Questions tagged [tensorflow]
For questions related to Google's open-source library for machine learning and machine intelligence. However, note that programming questions are off-topic here.
156 questions with no upvoted or accepted answers
1
vote
0
answers
26
views
Why Acme is using own uniform initializer?
Why is Acme using own initializer for both tanh and ELU, when commonly used for tanh is Xavier and for ELU is He initializer? What mathematics is behind them?
Here is the code.
...
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
1
answer
159
views
What could cause the hamming loss and subset accuracy to get stuck in a multi-label image classification problem?
I am rather new to deep learning and got some questions on performing a multi-label image classification task with keras convolutional neural networks. Those are mainly referring to evaluating keras ...
- 11
1
vote
0
answers
954
views
What would be the advantage of making channel dimension first in TensorFlow Keras implementation?
I was reproducing the findings of a research article in which I discovered that they had switched the Channel dimension from last to first. To clarify this concept, I went through A Gentle ...
- 41
1
vote
0
answers
137
views
Would the reward normalization be wrong in early episodes?
It's confusing me that how can we normalize the reward without actually knowing the true mean and variance of the reward distribution, specifically, at the early steps and episodes. This may cause ...
1
vote
0
answers
144
views
How to deal with images that do not contain any object of interest?
I'm currently working on an iOS App where I want to detect if there is a table, chair or bench in the current camera input.
My idea was to take the MobileNetV2 model and get it to classify these three ...
- 11
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
140
views
Is a true RNN auto encoder possible with Keras/TF
I want to get some encodings for temporal data (with a highly varying number of timesteps).
The dataset is of the format: ...
- 141
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
378
views
DQN Agent with a 2D matrix as input in Keras
I have a Reinforcement Learning environment where the state is a 2D matrix with 0s and 1s (only one column with the value of 1 in each row).
Example:
...
- 206
1
vote
0
answers
163
views
How to design my Neural Network for Game AI
For my school project, I have to develop an agent to play my game.
The base I have is a 'GameManager' which call 2 AIs, each taking a random move to do.
To make my AI perform, I decided to make a ...
1
vote
0
answers
149
views
How to design an observation(state) space for a simple `Rock-Paper-Scissor` game?
For weeks I've been working with this toy game of Rock-Paper-Scissor. I want to use a PPO agent learn to beat a computer ...
- 111
1
vote
0
answers
210
views
Keras model accuracy not improving beyond threshold
I am currently working on a public project for the National Weather Model. We are experimenting with using a recurrent neural network to replace the output of a quadratic formula that is in use. The ...
1
vote
0
answers
128
views
Embedding Layer into Convolution Layer
I'm looking to encode PDF documents for deep learning such that an image representation of the PDF refers to word embeddings instead of graphic data
So I've indexed a relatively small vocabulary (88 ...
- 131
1
vote
0
answers
1k
views
How to compare SegNet, U-Net and EfficientNet?
SegNet and U-Net are created for segmentation problem and EfficientNet is created for classification problem. I have a task and it is saying that train these models on the same dataset and compare ...
- 121
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
0
answers
42
views
Trying to Train Cards Game with RL
I am trying to train a card game called Callbreak I tried inputs like all the opponents discarded cards all hands everything a human can see and calculate with "common sense" I fed it to the Agent but ...
1
vote
0
answers
58
views
Why does this tutorial on reinforced learning not check whether the environment is 'game over' during training?
I am following the tutorial Train a Deep Q Network with TF-Agents. It uses the hello world environment of reinforced learning: cart pole.
At the end, the agent is ...
- 153
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
242
views
How can I use GPT-2 to modify seed text of one form into a different form (LENGTH INVARIANT) whilst retaining meaning?
I am currently starting a research project whereby I am trying to convert text of one form into another.
i.e. If I were to write a seed sentance of the form "Scientists have finally achieved the ...
- 111
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
1
answer
278
views
How to handle extremely 'long' images?
After transforming timeseries into an image format, I get a width-height ratio of ~135. Typical image CNN applications involve either square or reasonably-rectangular proportions - whereas mine look ...
1
vote
0
answers
69
views
Neural Network Results always the same
I have a GRU model which has 12 features as inputs and I'm trying to predict output power. I really do not understand though whether I choose
1 layer or 5 layers
50 neurons or 512 neuron
10 epochs ...
- 123
1
vote
0
answers
45
views
How to deal with features which are here just for training?
I'm new to the Data Science field and last week I started to learn about Neural Networks and Deep Learning. To practice, I decided to do a small project: design a Neural Network to predict the winner ...
