CS294-112. The thing I cannot figure out is how to compute loss in policy gradients. Basically, REINFORCE algorithm has the following update ...
3
votes
1answer
42 views

Which machine learning model could be used for the following?

I am an experienced programmer but very new to machine learning. I have a data set that consists of about 50,000 sets of 2,000 ordered values. All of the values are floats normalised to between 0 and ...
0
votes
0answers
23 views

Is it a good idea to implement a sklearn model for a real time image processing application?

I'm testing a support vector machine (SVM) model trained with scikit learn library for image processing, but i don't know exactly if for real time this library could be better than tensorflow or both ...
0
votes
0answers
39 views

Why the Logistic regression model trained with tensorflow performed so poor

I trained a logistic regression model with tensorflow but the accuracy of the model was so poor (accuracy = 0.68). The model was trained using simulated dataset and the result should be very good. is ...
1
vote
0answers
292 views

Why Massive Random Spikes of Validation Loss?

My problem is to estimate the length of a straight line in an image, in pixel. My training size is 6000 images, validation is 1000 images. Each image has 200 x 200 pixels. My data is generated using ...

1 2
3
4 5
12