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
4
votes
1answer
601 views

Loss function (and encoding?) for angles

I'm training a network to predict the angle of arrival of a signal. Labels are single values in the [-180, 180) interval. I'm seeing a discontinuity in predictions around ±180 degrees, which makes ...
1
vote
0answers
35 views

What is default error threshold Tensorflow? [closed]

My homework states that I am asked "to report the default error threshold used in the TensorFlow default configuration for convergence. Usually it is documented for MNIST and CIFAR-10". What's that? ...
0
votes
0answers
10 views

Can a neural network independently change its learning parameters while the error between what was predicted and what was not the most minimal in R

I performed script which create forecast of usd/btc pair. Data was taken form open source https://www.cryptodatadownload.com/apac/ https://www.cryptodatadownload.com/cdd/Binance_BTCUSDT_1h.csv Here ...
0
votes
1answer
914 views

no attribute '_inbound_nodes' error even when using Lambda layer in Keras [closed]

I have a (28,000 x 300) dimension matrix, let's call it label_embedding, which I want to do a dot product with the bottleneck layer of my model. I have created an architecture which gives a (...
0
votes
0answers
37 views

Unable to learn weights of a Word2Vec model [duplicate]

I was going to implement a word embedding model - namely Word2Vec - by following this TensorFlow tutorial and adapting the code a little bit. Unfortunately, though, my model won't learn anything. I've ...
1
vote
0answers
18 views

Needing 4th dimension for shape [closed]

I was working on a transfer learning solution to categorize between diseases in the eye. I was using the Xception model built into Keras and it uses a data set that I was able to accumulate. However ...
0
votes
1answer
88 views

How do I fix this dimenion error in keras / tensorflow? [closed]

This is the code I am trying to run. X is an array of shape (1000,26) and Y is of shape (1000, 1). I am trying to fit a model that predicts a 1 or a 0 for each row of the X array. For whatever reason ...
0
votes
0answers
54 views

Chinese character recognition from generated images - Validation accuracy does not improve

I am currently working on creating a simple Chinese character recognition network. Given an grayscale image of a character, the goal is to predict the depicted character. I want to run the model on a ...
0
votes
0answers
61 views

Data balancing in image classification

I've to segment defects from an image. The image consists of only tomatoes with it's defects in it. The defects and tomatoes in the dataset are as follows: ...
0
votes
1answer
39 views

Increasing sample size increases no of trainable parameters

I was working with keras and tensorflow as backend on an NLP problem when I observed that increasing my training data size caused an increase in the number of trainable parameters even when batch size ...
0
votes
0answers
18 views

How can I iterate on the hidden activations in a neural network? - Lifetime and spatial sparsity in WTA Autoencoders

I've built a convolutional autoencoder and trained it on MNIST in keras and tensorflow. I wanted to make this autoencoder a WTA autoencoder as talked about in this paper. To do so, I need to add ...
2
votes
0answers
87 views

How to choose number of neurons and hidden layers? [duplicate]

I followed this guy's tutorial on YouTube. Following is the code that was used for classifying 0 to 9 handwritten digits from MNIST dataset. The dataset contains 70,000 images of 28 x 28. Here, 60,000 ...
2
votes
1answer
362 views

MAP of Gaussian Process Classification in Tensorflow Probability

I'm attempting to implement Gaussian Process Classification learning in tensorflow-probability, but my estimator turns out to be very biased toward zero. As opposed ...
0
votes
1answer
29 views

Dynamic/ Static outputs are not same, why?

I am trying to implement a patch creation function with using tensorflow's extract_image_patches function but dynamic output shape is not same as my expectation. Let me tell briefly what it does. ...
0
votes
0answers
43 views

MNIST with Tensorflow and Keras, same architecture but less accurate in Tensorflow

I implemented a neural network in Keras and Tensorflow to make predictions on the MNIST dataset. I used the same architecture for both Keras and Tensorflow. While the code in Keras gives me always an ...
1
vote
0answers
40 views

Neural Network to discover an unknown number of patterns from a dataset of images?