- 111
1
vote
0
answers
21
views
Irregular results while prediction identical object on same image
I used the pre-trained model faster_rcnn_resnet101_coco.config with my own dataset.
I have two issues
some objects were not detected, while I learned it, with a high number of steps, and test over ...
- 11
1
vote
0
answers
68
views
Training an unsupervised convolutional neural network to learn a general representation of a Lua module
I am trying to train a CNN in keras to learn a general representation of a Lua module, e.g. requires at the beginning, local variables, local functions, interface (returns) and in between some ...
- 151
1
vote
0
answers
221
views
Simple sequential model with LSTM which doesn't converge
I'm actually trying to create a sequential neural network in order to translate a "human" sentence in a "machine" sentence understandable by an algorithm. Like It didn't work, I've try to create a NN ...
- 11
1
vote
0
answers
125
views
Error when using tensorflow HMC to marginalise GPR hyperparameters
I originally posted on SO (original post) but was suggested to post here.
I would like to use tensorflow (version 2) to use gaussian process regression to fit some data and I found the google colab ...
- 11
1
vote
0
answers
24
views
Is there a way to use RNN (in tensorflow) to do something like a batch Kalman with the weight dynamics specified in the loss?
Or would you simply do this as a time series of models.
Basically I think you can think of time series of weights as the hidden states and the dynamics driving the weight time series as the RNN ...
- 141
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
734
views
Reasoning behind $Zero$ validation accuracy in the following ResNet50 model for classification
I have written this code to classify Cats and dogs using Resnet50. Actually while studying I came to the conclusion that Transfer learning gives very good accuracy for deep learning models, but I ...
- 11
1
vote
0
answers
35
views
Can't figure out what's going wrong with my dataset construction for multivariate regression
TL;DR: I can't figure out why my neural network wont give me a sensible output. I assume it's something to do with how I'm presenting the input data to it but I have no idea how to fix it.
Background:...
- 19
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
83
views
Can mobilenet in some cases perform better than inception_v3 and inception_resnet_v2?
I have implemented a multi-label image classification model where I can choose which model to use, I was surprised to find out that in my case mobilenet_v1_224 performed much better (95% Accuracy) ...
- 125
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
1
answer
136
views
Indoor positioning with variable number of distance measurements in tensorflow
Currently I have a setup where I'm determining the position of a transmitter using the RSSI of 4 receivers. Its a simple feed-forward network with some hidden layers, where the input is the RSSI ...
- 61
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
49
views
Dynamic frames processing with CNN LSTM combination or otherwise
I have a unique implementation where I have to process videos with dynamic frame rates (that is the number of frames is different for each video in a batch). I am stacking all the frames in a single ...
- 111
1
vote
1
answer
919
views
Problem over DQN Algorithm not converging on snake
I'm using a DQN Algorithm to play Snake.
The input of the neural network is a stack of 4 images taken from the games 80x80.
The output is an array of 4 values, one for every direction.
The problem ...
- 127
1
vote
0
answers
496
views
How are the attention weights normalised in the transformer?
In the Transformer (adopted in BERT), we normalize the attention weights (dot product of keys and queries) using a softmax in the Scaled Dot-Product mechanism. It is unclear to me whether this ...
- 131
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
35
views
Using two generative adversarial nets to classify articles - what is a good approach?
I'm trying to create a deep learning network to classify news article based on the text and associated image. The idea comes from a novel use of GANs to classify based on generated data.
My approach ...
- 119
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
1
vote
0
answers
249
views
Transfer learning from model trained in a similar dataset
I am currently working on a defect detection algorithm but I only have a few samples of defects.I googled for defect detection datasets and I found this one:
http://resources.mpi-inf.mpg.de/...
- 121
0
votes
1
answer
20
views
How to Resolve Matrix Size Mismatch in TensorFlow Model Builder for Combined Text and Numeric Inputs?
I'm working on a Keras model using the Functional API that processes two inputs:
Text Input: A padded integer array with a shape of (32, 1149) (batch size 32, sequence length 1149). Example: [5, 10, 3,...
0
votes
0
answers
25
views
How to Implement a Custom TensorFlow Layer to Apply CLAHE on an Image?
I am trying to implement a custom TensorFlow layer to apply Contrast Limited Adaptive Histogram Equalization (CLAHE) on an image. I have written the following code, but I am not sure if it is correct ...
0
votes
0
answers
19
views
My CNN validation Accuracy increases super slow?
im doing a retinopathy detection project with over 3500 images, 700 in each class. I've filtered the image like
It seems that my model isn't learning from the data, or is having trouble because the ...
- 1