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
0
votes
0answers
42 views

Where are the Graphs in TensorFlow 2?

In TensorFlow 1.X we had very explicit access to the computation graph with tf.get_default_graph() or explicitly work with one of our choice from the start. We ...
0
votes
0answers
27 views

Increase dimension of RNN LSTM cell in Keras

I want to increase amount of recurrent weights in rnn or lstm cell. The idea is that RNN neuron takes prevois output as input. I want to increase amount of previous values taken as input. If you ...
1
vote
0answers
92 views

Keras multi-gpu seems to heavily load one of the cards

I'm using Keras (tf backend) to train a neural net; I'm accelerating with GPUs using the multi gpu options in Keras. For some reason, the program seems to heavily load one of the cards and the others ...
0
votes
1answer
259 views

How do Bahdanau - Luong Attentions use Query, Value, Key vectors?

In the latest TensorFlow 2.1, the tensorflow.keras.layers submodule contains AdditiveAttention() and ...
3
votes
1answer
35 views

Why are the weights of my first layer and last layer in the CNN change while the middle layers don't?

The weights of my first and last convolution layers do change in a noticeable way. However, the rest of my convolution layers, in the middle, do not. I should add that all convolution layers' biases ...
2
votes
0answers
19 views

Training pipelines where featurization/NLP is more expensive than backprop

I'm working on a document classification project and I'm using a neural net in tensorflow, where the features are 300-dimensional word embeddings, either from fastext or word2vec (yes I know that ...
0
votes
1answer
34 views

What is Image Annotation?

Why do we need to use Labelimg tool for object detection? After labeling the bunch of training images using labelimg tool which will give CSV file How that CSV file works with TensorFlow object ...
0
votes
1answer
26 views

Constructing an image from a dense layer output

I am trying to reconstruct an image from a dense layer with is a concatenation of outputs from a 1) convolutional network with image inputs; and 2) dense layer with numerical inputs The concatenated ...
0
votes
1answer
117 views

Retraining EfficientNet on only 2 classes out of 4

EfficientNet model was trained on ~3500 images for a 4-class classification: A, B, C and Neither – with accuracy of 0.985 – by someone else, not me. I'm quite new to ML. So we have this model, and it ...
0
votes
0answers
12 views

What is the advantage of Automatic Differentiation over Symbolic or Numerical Differentiation?

I have read that Automatic Differentiation(AD) is comparatively faster to optimize the learning rate of a model. But what is AD's advantage over Symbolic Differentiation or Numerical Differentiation?
0
votes
0answers
18 views

Are these images too 'noisy' to be correctly classified by a CNN?

I'm attempting to build an image classifier to identify between 2 types of images on property sites. I've split my dataset into 2 categories: [Property, Room]. I'm hoping to be able to differentiate ...
0
votes
0answers
48 views

Multiple GRU layers in TensorFlow 2

I have some TensorFlow 1 code which implements a GRU layer, and I am updating it to TensorFlow 2. So instead of the hand-written layer iterating over timesteps with a GRUCell I am using the in-built ...
1
vote
0answers
29 views

Transfer learning from saved frozen graph

Using tensorflow graph (core tensor api's), I have trained a model and saved as a frozen graph. As a part of transfer learning, I want to use these trained layers and extend my ML network with some ...
0
votes
0answers
23 views

Is tensorflow provide object tracking api with detection?

I am using the TensorFlow object detection API to detect the person. I have one more use case to track a person. Is there any possibility to achieve this using TensorFlow object detection API or they ...
0
votes
2answers
19 views

How can we utilize the TensorBoard

I tried the sample code form the link below. https://www.tensorflow.org/tensorboard/get_started It pretty much worked fine; just had to make a couple tweaks to get it working on my machine. I was a ...
3
votes
0answers
95 views

How to detect vanishing and exploding gradients with Tensorboard?

