All Questions
Tagged with convolutional-neural-networks keras
61 questions
0
votes
2
answers
64
views
How do I improve my model accuracy and val_accuracy for my cnn model?
I'm using 3000+ retinopathy images in my CNN model. The accuracy remains around 77 to 80, how do i improve the accuracy value and reduce loss value?
I've tried dropout and Adam optimizer to increase ...
- 1
0
votes
0
answers
24
views
Why can't I replicate the validation loss from a Keras tuner (LSTM)
I feel like I'm doing a pretty straightforward sequence of tasks and must be making a simple mistake - I simply build a sequential model, tune it, build a clone of the optimal model by extracting the ...
- 101
0
votes
0
answers
14
views
weighted multi class classification
i'm working on a multi class classification problem which classifies jellyfish and plastic pollution so basically i have 6 classes (barrel_jellyfish, compass_jellyfish, lions_mane_jellyfish, ...
- 1
0
votes
0
answers
41
views
How can I process financial stock data before passing it to an LSTM for time series classification?
I'm trying to make an LSTM that can classify the next day of a stock as either 1 or 0 for going up or down. The issue I've been having is that Keras tuner seems to stay at a constant value of val_loss ...
0
votes
0
answers
7
views
Design approach for image classification regarding genders
I am new to the world of AI and wanted to ask your guidance on how to design a ML model to classify genders based on images.
There will be only one person in the image.
The person could be kids, ...
- 25
0
votes
1
answer
128
views
Transfer learning using pretrained tensorflow object detection model [closed]
I am new to AI/ML and wanted to seek guidance as I am totally lost. I will simplify my issue as follows:
Let's say I would like to detect apples and oranges in images.
I would like to leverage a pre-...
- 25
2
votes
1
answer
215
views
How can I tell a CNN to ignore nodata values in satellite images?
I'm trying to train an image segmentation model on satellite images. There are two main issues: first, not all of the images are the same size. My understanding is that by using a fully convolutional ...
- 21
1
vote
2
answers
68
views
Which type of neural network to use to classify data by which equation most likely generated it?
Problem Summary: Identify which equation a set of data was most likely generated from
Problem Description: Let's say I have two different equations that are functions of variables X and Y and ...
- 143
1
vote
0
answers
44
views
Loss Function for Binary Classification with Multiple Correct Choices
I have a binary classification problem, where there are multiple correct predictions, however, I would consider the prediction to be correct if the highest confidence prediction of a 1 is correct.
I ...
- 11
0
votes
1
answer
264
views
What data can I obtain from CNN model (H5 file)? [closed]
I created a CNN model and it is saved in h5 format. I used the Netron app, where I obtained the model architecture, however ...
- 103
1
vote
1
answer
3k
views
keras model accuracy not improving
I am trying to do multi class(16) classification, however no matter what parameters or number of layers I use my accuracy is not improving, its in 30s the max I got was 43.
I have tried early stopping ...
- 11
-1
votes
1
answer
191
views
Denoise autoencoder not training properly [closed]
I'm trying to make a denoise autoencoder wherein the encoder part is vgg16 and decoder is opposite of vgg16(encoder) network. My dataset consists of 5K images in grayscale.
Now while training, the ...
1
vote
2
answers
302
views
Are these book example CNN results realistic?
I've been following a deep learning book and the current section I'm on is about convolutional neural networks. The author presents some code to create a basic CNN with about 1 million parameters, ...
- 21
2
votes
2
answers
368
views
Improving validation losses and accuracy for 3D CNN
I have used a 3D CNN architecture, for detecting the presence of a particular promoter (MGMT), by using FLAIR brain scans. (64 slices per patient). The output is supposed to be binary (0/1).
I have ...
- 141
1
vote
0
answers
955
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
68
views
Pixel values of segmap in multi-class semantic segmentation
I'm preparing a dataset for a multiclass semantic segmentation using U-Net like architecture. To be precise, I've got it ready but a question came to my mind. How does pixel values of a segmentation ...
