People who code: we want your input. Take the Survey

Questions tagged [convolutional-neural-network]

A convolutional neural network is a form of neural network with an additional convolutional layer, typically used in image & audio analysis. The convolutional layer is essentially a filtering stage defined by the kernel which is used. For example, a convolutional layer could have a kernel which extracts edges from an image towards the goal of learning which objects are in a scene.

Filter by
Sorted by
Tagged with
1
vote
0answers
31 views

How to train my CNN using AMD GPU on Windows?

I only have a laptop running Windows 10 with AMD Radeon Graphics Card at my disposal right now. I am aware that this is likely to make things tougher but I need to stick with this as long as I can't ...
1
vote
1answer
71 views

What is a sliding-window convolutional neural network?

In the abstract of "U-Net: Convolutional Networks for Biomedical Image Segmentation", the authors mention a sliding-window convolutional neural network. I've found several other articles ...
1
vote
2answers
87 views

What are the activation functions in Convolutional Layers for?

I read a lot about CNNs but I didn't quite understand some things: What are the activation function in CLayers for? If I understood it right, the only weights in these layers are the ones in Filters, ...
1
vote
0answers
18 views

Are 3D kernels in convolutions summed over their channels?

Say for example that I have a 28x28x1 grey scale image and I will perform two consecutive convolutions. The first convolution has 2 3x3x1 filters and the second has 3 3x3x2 filters. Each convolution ...
0
votes
1answer
23 views

Why are mini-batches degrading my conv net MNIST classifier?

I have made a convolutional neural network from scratch in python to classify the MNIST handwritten digits (centralized). It is composed of a single convolutional network with 8 3x3 kernels, a 2x2 ...
2
votes
1answer
13 views

Architectures that take inputs of mixed sampling rates

Let's say a model is trained on multiple datasets of 1D time series. These datasets have been gathered with different sampling rates. I plan to use a convolution neural network to process these time ...
0
votes
0answers
10 views

Why can't SPPnet update convolutional weights according to the fast R-CNN paper?

While discussing the drawbacks of SPPnet in the fast R-CNN paper, the authors state "But unlike R-CNN, the fine-tuning algorithm proposed in [SPPnet] cannot update the convolutional layers that ...
0
votes
1answer
575 views

How to Connect Convolutional layer to Fully Connected layer in Pytorch while Implementing SRGAN

I was implementing the SRGAN in PyTorch but while implementing the discriminator I was confused about how to add a fully connected layer of 1024 units after the final convolutional layer My input ...
0
votes
0answers
10 views

Theoretically Speaking, How Do Squeeze-and-Excitation Blocks Help?

A SE block works by assigning a weight to each channel, contrary to a vanilla filter, which gives equal importance to all channels. My question is, theoretically speaking, shouldn't a regular filter ...
0
votes
0answers
21 views

About the relevance and interprertability of convolutional filters?

Convolution filters are known to perform very well in tasks, concerning some work with the image or video data, due to their ability to preserve some spatial information and equivariance property ...
1
vote
2answers
72 views

Do smaller neural nets always converge faster than larger ones?

In your experience, do smaller CNN models (fewer params) converge faster than larger models? I would think yes, naturally, because there are fewer parameters to optimize. However, I am training a a ...
0
votes
0answers
612 views

Keras ValueError: Shapes (64,) and (32,) are incompatible

I am trying to run my first CNN model on the Fashion MNIST dataset. I am using kerastuner to tune the hyperparameters. The below code gave me an accuracy of 90.4% on test, 92.2% on validation and 94....
0
votes
1answer
22 views

How to build a classification pipeline that will pass to another model?

Not sure if the title explained it, but I am trying to build a pipeline where it's like a decision tree, but also not. Say for example, I had a picture. The model classified the picture, but now I ...
0
votes
1answer
58 views

Are there any control-flow/conditional statements in AI/ML models?

I was recently asked this during an interview. When we write a C program, it has a control-flow in the form of conditional statements like if, ...
0
votes
0answers
30 views

Understanding the network structure of a multiple timeseries fusion model

Please don't mark this question as duplicated to Can I create a layer with multiple rnn cell ? [question about a paper] It has already been marked 2 times , I admit they do refer to a same paper, but ...
1
vote
1answer
169 views

TensorFlow 2 one-hot encoding of labels

I was following this basic TensorFlow Image Classification problem, where images of flowers have to be classified into one of 5 possible classes. The labels in the training set are not one-hot encoded,...
0
votes
0answers
15 views

torch.save(the_model, PATH) vs torch.save(the_model.state_dict(), PATH) - model loading incorrectly for one method

I just now noticed that the model does not get loaded correctly if I use the the_model.state_dict() method to save it. On the other hand, using ...
0
votes
0answers
12 views

Nan loss for one Image dataset but finite fraction loss for another dataset?