I have two "sub-questions" 1) How can I detect vanishing or exploding gradients with Tensorboard, given the fact that currently write_grads=True is deprecated in the Tensorboard callback as per "un-...
0
votes
1answer
59 views

Negative examples for a Yes/No image classification neural network

I'm trying to retrain a neural network using transfer learning that can classify whether an image has a certain object, say, a car. My positive sample dataset is quite small, only 2500~ images. It ...
0
votes
0answers
15 views

Implementing a Full-Feed-Forward (Cascading Feed Forward) Network in Tensorflow

About I am currently trying to reimplement a paper I read about neural net cryptanalysis. The paper claims to use a 128-256-256-128 Cascade-Feed-Forward net for cryptanalysis of DES. I think the term ...
0
votes
1answer
25 views

why we need data labelling tool for computer vision?

Before start training images with tensorflow object detection api we need to use labelling tool to annotate our images and converted to XML format. What happens when we convert our annoted image to ...
0
votes
2answers
1k views

Getting TypeError: expected bytes, Descriptor found while importing tensorflow

I am trying to use tensorflow and keras for one of the tasks but while importing the tensorflow I am getting the below error. Till now I have removed the virtual which I have created previously and ...
0
votes
1answer
74 views

How to create a model to recognize matching label and ROI with OCR

I am trying to make a model in python using Tensorflow to process the Tesseract OCR to detecting and extracting particular ROI from Image. I want to recognize the particular fields and values from ...
1
vote
0answers
22 views

MinMaxScaling vs L1/L2-Normalization

I'm wondering about the difference or the application of the different types of rescaling data. So far, I'm aware that standardization assumes the data has a gaussian distribution. So if this is the ...
1
vote
1answer
219 views

Using Tensorflow object detection API vs Keras

I am new to machine learning. I am curious to know what is the difference between using Keras instead of TensorFlow object detection API. We need to manually configure hidden layers and input layer in ...
1
vote
0answers
27 views

How can I get the predict future following value using Tensorflow LSTM?

Thank you for reading. I'm not good at English. I am wondering how to predict and get future time series data after model training. I would like to get the values after N steps. So, I used the time ...
0
votes
0answers
24 views

Dynamic sequence length in Keras LSTM layer

I'm implementing an LSTM with Keras to predict the correct words order. My dataset is composed by sentences, each sentences is ...
0
votes
0answers
77 views

Indexing tensors in custom loss function with Keras

I'm using a custom loss function in Keras. This is the function: ...
1
vote
0answers
13 views

How can I do a sequence to sequence model (RNN / LSTM) with Keras with fixed length data?

What I'm trying to do seems so simple, but I can't find any examples online. First, I'm not working in language, so all of the embedding stuff adds needless ...
1
vote
1answer
25 views

Distributed DL model with Tensorflow

Suppose I want to develop and train a big end-to-end deep learning model using Tensorflow (1.15, for legacy reasons). The objects are complex, with many types of features that can be extracted: vector ...
2
votes
1answer
138 views

How to get sentence from embedding vector with Universal Sentence Encoder?

I'd like to ask, if there is possibility to get sentence (or word) from embedding vector using Universal Sentence Encoder? First of all, I've clustered my embedded sentences and I've got a vector ...
0
votes
0answers
23 views

How does one apply a arbitrary map to a TensorFlow tensor?

BACKGROUND Consider the following code ...
0
votes
0answers
17 views

Is there a function that could find slope of a curve ignoring peaks?

Let's say I obtained a timeserie (in blue) (with some missing data) that is (as far as i understood) : - following a general trend between specific points - more or less cyclic I have drawn the red ...
0
votes
1answer
50 views

How to label images for CNN use as classifier

I have theorical question that I couldnt decide how to approach. I have tons of grayscaled shape pictures and my goal is seperate these images to good printed and bad printed. For this, I look at ...
0
votes
0answers
53 views

Custom training loss with custom gradients

I am trying to write a custom loss in Tensorflow v2, for simplicity let's say that I'm using Mean Squared Error loss as follows, ...
0
votes
0answers
41 views

