Questions tagged [tensorflow]

TensorFlow is an open source library for machine learning and machine intelligence. TensorFlow uses data flow graphs with tensors flowing along edges. For details, see https://www.tensorflow.org. TensorFlow is released under an Apache 2.0 License.

Filter by
Sorted by
Tagged with
4
votes
1answer
5k views

Tensorflow and OpenCV real-time classification

I am testing the machine learning waters and used TS inception model to retrain the network to classify my desired objects. Initially, my predictions were run on locally stored images and I realized ...
3
votes
1answer
753 views

multiple digit detection

this question is about detection of a number having multiple digits in a single image. i have a trained model in tensorflow using Deep CNN for image recognition. the training was done on cropped ...
0
votes
1answer
2k views

why is the model prediction output in keras lstm imdb, a vector?

If you run the example of the LSTM sentiment classification task example in keras https://github.com/fchollet/keras/blob/master/examples/imdb_lstm.py and add ...
0
votes
1answer
761 views

tensorflow saved model to java

Hello data scientists (I'm not), I adapted a multi-class-text-classification-cnn from https://github.com/jiegzhan/multi-class-text-classification-cnn (thanks Jie Zhang) It works ! 90% accuracy ! Now ...
2
votes
0answers
670 views

Tensorflow - uninitialized variable under tf.cond(…)

I have an problem with tensorflow. I created a class for fully-connected layer with parameter in its constructor is_hidden_layer by which I decide to use or not to ...
3
votes
1answer
850 views

Evaluating Logistic Regression Model in Tensorflow

Following this tutorial, I have a doubt about the evaluation part in: ...
2
votes
0answers
439 views

Are there pretrained models on the ImageNet Bounding Boxes dataset?

When searching for some pretrained models for object detection with bounding boxes, I was wondering if there are also pretrained models on the ImageNet dataset for bounding boxes. Most of the time, I ...
0
votes
1answer
884 views

Retraining last layer of inception

...
4
votes
1answer
167 views

How to determine if a neural-network has a static computation graph?

I'm looking at implementing some neural networks from research papers. However, I'm concerned about which framework I should use, because I'm uncertain if the networks form static computation graphs (...
1
vote
1answer
1k views

Bahdanau Attention

In the original paper, the author says that the annotation are the concatenation fo the forward states and the backward states at each time step. In the tensorflow implementation (memory param), the ...
1
vote
1answer
910 views

Is cross-entropy a good cost function if I'm interested in the probabilities of a sample belonging to a certain class?

I'm training a neural network that, for each of six classes, tries to predict the probability that a sample belongs to it. After that, I want to use these probabilities as fractions of the sample ...
0
votes
1answer
152 views

Connection between the first pooling layer and the second convolutional layer

This is a follow-up question regarding this question. I managed to verify in python that the output of the first pooling layer will be a $14 \times 14\times 32$ ...
1
vote
0answers
192 views

Training ImageNet classifiers with keras on multi-channel images

I was wondering if it's possible to train any of the ImageNet classifiers on arbitrarily shaped data. In my case each "image" that I'd like to classify is a collection of NxMxK arrays. Here K would be ...
0
votes
1answer
4k views

A practical reason to use Cross-entropy as a error-function in Neural networks?

Cross-entropy tends to allow errors to change weights even when nodes saturate (which means that their derivatives are asymptotically close to 0.) Link Why is the above statement true? Figures ...
1
vote
3answers
5k views

Predict sinus with keras feed forward neural network

I have a very simple feed forward neural network with keras that should learn a sinus. Why is the predictive power so bad and what is generally the best way to pinpoint issues with a network? In the ...
12
votes
4answers
13k views

Detecting anomalies with neural network

I have a large multi dimensional dataset that is generated each day. What would be a good approach to detect any kind of 'anomaly' as compared with previous days? Is this a suitable problem that ...
0
votes
1answer
570 views

Tensorflow ArgumentError: argument --model_dir: conflicting option string: --model_dir

I am trying to execute this Tensorflow tutorial https://github.com/tensorflow/tensorflow/blob/r0.12/tensorflow/examples/learn/wide_n_deep_tutorial.py but I have the following error: ArgumentError: ...
1
vote
0answers
796 views

