All Questions
Tagged with tensorflow neural-networks
40 questions with no upvoted or accepted answers
6
votes
1
answer
118
views
It is possible to use deep learning to give approximate solutions to NP-hard graph theory problems?
It is possible to use deep learning to give approximate solutions to NP-hard graph theory problems?
If we take, for example, the travelling salesman problem (or the dominating set problem). Let's say ...
- 181
4
votes
0
answers
71
views
Why does a neural network struggle to solve this simple problem?
Consider the following problem:
Given a vector x of size dim with values between 0 and 1 (exclusive), determine if ...
- 201
4
votes
0
answers
1k
views
Can we combine multiple different neural networks in one?
I want to make a kind of robotic brain, i.e. a big neural network, which includes an NLP model (for understanding human voice), real-time object recognition system (so that it can identify particular ...
- 41
3
votes
0
answers
258
views
Understanding the TensorFlow implementation of the policy gradient method
I was trying to understand the implementation of a basic policy gradient (REINFORCE) method using TensorFlow.
I think I got almost everything. The only thing that still bothers me is the loss function ...
- 31
3
votes
0
answers
392
views
How do I create a chatbot using tensorflow or pytorch using like the one defined in dialogflow?
How do I create a chatbot using TensorFlow or PyTorch using like the one defined in DialogFlow? What are the best datasets that I can use so to create my own personal assistant like google assistant?
...
3
votes
0
answers
731
views
Getting worse performance when training a pre-trained model with the existing class
I am training pre-trained SSD-InceptionV2-Coco to detect the "car",
which is one of the classes in mscoco label.
I train the model with ~50k sample from KITTI, 500k iteration with batch size 2.
I ...
- 131
2
votes
0
answers
111
views
How to Create a Neural Network Model to Generate Dance Movements Based on Music in MMD Format
I am working on a project where I need to create a neural network model to generate dance movements based on music. My goal is to achieve results similar to this video: https://youtu.be/FrA7f5F9TsI
...
- 21
2
votes
0
answers
53
views
If I want to predict two unrelated values given the same sequence of data points, should I have a model with two outputs or two models?
I want to predict two separate y-values (not really logically connected) based on an input sequence of data (values x). Using LSTM cells.
Should I train two models separately or should I just increase ...
- 181
2
votes
0
answers
25
views
How to handle set-like size agnostic input format
Let's set up some hypothetical simplified scenario: Each instance $i$ of my imaginary dataset $D=\{i_{1}, \ldots, i_{MAX}\}$ has different number $k_{i}$ of $n$-dimensional vectors as input into my ...
2
votes
0
answers
74
views
How should I make output layer of my neural network so that I can get outputs ranging from [-20,-1]
I am trying to make a neural network which takes in 0 and 1 as it's input and should give me output ranging from [-20,-1].I am using three layers with sigmoid as the activation function .How should I ...
- 63
2
votes
0
answers
307
views
Suggestions for Deep Learning for regression on huge 3D volumes
I have a dataset of 3D images (volumes) with dimensions 400x250x400. For each input image I have an output of the same dimensions. I would like to train a machine learning (or deep learning) model on ...
- 53
2
votes
0
answers
28
views
In addition to matrix algebra, can GPU's also handle the various Kernel functions for Neural Networks?
I've read a number of articles on how GPUs can speed up matrix algebra calculations, but I'm wondering how calculations are performed when one uses various kernel functions in a neural network.
If ...
- 131
2
votes
0
answers
59
views
RNN: Different test results on balanced and unbalanced data
I trained a recurrent neural network (if it matters - it contains three CuDNNLSTM cells and 3 Dense layers, Dropout = 0.2). The result of data preparation is one array of ~330.000 sequences. Each ...
- 68
1
vote
0
answers
380
views
what is tfrs.metrics.FactorizedTopK in tensorflow recommenders
from the official documentation link
In our training data we have positive (user, movie) pairs. To figure out how good our model is, we need to compare the affinity score that the model calculates ...
- 11
1
vote
1
answer
166
views
How do you display a neural network
I'm new to tensorflow and ML but am progressing slowly. I know how to look at the weights and biases but am still trying to figure out if there is an easy way to display a neural network in the ...
- 151
1
vote
0
answers
127
views
Hand Landmark Detector Not Converging
I'm currently trying to train a custom model with TensorFlow to detect 17 landmarks/keypoints on each of 2 hands shown in an image (fingertips, first knuckles, bottom knuckles, wrist, and palm), for ...
- 111
1
vote
0
answers
24
views
Neural Network Regression Experiment Going Wrong
I've been trying to get a simple regression experiment going with a neural network and I would like some help interpreting what is going wrong.
My goal is to see what level of regression accuracy I ...
- 111
1
vote
0
answers
146
views
Is it possible to use RGB image with decimal values when feeding training data to CNN?
I am working with four grayscale images of float32 data type to perform regression using Keras. Three images are stacked using np.dstack to form a RGB data-set. The ...
- 11
1
vote
0
answers
42
views
Low accuracy during training for text summarization
I am trying to implement an extractive text summarization model. I am using keras and tensorflow. I have used bert sentence embeddings and the embeddings are fed into an LSTM layer and then to a Dense ...