I have a big set of images (>10.000), where there are similarities among them. I need to find a number/group of image patterns (eg, 5) that represent all images. As I do not know what patterns are, ...
0
votes
0answers
38 views

How to extract fixed sized feature vector from arbitrary graph data?

So I am dealing with graph data and graph neural networks. Usually a graph convolution network takes an adjacency matrix and one feature vector like this : ...
0
votes
0answers
137 views

When should I stop the object detection model training while mAP are not stable?

I am re-training the SSD MobileNet with 900 images from the Berkeley Deep Drive dataset, and eval towards 100 images from that dataset. The problem is that after ...
0
votes
0answers
12 views

Tensorflow: MNIST CNN only predicting 4s and 5s? [duplicate]

I am attempting to create my first CNN in TensorFlow. The objective is able to predict the MNIST Dataset. I have come across a very odd issue...my model is only able to predict 4s or 5s. There seems ...
0
votes
0answers
42 views

How can I interpret the result of get_weight of latent size in Seq2Seq model keras

My question is related to Seq2Seq models where we have LSTM as encoder and decoder. Imagine we have the Autoencoder alone, and we extract the weight associated ...
1
vote
1answer
22 views

TensorFlow 2.0 output specification in NLP model

I just started playing with TensorFlow 2.0 now that the new api is out. However, I do not get the model output specification. The model below is a simple example ...
0
votes
1answer
22 views

Class Imbalence Problem even after Balancing Data

So I am training a neural network on a binary classification problem and my Case (1) and Controls (0) were imbalanced so I oversampled my cases so that that the training set was 0.5053 made up of ...
0
votes
1answer
754 views

Why are weights being used in (generalized) dice loss, and why can't I? [closed]

Generalized dice loss is advocated as optimizing mIoU directly in semantic segmentation problems (especially those with a severe class imbalance), as opposed to other loss functions like multinomial ...
1
vote
0answers
106 views

How do I set up my hyper-parameter space for optimizing a convolutional neural network (using packages Skopt and Tensorflow)

I just finished building a 1D CNN using TensorFlow, and I want to optimize a variety of hyper-parameters using Scikit-Optimize (skopt) (although, I would be willing to use whatever optimization ...
1
vote
1answer
35 views

Meaning of Graph from tensorBoard

Can someone please help me to interpret the graph from tensorBoard. I have attached the screenshot herewith.
1
vote
0answers
21 views

Reference for Inception-v2

Cross-posted from Data Science StackExchange. The "Rethinking" paper doesn't describe the actual implementation of the Inception-v3 model in Tensorflow: an accurate description is written in model....
1
vote
0answers
23 views
0
votes
1answer
64 views

How to handle timeseries extremes (sigma > 20) in deep learning?

I'm using 16-channel, 400-Hz, standardized EEG data to train CNN-LSTM for seizure classification. The data contains $O(3)$ sigma > 20 points, rarely thousands in a ...
0
votes
1answer
686 views

Is there a way to implement something like sklearn's GridSearchCV for Tensorflow estimators? [closed]

Grid Search CV works fine for sklearn models as well as keras, however do we have any alternative for this specifically for tf estimators? Would be great if someone can guide in right direction
3
votes
0answers
188 views

How to reduce impact of false positive images in Tensorflow Object Detection Framework?