- 11
2
votes
1
answer
158
views
Preparing data set for the YOLO algorithm
Hi I am working on a project which requires the You Only Look Once algorithm in order to classify and localise objects within images. I have to prepare my dataset (which has 2 classes, and predicts 6 ...
1
vote
1
answer
2k
views
Should one use an "other" category in image classification?
In image classification, there are sometimes images that do not fit in any category.
For example, if I build a CNN in Keras to classify Dogs and Cats, does it help (in terms of training time and ...
- 113
1
vote
0
answers
111
views
Does the order of data augmentation and normalization matter?
What is the preferred order of data augmentation and normalization? Is it the former followed by the latter?
- 11
1
vote
1
answer
172
views
Keras 1D CNN always predicts the same result even if accuracy is high on training set
The validation accuracy of my 1D CNN is stuck on 0.5 and that's because I'm always getting the same prediction out of a balanced data set. At the same time my training accuracy keeps increasing and ...
1
vote
1
answer
1k
views
What happens if there is no activation function in some layers of a neural network?
What if I don't apply an activation function on some layers in a neural network. How will it affect the model?
Take for instance the following code snippet:
...
2
votes
2
answers
2k
views
What is the need for so many filters in a CNN?
Consider the following coding line related to CNNS
Conv2D(64, (3,3), strides=(2, 2), padding='same')
It is a convolution layer with filter size $3 \times 3$ and ...
- 3,990
0
votes
1
answer
91
views
Image Classification for watermarks with poor results
Just starting learning things about tensorflow and NN.
As an exercise I decided to create a dataset of images, watermarked and not, in order to binary classify these. First of all, the dataset ( you ...
- 101
1
vote
2
answers
277
views
How to construct input dependent convolutional filter?
I am constructing a convolutional variational autoencoder for images, starting out with mnist digits. Typically I would specify convolutional layers in the following way:
...
- 143
1
vote
1
answer
394
views
Why is the convolution layer called Conv2D?
When I build a convolution layer for image processing, the filter parameters should have 3 dimensions, (filter_length, filter_width, color_depth) is that correct?
...
- 197
1
vote
0
answers
118
views
How much data do we need for making a successful de-noising auto-encoder?
Is there a guide how much data do you need for making successful denoising model using autoencoders?
Or the rule is, the more data, the better it is?
I tried with small dataset 350 samples, to see ...
- 161
2
votes
2
answers
2k
views
How can I have the same input and output shape in an auto-encoder?
I'm building a denoising autoencoder. I want to have the same input and output shape image.
This is my architecture:
...
- 161
0
votes
1
answer
130
views
How to use 'Canny/Watershed' algorithm's output as an input for Image Classification Model
I have a very silly problem in hand. I have implemented 2 methods which give me the mask to separate the objects from the background. What I get from one method is the object encapsulated in the red ...
- 263
2
votes
2
answers
80
views
Heavily mixing signal differentiation from Open Set of backgrounds via CNN
I am currently attempting to detect a signal from background noise. The signal is pretty well known but the background has a lot of variability. I've since come to know this problem as Open Set ...
1
vote
0
answers
41
views
Is using a filter of size (1, x, y) on a 3D convolutional layer the same as using a filter of size (x,y) on a 2D convolutional layer?
I'm trying to predict some properties of videos with Keras using the following rough architecture:
Feed each frame through the same 2-D convolutional layer.
Take the outputs of this 2-D ...
- 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 ...
5
votes
1
answer
3k
views
How to add a dense layer after a 2d convolutional layer in a convolutional autoencoder?
I am trying to implement a convolutional autoencoder with a dense layer at the bottleneck to do some dimensional reduction. I have seen two approaches for this, which aren't particularly scalable. The ...
- 71
1
vote
1
answer
3k
views
How can I merge outputs of two separate layers so that the overall performance improves?
I am training a combined model (fine-tuned VGG16 for images and shallow FCN for numerical data) to do a binary classification. However, the overall AUC score is not what I expected it to be.
Image-...
- 241
2
votes
1
answer
181
views
Is it a sign of overfitting when validation_loss dips and then goes up with increasingly bigger swings?