Can tf.keras.utils.get_file(), be used to load local zip files? [duplicate]

I have zip file containing 4 image folders. The tutorial I followed on Google Colab uses a similar zip file but the file is hosted online and the link is given as the value of ...
0
votes
1answer
15 views

How to know the probability of correctness of a test data in a Binary Classifier

I have written a sequential classifier script using Keras, Tensorflow. Its a binary image classifier that predicts the class, given the directory path of a sample image. I want to implement a ...
0
votes
0answers
93 views

Teachable Machine Object detection

I have a trained an image classification model using teachable machine and can export it in any format. I would like to know if we can train/modify it for object detection i.e. getting bounding boxes ...
2
votes
1answer
83 views

Transfer Learning Question: Extending the Functionality of a Multipose-Estimation Machine Learning Model?

I have experimented with a number of different machine learning models used for pose estimation. Most of them output a heatmap and offsets for the detected person(s) in the image. I really like the ...
0
votes
0answers
10 views

Transfer learning on inference TensorRT model

Is it possible to do transfer learning using an inference model of tensorrt by converting it back into tensorflow?
1
vote
2answers
20 views

Metrics for same signal

Is there a metric in tensorflow.keras.metrics that counts how many time the predicted output and the real output have the same signal? For example, if the ...
0
votes
1answer
69 views

How to support a dynamic shape input for tf.where()

Tensorflow (tf.where) function does not support dynamic input shapes. For example, the following function calculates the svd of a matrix A and tries to identify the singular values greater than a ...
0
votes
1answer
236 views

Does keras' model.fit() remember learning rate when called multiple times?

Let's say I'm using the Adam optimizer, and calling fit() on my model multiple times. What parameters does the fit function remember? From what I've observed, the loss function/metrics seem to ...
1
vote
1answer
764 views

AttributeError: module 'keras.backend' has no attribute 'backend'

Hi I have tensorflow installed of version 1.14.0 on my ubuntu machine. I am trying to run a code with import keras and I get an error ...
0
votes
0answers
23 views

In what form the optical flow data is fed to a 3d cnn model?

I want to create a 2 stream architecture for video classification using keras and tensorflow as its back-end .In this method you basically give 2 types of data to the model.One is the video itself(...
1
vote
0answers
21 views

Why tensorflow saver meta file is getting large?

Far as I know, a meta file for saver is for the information of model like structure and operation. So the file size should be same, but the first meta file size is much smaller than the last meta file....
3
votes
1answer
89 views

tensorflow pseudo inverse doesn't work for complex matrices!

The Tensorflow documentation here says that: tf.linalg.pinv is ''analogous to numpy.linalg.pinv. It differs only in default value of rcond''. However, tf.linalg.pinv requires the matrix to ...
1
vote
0answers
27 views

Keras Encoder - Decoder Model

Im training a model of 400 samples . The dataset contains 400 images of faces as input (X) and also 400 faces with glasses as output (Y) . im training the model by code below : ...
1
vote
1answer
68 views

Is there a difference between tf.nn.conv1d and tf.nn.convolution in Tensorflow?

I want to know what is the difference between a these two. For me, they are the same function, so I do not see the reason of existance two same functions.
2
votes
1answer
72 views

Attention mechanism in Tensorflow 2

In the past days, I read up on the theory behind attention, when to apply it and what types there are. I think I have a decent first understanding of the concept, but now I would like to apply some of ...
3
votes
0answers
26 views

How to encode multiple inputs and multiple outputs

I have a piece of math more complicated than I can understand at the moment, a dynamic graph visualization. It uses a physics metaphor of springs and magnets, where the vertices act as magnets ...
2
votes
0answers
20 views

Why does this implementation of SimpleNet use 3x3 kernels on it's final layer for cifar10?

Question; I'm trying to implement simplenet in tensorflow and I have a question that I can't seem to answer myself. The implementation I'm basing this off of is here: https://github.com/Coderx7/...

1
4 5
6
7 8
30