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
2
votes
1answer
84 views

How to determine the number of forward and backward passes in deep learning (CNN)? [closed]

Is there a way to determine the number of forward and backward passes in the training of a neural network using python?
2
votes
1answer
2k views

Using handcrafted features in CNN

What is the difference between using CNN with handcrafted features and CNN without handcrafted features? Thank you
2
votes
1answer
13k views

“concat” mode can only merge layers with matching output shapes except for the concat axis

I have a function I am trying to debug which is yielding the following error message: ValueError: "concat" mode can only merge layers with matching output shapes except for the concat axis. Layer ...
2
votes
1answer
3k views

How to map ground truth to prediction for UNet architecture

I've gone through the paper describing the UNet convolutional neural network a number of times, but am still having trouble figuring out how to connect the output of the network to the ground truth ...
2
votes
1answer
2k views

Input and output feature shapes in CNN for speech recognition

I am currently studying this paper and are trying to understand what exactly the input and output shape is. The paper describes an acoustic model consisting of using cnn-hmm as the acoustic model. ...
2
votes
2answers
1k views

Test accuracy of neural net is going up and down

I am using a CNN to classify medical images. I am using a four convolutional layers with ReLU activation followed by a softmax layer. I am using rmsprop as the optimizer. The problem I am facing is ...
2
votes
2answers
102 views

Is there any public implementation / publication with Hintons capsules idea?

In Hintons talk "What's wrong about convolutional nets" (Late 2016 or early 2015, I guess) he talks about capsules to make a modular CNN. Is there any publicly available implementation or papers ...
2
votes
1answer
215 views

Trying to figure out how to set weights for convolutional networks

I am working on CNN, and I have some doubts. Let's assume I only want one feature map, just to make things easier. And let's suppose my image is grayscale, to make things even easier. So, let's say my ...
2
votes
1answer
134 views

Applying ConvNets to classify motion/video data

How would someone go about using deep learning to classify sign language gestures? For example, suppose I had video files of many different gestures. For any given gesture, I might have many videos of ...
2
votes
1answer
34 views

Why first fully connected layer requires flattening in cnn?

One can read everywhere on internet or in books that in convoluted neural networks, between convolution layers and the first fully connected layer, you should flatten your data. I managed to ...
2
votes
1answer
40 views

why transpose convolution is called “transpose”

https://d2l.ai/chapter_computer-vision/transposed-conv.html https://en.wikipedia.org/wiki/Transpose I understand what transpose convolution does, but I am confused about the name of 'transpose'. In ...
2
votes
1answer
93 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 ...
2
votes
1answer
363 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 ...
2
votes
2answers
51 views

What can we understand from max-activation generated images?

There are several approaches to generate psychedelic images, providing maximum activations for individual neirons in convolutional neural networks. For example there is a lot of them there https://app....
2
votes
2answers
826 views

Model not learning when using transfer learning

I am working on a personal project on image classification (two classes) and am trying to see how the MobileNet v2 structure would perform. While training the training accuracy is already quite high ...
2
votes
1answer
529 views

Tensorboard with pytorch dont display a graph

I am trying to visualize a model I created using Tensorboard with Pytorch but when running tensorboard and going to the graph tab nothing is shown, im adding my code for reference, also im adding a ...
2
votes
1answer
921 views

1x1 convolutions, equivalence with fully connected layer

I'm confused by the concept of equating a 1x1 convolution with a fully connected layer. Take the following simple example of a 1x1 convolution of 2 input channels each of size 2x2, and a single output ...
2
votes
1answer
2k views

Question about “1x3 and 3x1 conv is equivalent to 3x3 conv”

I see a lot of sites talk that we can substitute 1x3 conv + 3x1 conv for 3x3 conv. In order to demonstrate easily, we use a 3x3 image as an example. From the point of view of parameters, I know that ...
2
votes
1answer
2k views

Shaping data for ConvLSTM for many-to-one image model

Ultimately, I am trying to obtain a binary segmentation mask for an image sequence. I have n number of image sequences, each with 500 greyscale images of size 256px by 400px. Each of these sequences ...
2
votes
1answer
390 views

How many Layers in the original Yoon Kim CNN implementation?

I saw some implementations of Yoon Kim's Convolutional Neural Network (Paper: http://www.aclweb.org/anthology/D14-1181).... ...in some implementations they put one more Dense(..) Layer before the ...
2
votes
1answer
122 views

Resource and useful tips on Transfer Learning in NLP

I have a few label data for training and testing a DNN. Main purpose of my work is to train a model which can do a binary classification of text. And for this purpose, I have around 3000 label data ...
2
votes
2answers
93 views

How can I infer no target in a target classification problem based on deep learning?

Let's take the MNIST dataset (My application is different) with a lot of noise, I am going to train a deep NN to classify the letters. What's the right way to infer, there's no letter possibility? or ...
2
votes
1answer
87 views

What kind of neural network structure is suitable for image to image learning?

There exists a mapping from input image to out image. Say input image is a piece of paper with a square hole in the center, and output image is the shadow of the input image when light shines on the ...
2
votes
1answer
315 views

Any difference between adding epochs and duplicating data for neural nets?

Let's say I am training a neural net (e.g. convolutional network or LSTM). Generally, the longer the training (more epochs) leads to better accuracy, albeit at times at the expense of overfitting. ...
2
votes
1answer
4k views

Is it possible to use grayscale images to existing model?

From tensorflow's object recognition (R-CNN) I'm re-training the existing model with new categories: the types of clothes (jeans, pants, blouse, and so on). Since we don't need colors to determine ...
2
votes
1answer
781 views

RCNN - recurrent convolutional neural networks - what is a time step?