Tensorflow Training Time Estimates

When I build models and before I train them, I have the habit of estimating the training time to make sure it is reasonable. This usually comes in the form of my naive estimate, training hours = ...
2
votes
1answer
1k views

Tensor Decomposition in TensorFlow for multinomial time series dimensionality reduction

I'm doing unsupervised learning (clustering and DR) on multinomial time series. I need to reduce dimensions for my data, which is sparse and has a lot of dimensions. I realized that some form of ...
2
votes
2answers
584 views

Linear Model to generate probability of each possible output

This is related to Sports prediction (Cricket). I am new to Machine Learning and learning it through TensorFlow. I am focusing only on one topic which is "How many runs ...
23
votes
3answers
43k views

What is weight and bias in deep learning?

I'm starting to learn Machine learning from Tensorflow website. I have developed a very very rudimentary understanding of the flow a deep learning program follows (this method makes me learn fast ...
0
votes
1answer
592 views

Training LSTM Recurrent Network in TensorFlow

I have trained RNN's before "by hand" using basic tools like Numpy or BLAS, but I am having trouble getting a simple RNN to converge in TF. Full Code I tried standard things like adjusting the ...
0
votes
1answer
2k views

Feature Extraction from Concolutional neural network (CNN) and use this feature to other classification algorithm

As in this the author is using CNN to extract features of the images. And then doing SVM for further analysis. My question is how to extract features in CNN? E.g. Here is a CNN code I'm using: ...
1
vote
1answer
311 views

how to train tensorflow chat application on updated dataset everyday

I have created chatbot on Cornell movie dataset and it's working fine. I have trained chatbot application up to global step 330000. I am using tensorflow library. I am using ||source|| chatbot. I am ...
0
votes
1answer
2k views

Attempt to reuse RNNCell with a different variable scope

I'm using Tensorflow 1.1.0 with GPU support and I have this function: ...
-1
votes
1answer
70 views

What are the differences between IBM BlueMix and IBM Data Science Experience?

This may seem like a silly question, but as I am going through the documentation for both services it is difficult to disentangle what each does, specifically. From what I've gathered BlueMix is ...
2
votes
1answer
894 views

Improve classification accuracy on Iris data set - tf.contrib.learn Quickstart tutorial

I run through the Quickstart tutorial of the tf.contrib.learn, which uses the Iris data set. After training the DNN model I get an accuracy of ~0.967. In an attempt to improve the accuracy, I tried ...
1
vote
2answers
634 views

time series prediction using LSTM

Hi I have fairly very short time series data. The data set has number of systems $s_{1}, s_{2}, s_{3},..s_{n}$. For each $s_{i}$ we have recorded number of failures on each day. As of now, we have ...
3
votes
1answer
548 views

Understanding the training phase of the tutorial “Using Keras and Deep Deterministic Policy Gradient to play TORCS” tutorial

I am trying to understand the training phase of the tutorial Using Keras and Deep Deterministic Policy Gradient to play TORCS (mirror, code) by Ben Lau published on October 11, 2016. The tutorial ...
6
votes
2answers
17k views

What is the best hardware/GPU for deep learning? [closed]

What is the best GPU for deep learning currently available on the market? I've heard that Titan X Pascal from NVidia might be the most powerful GPU available at the moment, but would be interesting ...
1
vote
1answer
44 views

Creating an Artifical Neural Network that produces a set of possible outputs

I'm new to machine learning, and was working on creating an ANN which would classify each observation to a certain value. I have worked primarily with the sigmoid function up to this point to get the ...
4
votes
1answer
2k views

Are CNNs best approaches to find and count objects in images?

I'm starting my first real data-science project, I made a reserach and want to ask if my approach is correct: I HAVE: 600 photos of electronic components, hundreds of components in a single ...
1
vote
1answer
2k views

How to build a model which can predict the probability of an event based on a set of timeseries data?

I am trying to build a deep learning neural model using keras and tensorflow which can predict if a certain event will occur based on a set of timeseries data and some fixed data together . For ...
2
votes
1answer
2k views

How to create a multi-dimensional softmax output in Tensorflow?