I am training neural network using chainer library on MNIST dataset and one other dataset. As MNIST dataset is greyscale, hence I converted the other colored dataset to greyscale using cv2 library. I ...
1
vote
0answers
95 views

How do you deal with variable input sizes with an encoder-decoder net with skip connections in Keras?

I am currently getting into image segmentation with Keras, and I am using an encoder-decoder type as in the image below. My problem is that applying a MaxPooling2D ...
2
votes
1answer
76 views

Where are the 60 million params of AlexNet?

On the abstract of the AlexNet paper, they claimed to have 60 million parameters: The neural network, which has 60 million parameters and 650,000 neurons, consists of five convolutional layers, some ...
1
vote
1answer
78 views

How do I deal with additional input information other than images in a convolutional neural network?

I try to convert a game state of a board game into the input for a convolutional neural network. A convolutional neural network is useful because the players have to place items on the board, and the ...
0
votes
0answers
20 views

Training CNN for object detection

I have an idea for build object detection model and I would like to share it with community in order to see if it makes sense. Dataset: I've gathered images with different shapes and annotated them ...
0
votes
0answers
14 views

Intuition behind CNN Training Accuracy being Different than Loaded Model predicted on same exact data

I am trying to display some metrics in my final evaluation of several CNN models that I have trained using Tensorflow/Keras. I want to list the training accuracy for demonstration sake. However, I am ...
1
vote
0answers
10 views

Can we use CNN to effectively learn from a table whose various rows are permuted in the testing dataset, output for each remains same?

I have a set of classes, 37 to be precise. Each class is represented by a feature vector of size [1,10]. A single input sample has the dimensions of ...
1
vote
1answer
29 views

EfficientNet function composition or Hadamard

In the page 3 of the paper of EfficientNet, there is a equation $$\mathcal{N} = \bigodot_{i=1...s} \mathcal{F}_{i}^{L_i} \big(X_{\langle H_i, W_i, C_i \rangle}\big)$$ where $\mathcal{N}$ is the conv ...
0
votes
1answer
356 views

PyTorchs ConvTranspose2d padding parameter

Im confused about what PyTorchs padding parameter does when using torch.nn.ConvTranspose2d. The docs say that: "The padding argument effectively adds dilation * (kernel_size - 1) - padding ...
0
votes
1answer
32 views

Debugging a simple 1-D CNN for solving a simple classification problem

I have a rather simple classification problem that I am trying to solve. Each instance in my problem is a list of 1024 bytes (each byte is represented by a digit between 0 and 255). There are 2 ...
7
votes
1answer
218 views

Convolution backpropagation

I'm in the progress to learn, and understand different neural networks. I pretty much understand now feed-forward neural networks, and back-propagation of them, and now learning convolutional neural ...
2
votes
2answers
2k views

Is Flatten() layer in keras necessary?

In CNN transfer learning, after applying convolution and pooling,is Flatten() layer necessary? I have seen an example where after removing top layer of a vgg16 ,first applied layer was ...
0
votes
1answer
20 views

Understanding declared parameters in my Conv2d layer of my convolutional neural network

I am trying to understand the architecture of my keras model implemented by the sequential model. Here is a piece of the code : ...
0
votes
0answers
15 views

Is it possible to create a 3d to 2d U-net?

I was curious if it is possible to create a U-net type architecture that takes in a 3d image and outputs a 2d image? Or, alternatively, would some other architecture be better suited for this problem? ...
4
votes
2answers
556 views

Why are results without Transfer Learning better than with Transfer Learning?

I developed a neural network for license plate recognition and used the EfficientNet architecture (https://keras.io/api/applications/efficientnet/#efficientnetb0-function) with and without pretrained ...
0
votes
0answers
44 views

ConvNet - What to improve regarding architecture, procedure and technique?