I am training a single object detector(for car) with Faster R-CNN with Inception v2 config file. I started with around 300 examples of images of the object with bounding boxes and trained that, got ...
1
vote
0answers
465 views

Many false positives in a custom SSD model with Tensorflow object detection API

My model has 2 classes (no background class) and is trained using transfer learning with ssd_mobilenet_v2_coco. It detects and classifies well the objects it was trained on. However, on new images it ...
1
vote
1answer
259 views

Softmax with Cross Entropy optimization vs Backpropagation

I am following a tutorial from Analytics Vidhya on creating a neural network to recognize handwritten digits (the classic example). The code from the tutorial states "First we need to define the ...
1
vote
1answer
188 views

Reproducible numbers in Keras/TensorFlow

Every time I run a Keras/TensorFlow code gives different results. Can someone suggest how to get reproducible numbers?
-2
votes
1answer
148 views

why the neural network gives me null results? [closed]

I trying to predict some fluid parameters, you will find the data I use in the drive link (24 input and 3 output to predict): DATA. first of all I replaced the null values ​​in the data with the ...
0
votes
0answers
38 views

Holdout loss much worse than training & testing data

I am creating a simple MLP which is to predict a single output based and 9 inputs. The data is scaled between 0 and 1, and the data is shuffled before training. The resulting model leads to very low ...
0
votes
0answers
489 views

Custom TF 2.0 training loop performing considerably worse than keras fit_generator - can't understand why

In trying to better understand tensorflow 2.0, I am trying to write a custom training loop to replicate the work of the keras fit_generator function. In my head, I have replicated the steps ...
0
votes
0answers
45 views

Accuracy of RNN getting stuck after 90% [duplicate]

I am using Keras RNN Cell to perform parts of speech tagging. The architecture is as follows(I cannot put the code because of privacy reasons) : An embedding layer of of 40 units of shape (...
0
votes
1answer
32 views

Training with default BN parameters

Training with default BN parameters in tensorflow I obtain strange loss curve. For experiment train and val are the same dataset. Blue is val loss, orange is train loss. BN with momentum 0.99 (...
1
vote
1answer
255 views

Why is there no Target Value function in PPO?

I just implemented the PPO algorithm in tensorflow and strictly followed the algorithm provided in the original PPO paper by Schulman et. al. 2017 Previously I did some experiments with the DDPG ...
1
vote
1answer
52 views

What type of neural network is used for image to restore pictures from pixels

When we have small low resolution, fuzzy image for example: and if it to zoom, an unrelated set of pixels is obtained. For example Tell me, please is there the way to train a neural network to ...
0
votes
1answer
1k views

why the accuracy of my CNN decreasing after some epochs?

at high accuracy, after some epochs the accuracy as well as validation accuracy is decreasing and got stuck after few more epochs. i dont understand why this happened. does more epochs at some point ...
0
votes
0answers
15 views

faulty autoencoder [duplicate]

I am developing an autoencoder for CIFA10 dataset, without adding noise at the input (which is 2nd goal). The Convnet based autoencoder is not converging: Any suggestions ...
1
vote
1answer
45 views

What does linear regressor output mean? I am using tensorflow estimator in R

I try the code at tensorflow in R tutorial (https://tensorflow.rstudio.com/tfestimators/) but I cannot understand the output what the code produces. Code: ...
0
votes
0answers
35 views

Machine Learning: Model doesn´t recognize letters but has 80% accuracy

I have build a model to classify numbers and characters on Images. I trained it on the Chars74K dataset and in training it has 80% validation accuracy. I just use the number and uppercase characters ...
2
votes
1answer
80 views

Creating a neural network that can make a decision with optional arguments

I'm a final year computer science student and for my final year project I have to design a neural network to play a little known board game called 'The Downfall of Pompeii'. I have to use ...
2
votes
1answer
193 views

Catastrophic forgetting: Retraining a trained neural network with small data

I have a fully connected deep neural network with 7 hidden layers, which is trained with around 20000 simulated materials data. And we've got a very small measurement dataset (size<200) which ...
0
votes
0answers
34 views

Confusion with Computing Probabilities of a Normal Distribution without the Integral

How does this code is calculating the probability of Normal distribution without calculating the integral ...
0
votes
1answer
94 views
5
votes
3answers
1k views

Why is binary cross entropy (or log loss) used in autoencoders for non-binary data

I am working on an autoencoder for non-binary data ranging in [0,1] and while I was exploring existing solutions I noticed that many people (e.g., the keras ...

1 2 3
4
5
12