- 41
1
vote
4
answers
420
views
How to improve neural network training against a large data set of points with varying magnitude
I am currently using TensorFlow and have simply been trying to train a neural network directly against a large continuous data set, e.g. $y = [0.014, 1.545, 10.232, 0.948, ...]$ corresponding to ...
- 61
1
vote
0
answers
57
views
Why does the result when restoring a saved DDPG model differ significantly from the result when saving it?
I save the trained model after a certain number of episodes with the special save() function of the DDPG class (the network is saved when the reward reaches zero), but when I restore the model again ...
- 111
1
vote
0
answers
788
views
TensorFlow fit() and GradientTape - number of epochs are different
if I define the architecture of a neural network using only dense fully connected layers and train them such that there are two models which are trained using model.fit() and GradientTape. Both the ...
- 235
1
vote
0
answers
125
views
What is the correct input shape for my LSTM network?
My professor gave us a workshop where we have to do classification of a dataset of ECG signals between healthy and unhealthy types using LSTM. Each signal consists of 1,285 time steps.
What my prof ...
- 181
1
vote
0
answers
25
views
What are examples of models for traffic sign detection that can be easily implemented?
I'm working on a college project about traffic sign detection and I have to choose a paper to implement it, but I have basic knowledge of TensorFlow and I'm afraid of choosing a paper that I can't ...
- 11
1
vote
0
answers
174
views
Is this TensorFlow implementation of partial derivative of the cost with respect to the bias correct?
I have a neural network for MNIST classification which I am hard coding using TensorFlow 2.0. The neural network has an input layer consisting of 784 neurons (28 * 28), one hidden layer having "...
- 235
1
vote
0
answers
49
views
How could I locate certain words or numbers in a financial statement?
I would like to code a script that could locate a specific word or number in a financial statement. Financial statements roughly contain the same information, they are however not identical and ...
- 11
1
vote
0
answers
120
views
Trying to separate spiral data with neural network, learning tensorflow
I am learning how to use tensorflow without keras, just to make sure I understand tensorflow directly.
I created a spiral-looking datasets with 100 points of each class (200 total), and I created a ...
- 111
1
vote
0
answers
181
views
DQN not able to learn in a game where other agents perform random walks
I am making a school project where I should develop any kind of game where I can have one reactive agent and one agent based on machine learning competing with each other.
My game consists of a ...
- 205
1
vote
0
answers
56
views
How to create a task-graph based neural network?
I'm trying to design a neural network with a task hierarchy. This is my idea so far:
...
- 2,246
1
vote
0
answers
209
views
Trajectory classification using RNN
The problem: I want to classify a trajectory if it has some properties, for example I want to create a simple 0/1 classifier for circular trajectories. If a target is moving in a circular trajectory ...
- 111
0
votes
0
answers
34
views
Predict more elements than the input
I can use any machine learning algorithms (but neural networks are better for me) to resolve this issue: use few elements as input (numerical) to predict more elements as output. In normal regression ...
- 101
0
votes
0
answers
13
views
Help With Converting NumPy Function To TensorFlow Ops (graph execution issue)
I'm trying to export my command recognition model for deploymenet on embedded devices, however, I'm facing trouble when trying to encapsulate the preprocessing function into my model, that way, when I ...
0
votes
1
answer
122
views
How do I input multi-channel Numpy array to U-net for semantic segmentation
I had lidar 3D point cloud data from semantckitti. I want to perform Semantic Segmentation on the data using U-Net. I converted the 3d point cloud data into 2D using spherical conversion and saved the ...
0
votes
0
answers
101
views
Why Is There The Term 1/m In Backpropagation
In backpropagation the gradients are used to update the weights using the formula
$$w = w - \alpha \frac{dL}{dw}$$
and the loss gradient w.r.t. weights is
$$\frac{dL}{dw} = \frac{dL}{dz} \frac{dz}{dw} ...
- 31
0
votes
0
answers
59
views
Is the graph considered as overfit?
I have a training dataset of 2000 images and 500 images for validation. I have executed 50 epochs, however I realized that my graph seems to be different as my accuracy is smaller than my loss. I am ...
- 1
0
votes
0
answers
26
views
Training a sequential model that can only evaluate after several hundred cycles
I'm attempting to build a neural network to play the card game, Lost Cities.
A brief overview of the game:
The game involves two players taking turns to play cards on expeditions.
Expeditions incur a ...
0
votes
0
answers
462
views
Is it possible to transform audio with neural networks to make it sound like 3d sound
so the idea is to feed neural network data like
input: mono audio(extracted from existing 3d audio) output: 3d audio
after training it should convert mono audio to 3d sound
do you think it is possible?...
- 21
0
votes
1
answer
893
views
Why won't my model train with CTC loss?
I am trying to train an LSTM using CTC loss, but the loss does not decrease when I train it. I have created a minimal example of my issue by creating training data where the network simply has to copy ...
- 101
0
votes
0
answers
184
views
How GAN generator produce integer RGB colored picture?
For traditional neural networks, I know that we can't constraint the output to be strict integers. My question is what technique does GANs use to produce integer outputs, that can be then converted to ...
- 197
-1
votes
1
answer
135
views
Exploration for softmax should be binary or continuous softmax?
Maybe it's silly to ask but for random exploration in an RL for choosing discrete action, that in the neural network last layer softmax will be used, what random samples should we provide? binary like ...