I have a dataset of 180k images of license plates (so, not necessary to localize the license plate at first) for which I try to recognize the characters on the images (License plate recognition). All ...
0
votes
0answers
83 views

Plotting scikit-learn confusion matrix returns no values in the last class

I am attempting to create a confusion matrix using Scikit-Learn for a multiclass classification CNN, and it works well except for the fact that it does not provide ...
1
vote
1answer
177 views

pytorch convolution with 0-stride along one dimension

For some square images, I'd like to use torch.nn.Conv2d with the kernel as a vertical block. As in, the kernel size is defined as max value of the first dimension by 1. Since the first dimension has ...
0
votes
1answer
31 views

Is always converting a input vector into matrix and apply cnn's good idea?

I know the benefits of using cnns(reduced size weight matrices). Is it a good idea to convert a input vector(which is not a image) into a matrix and apply cnn's. What I understand is that it should ...
0
votes
0answers
26 views

How to use AutoEncoders or VAE for initializing custom CNN architecture?

I would like to use AutoEncoder or VAE in order to learn set of features which I can use to initialize training procedure of a custom CNN architecture that I've build. Here is the code: ...
1
vote
0answers
44 views

Why does regression model predict the same output

I have built a CNN for regression, but it is giving identical predictions (up to 8 sig. fig.) for almost 1/3 of the test data set. (The other outputs are different.) Is there a reason why this might ...
2
votes
1answer
330 views

Back propagation through a simple convolutional neural network

Hi I am working on a simple convolution neural network (image attached below). The input image is 5x5, the kernel is 2x2 and it undergoes a ReLU activation function. After ReLU it gets max pooled by a ...
0
votes
0answers
44 views

1D convolutional neural network validation improvement

I created 1D CNN in Keras, but I'm having issues with validation loss and accuracy. I have 24k records, 22 features. Is my model overfitting or what is going on so validation loss and accuracy is ...
0
votes
0answers
16 views

How to use Meta-SGD with U-Net

I'm guessing how to use Meta-SGD with U-Net network. I've been searching for an example, but I haven't found anything yet. I'm reading the book Hands On Meta Learning with Python, which has the ...
3
votes
3answers
797 views

How does “ Sparsity of connections” in CNNs causes the network to have less parameters?

I am studying Andrew NG's lectures on Convolutional Neural Network and he had provided two reasons for CNNs having less parameters compared to Non-Convolutional networks . They are : Parameter ...
0
votes
0answers
34 views

Configuration of CNN model for recognition of sequential data - Architecture of the top of the CNN - Parallel Layers

I am trying to configure a network for character recognition of sequential data like license plates. Now I would like to use the architecture which is noted in Table 3 in Deep Automatic Licence Plate ...
1
vote
0answers
196 views

How to deal with severe overfitting in a UNet Encoder/Decoder CNN in a task very similar to image translation?

I am trying to fit a UNet CNN to a task very similar to image to image translation. The input to the network is a binary matrix of size (64,256) and the output is of size (64,32). The columns ...
0
votes
1answer
97 views

Varying Image sizes in Tensorflow Malaria dataset | Dealing with unclean tensorflow data

I am trying to build a CNN based image recognition system for the Tensorflow malaria dataset. I loaded the dataset (~27k RGB images) using conventional tensorflow_datasets syntax. After some data ...
0
votes
0answers
15 views

Local RoI features in Faster/Mask R-CNN

I use Faster and Mask R-CNN for various problems, including training GANs. I'm particular interested in local features that Region Of Interest module in Faster R-CNN extracts from feature layer(s). ...
0
votes
0answers
10 views

Segmentation-free character recognition on an image: Multi-label, multi-class or sequential image classification problem?

I have some images which look like this one: They exist of 3 possible characters (A-C) and a length of 4. Now, I would like to run a neural network, which recognizes each character in the picture ...
1
vote
1answer
29 views

CNN model contains several images that are null

I'm using a deep CNN with the ReLU activation function. When visualizing the layers (each with 32 filters), several of the filtered images are zeros. I am trying to reason why this may be happening? ...
0
votes
1answer
64 views

What is the best way of combining audio and visual data to make predictions?

I am trying to predict the probability of a disease by using audio and images, the audio and the images do not come from the same source. I am thinking of combining the outputs (maybe average them) of ...
6
votes
3answers
311 views

Disparity between training and testing errors with deep learning: the bias-variance tradeoff and model selection

I am developing a convolutional neural network and have a dataset with 13,000 datapoints that is split 80%/10%/10% train/validation/test. In tuning the model architecture, I found the following, after ...

1 2
3
4 5
12