I came across this research paper released by YouTube, on how they use deep learning neural networks for recommendations. It's located here: https://static.googleusercontent.com/media/research.google....
0
votes
1answer
430 views

Adding document vector doc2ec to seq2seq model

In general we use word2vec for word embedding in seq2seq model, is it possible to add the document vector from Doc2vec with the input words , I mean using the tag of the document as a word and its ...
1
vote
1answer
1k views

MNIST Deep Neural Network using TensorFlow

I have been working on this code for a while and it gave me a lot of headache before I got it to work. It basically tries to use the mnist dataset to classify handwritten digits. I am not using the ...
0
votes
1answer
468 views

State of the art for Object detection/image recognition

I was asked to verify the feasibility for solving a particular problem: recognizing for a fashion brand the model of its products. I have little experience with image recognition in general, I ...
1
vote
2answers
1k views

Getting low accuracy on keras pretrained word embeddings example

Original blog post claims that it is possible to get 95% accuracy on the validation set (20 Newsgroup dataset) after only 2 epochs using pretrained word embeddings (glove.6B.100d). All code is located ...
2
votes
1answer
934 views

Understanding Imagenet training

I am trying to start training Imagenet classification training using Tensorflow's inception model. I am a bit confused as I am not sure how to fully train the model. Wherever I go everyone seems to ...
2
votes
1answer
6k views

How can I implement deconvolution on CNN (TensorFlow)?

I'm new in tensorflow and machine learning. Could you explain me how implement deconvulation on this CNN model(http://www.wildml.com/2015/12/implementing-a-cnn-for-text-classification-in-tensorflow/) ...
5
votes
3answers
2k views

Binary classification of similar images with small region of interest

I have a dataset of microscope images and I want to train a ML/DL algorithm to perform binary classification. The positive class is when there is only one cell in the image, and the negative class is ...
1
vote
1answer
130 views

Tensorflow / Deepmind: how do I take actions from observations for math algorithms related to proofs?

Crossposted from: https://stackoverflow.com/questions/42809054/tensorflow-deepmind-how-do-i-take-actions-from-observations-for-math-algorith This question is to ask for directions/suggestions/help on ...
0
votes
1answer
458 views

TensorFlow with Phonegap

I'm new into the ML Scene and I want to create a phonegap app involving Tensorflow but I'm unsure where to start or if this is even possible. Can anyone give me a hand (Probably by linking me to some ...
23
votes
4answers
34k views

Using TensorFlow with Intel GPU

I am a newbie in deep learning. Is there any way now to use TensorFlow with Intel GPUs? If yes, please point me in the right direction. If not, please let me know which framework, if any, (Keras, ...
4
votes
1answer
2k views

Input Pipeline for Tensorflow on GPU

The tensorflow example CIFAR10 uses input pipelines to load data from the disk to a queue. I would like to implement this for my own models, but I run into an error that I can't fix somehow. My ...
7
votes
1answer
6k views

How to user Keras's Embedding Layer properly?

I'm a bit confused the proper usage of Embedding layer in Keras for seq2seq purpose (I'd like to reconstruct the TensorFlow se2seq machine translation tutorial in Keras). My questions are the ...
2
votes
2answers
9k views

Fine-tuning a model from an existing checkpoint with TensorFlow-Slim

I'm trying to retrain the final layer of a pretrained model with a new image dataset using TensorFlow-Slim. Lets say I want to fine-tuning inception-v3 on flowers dataset. Inception_v3 was trained ...
21
votes
2answers
25k views

How to deal with string labels in multi-class classification with keras?

I am newbie on machine learning and keras and now working a multi-class image classification problem using keras. The input is tagged image. After some pre-processing, the training data is represented ...
5
votes
1answer
637 views

tensorflow in production

I am using tensorflow-serving to write a server to consume models in production. I have a question about consuming the service by clients: does tensorflow-serving support a REST API? Is there is ...
1
vote
1answer
313 views

Retrain final layer of Inception model

I'm trying to retrain Inception model final layer for a binary classification. My training image set contain 2000 images in class 1 and more than 6000 images in class 2. Will this huge difference in ...