I am experimenting with a ConvNet to categorize images taken with a depth camera. So far I have 4 sets of 15 images each. So 4 labels. The original images are 680x880 16-bit grayscale. They are scaled ...
- 153
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
49
views
Wouldn't training the model with this data lead to inaccuracies since the testing data would not be normalized in a similar way?
I was trying to normalize my input data images for feeding to my convolutional neural network and wanted to use standardize my input data.
I referred to this post, which says that ...
- 11
1
vote
1
answer
111
views
Hand-Signs Recognition using Deep Learning Convolutional Neural Networks
I am developing a CNN model to recognize 24 hand-signs of American Sign Language. I have 2500 Images/hand-sign. The data split is:
Training = 1250 Images/hand-sign
Validation = 625 Images/hand-sign
...
- 51
37
votes
6
answers
11k
views
Why do CNN's sometimes make highly confident mistakes, and how can one combat this problem?
I trained a simple CNN on the MNIST database of handwritten digits to 99% accuracy. I'm feeding in a bunch of handwritten digits, and non-digits from a document.
I want the CNN to report errors, so I ...
- 1,369
1
vote
1
answer
578
views
How can I make the kernels non-learnable and set them manually?
I'm a newbie in Convolutional Neural Networks. I have found out that kernels in convolutional layers are usually learned while training.
Suppose I have a kernel that is very good to extract the ...
- 493
2
votes
1
answer
152
views
Is my fine-tuned model learning anything at all?
I am practicing with Resnet50 fine-tuning for a binary classification task. Here is my code snippet.
...
- 241
1
vote
1
answer
2k
views
How many parameters are being optimised over in a simple CNN?
Okay so here's my CNN (simple example from a tutorial) along with some arithmetic to get the total number of free parameters.
We've got a dataset of 28*28 grayscale image (MNIST).
First layer is a ...
- 1,369
2
votes
1
answer
5k
views
How to compute the number of weights of a CNN?
How can we theoretically compute the number of weights considering a convolutional neural network that is used to classify images into two classes:
INPUT: 100x100 gray-scale images.
LAYER 1: ...
- 157
2
votes
1
answer
119
views
Is CNN capable of extracting the descriptive statistics features
I was trying to build a CNN model. I used time series data of daily temperature to predict if there is risk of an event, say bacteria growth. I calculated the descriptive statistics of the time series,...
- 251
1
vote
1
answer
41
views
Semantic issues with predictions made by my trained model
I'm new to Deep Learning. I used Keras and trained a inception_resnet_v2 model for my binary classification application (fire ...
- 983
3
votes
1
answer
264
views
What is the fastest way to train a CNN with billions of examples?
I have a CNN model that I need to train for a large scale genomics application. It is working well with a subset of my training data. I have scaled up to a subset of about 130 million examples and ...
3
votes
1
answer
3k
views
How can I reduce the GPU memory usage with large images?
I am trying to train a CNN-LSTM model. The size of my images is 640x640. I have a GTX 1080 ti 11GB. I am using Keras with the TensorFlow backend.
Here is the model.
...
- 33
2
votes
1
answer
156
views
Understanding the intuition behind Content Loss (Neural Style Transfer) [closed]
I'm trying to understand the intuition behind how the Content Loss is calculated in a Neural Style Transfer. I'm reading from an articles: https://medium.com/mlreview/making-ai-art-with-style-transfer-...
- 299
2
votes
0
answers
213
views
Understanding CNN+LSTM concept with attention and need help
I have a question about the context of CNN and LSTM. I have trained a CNN network for image classification. However, I would like to combine it with LSTM for visualizing the attention weights. So, I ...
- 21
0
votes
1
answer
159
views
How can I suppress a CNN’s translation invariant or translation equivariant?
I am trying to understand this post, but I get confused by the definitions and the differences. What's definition of equivariant?
If I remove all the pooling layers from a CNN, will it make the ...
- 281
2
votes
1
answer
52
views
how to benefit from previous training weights in training again to increase accuracy?
I have trained a modified VGG classification CNN, with random initialized weights; therefor the validation accuracy was not high enough for me to accept (around 66%).
now using the weights resulted ...
- 125