I am currently studying this paper for implementing it into a speech recognition application, but seem to have some problems understanding the concepts of time step. What is a time step? I haven't ...
2
votes
1answer
1k views

(CNN+)RNN-HMM hybrid for learning phonemes from a spectogram

I am currently working on a speech recognition task, on applying deep learning onto the standard acoustic model (gmm-hmm). I've currently generated a spectrogram of my utterances, and using simple ...
2
votes
1answer
144 views

Self adjusting CNN network

I am currently trying to build a self adjusting network, such that given any number of inputs, should always provide an output of shape (15,145) The network structure is pretty simple and looks like ...
2
votes
1answer
178 views

Layers' function in a convolutional neural networks

From Wang et al (2015) "Visual Tracking with Fully Convolutional Networks": A top layer encodes more semantic features and serves as a category detector, while a lower layer carries more ...
2
votes
1answer
2k views

Applying convolutional neural network over text documents using 1-D tf-idf feature vectors

I want to apply a CNN over documents. I have tf-idf vectors of documents with me (one vector per document). My question is, is 1D CNN applicable in this case? The reason I am asking this question is ...
2
votes
0answers
25 views

Regress values inside the bounding boxes to predict a value in Object Detection

I am currently working on an object detection task. I have a dataset of grayscale and depth images. The annotation format is $x_1, y_1, x_2, y_2, class, depth$. I calculated this depth (of each ...
2
votes
0answers
23 views

Convolutional autoencoder - why keras example is asymmetry model?

I'm looking on keras convolutional autoencoder example, and confused with the model structure: ...
2
votes
0answers
17 views

How to modify a Convolutional Neural Network architecture built for a univariate time series to multivariate time series?

I have built a CNN (in combination with a LSTM cell) that takes 1D time series-like data as an input and performs classification. I am obtaining a good performance, but the complete data has actually ...
2
votes
0answers
28 views

Methods to visualize the filters in the later layers of a CNN?

I've extracted the weights from the filters of a pretrained model (AlexNet). I wish to represent these weights visually, this works fine for the first layer as there is only 3 input channels so I can ...
2
votes
1answer
222 views

TypeError: Expected int32, got None of type 'NoneType' instead

I want my model batch size to be a dynamic shape, and I've assigned none as batch size, but that's causing an error. Here, in the first line, I specified batch size as None: ...
2
votes
0answers
40 views

What is the difference in computational cost at inference time between object detection and semantic segmentation?

I am aware that YOLO (v1-5) is a real-time object detection model with moderately good overall prediction performance. I know that UNet and variants are efficient semantic segmentation models that are ...
2
votes
1answer
15 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 ...
2
votes
0answers
24 views

What is the meaning of 'concatenate' in this neural network architecture?

I am trying to understand the lane edge proposal network proposed in LaneNet for lane detection. My understanding of this is that a number of convolutional and pooling layers are first used to ...
2
votes
0answers
45 views

Precision Recall using Distance Matrix

Given a Pre-trained CNN model, I extract feature vectors for 3450 Reference (Winter) and 3450 Query images (Spring) and compare features with euclidean distance to plot the distance matrix besides ...
2
votes
0answers
24 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/...
2
votes
0answers
91 views

Understanding the significance of LeNet-5 w/ MNIST data set

I'm beginning to learn about conv nets and started with what I understand to be one of the seminal works: LeNet-5. However, my limited experimentation doesn't seem to show any advantage over a single ...
2
votes
1answer
293 views

Why is convnet transfer learning taking so long?

I am using transfer learning to train a binary image classification model using keras' pretrained VGG16 model. The code can be found below : ...
2
votes
1answer
88 views

How to perform polynomial landmark detection with deep learning

I am trying to build a system to segment vehicles using a deep convolutional neural network. I am familiar with predicting a set amount of points (i.e. ending a neural architecture with a Dense layer ...
2
votes
0answers
230 views

How to train two neural networks together

This could be considered as an extension of my previous question "How to make a region of interest proposal from convolutional feature maps?". Network 1: I have a multi-input neural network, it ...
2
votes
2answers
4k views

How to properly save and load an intermediate model in Keras?

I'm working with a model that involves 3 stages of 'nesting' of models in Keras. Conceptually the first is a transfer learning CNN model, for example MobileNetV2. (Model 1) This is then wrapped by a ...
2
votes
0answers
49 views

CNN kernel location for input image

Given a CNN, say AlexNet: How could one relate kernel locations at the 3rd conv block, i.e 13x13 filter size to the input image. Would that give a meaningful representation in terms of the input ...
2
votes
0answers
359 views

Data augmentation / feature extraction on pre-trained convnets

I'm reading 'Deep Learning with Python' by François Chollet, which is an excellent book. He talks about using pre-trained convnets (in his example, VGG16) and then running smaller datasets to tweak ...
2
votes
0answers
510 views

Tensorflow CNN sometimes converges, sometimes not

originally asked on stackoverflow, deleted Im having trouble traing a convolutional neural network in tensorflow. When I start my program, sometimes the model learns nicely (cost/cross_entropy goes ...
2
votes
2answers
599 views

MLP conv layers

When should MLP conv layers be used instead of normal conv layers? Is there a consensus? Or is it the norm to try both and see which one performs better? I would love to better understand the ...
2
votes
0answers
24 views

Contextual Object Detection

An example of what I'd like to do is identify the price of a product on a product page. While I can train a CNN to identify prices, it's likely that it would recognise every instance of a price on a ...

1
3 4
5
6 7
12