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.

214 questions with no upvoted or accepted answers
Filter by
Sorted by
Tagged with
5
votes
0answers
63 views

Training value neural network AlphaGo style

I have been trying to replicate the results obtained by AlphaGo following their supervise learning protocol. The papers specify that they use a network that has two heads: a value head that predicts ...
4
votes
0answers
325 views

1D CNN Variational Autoencoder Conv1D Size

I am trying to create a 1D variational autoencoder to take in a 931x1 vector as input, but I have been having trouble with two things: Getting the output size of 931, since maxpooling and upsampling ...
4
votes
0answers
292 views

How to detect vanishing and exploding gradients with Tensorboard?

I have two "sub-questions" 1) How can I detect vanishing or exploding gradients with Tensorboard, given the fact that currently write_grads=True is deprecated in the Tensorboard callback as per "un-...
4
votes
1answer
705 views

How to use PCA in CNN for image recognition using Keras?

I created a CNN model for image classification and I want to use Principal Component Analysis (PCA) but when I run pca.fit() code, the code still running for hours ...
4
votes
1answer
2k views

Gradient flow through concatenation operation

I need help in understanding the gradient flow through a concatenation operation. I'm implementing a network (mostly a CNN) which has a concatenation operation (in pytorch). The network is defined ...
4
votes
0answers
269 views

how to propagate error from convolutional layer to previous layer?

I've been trying to implement a simple convolutional neural network. But I've been stuck at this problem for over a week. To be specific, assume there are 3 layers in a convolutional pass, marked as ...
4
votes
2answers
575 views

How to determine the number of the training images in Keras after data augmentaion?

I want to create a CNN model and I am using data augmentation. I want know the number of augmented images in Keras. How to determine the number of the training images in Keras after data augmentation?...
3
votes
0answers
31 views

Using softmax for multilabel classification (as per Facebook paper)

I came across this paper by some Facebook researchers where they found that using a softmax and CE loss function during training led to improved results over sigmoid + BCE. They do this by changing ...
3
votes
0answers
74 views

What happens with activations?

I am playing with convolution network, assembling something between AlexNet and ResNet. Not very deep, about 10 conv. layers including 2 through residual connection, and 3 fully-connected layes at the ...
3
votes
0answers
56 views

Keras model with second to last sigmoid activated Conv1D layer followed by globalMaxPool outputs values outside [0,1]. Why?

I am trying to train a binary classifier. It is a residual network with skip layers etc. but ultimately, the bottom two layers are a 1D convolution with sigmoid activation followed by a global max ...
3
votes
1answer
222 views

Why is training and validation loss steadily rising (eventually to NaN) in this CNN of mine?

Dear ML and data scientists: I have 4 layers of gray scale images for every single biological specimen in my dataset. I am trying to train a 4-convolution CNN (see pytorch architecture below) to ...
3
votes
2answers
57 views

ConvNet with concatenated data

I have a basic question regarding convolutional neural network. Assume I have a set of 1000 RGB images and I train a CNN from this set. I can obviously split each of my RGB images into 3 different ...
3
votes
0answers
73 views

Computing derivatives for backpropagation across a convolution step

This will be a long post, but I hope it'll be instructive to anyone else in my position. I'm trying to find how the derivatives of the loss function are calculated with respect to the kernels and ...
3
votes
0answers
908 views

Multi label classification and sigmoid function

I'm new to neural networks so this may be silly question. I have build standard CNN network for image classification. I want multi-label classification network so I use binary_crossentropy as loss ...
3
votes
1answer
304 views

LeNet-5 - combining feature maps in C3 layer

Famous LeNet-5 architecture looks like this: The output of layer S2 has dimension: 10x10x6 - so basically an image with 6 convultions applied to it to derive features. If each dimension was again ...
3
votes
0answers
1k views

Cross validation for convolutional neural network

I am using Keras to create a CNN model, and I would to use K-fold cross-validation to train the dataset. The dataset contains images and I am using ...
3
votes
0answers
379 views

Convolutional neural network with cross validation in Keras

I want to use K-fold cross-validation on my dataset of images. I am reading the data (images) from a directory. How do I use cross validation with convolutional neural network in Keras?
3
votes
1answer
937 views

Keras bug NasNetlarge no top

I am trying to use NasNetlarge in Keras without the top but I cant get rid of the top: ...
3
votes
0answers
490 views

Keras - Masking CNNs

I have a 3D tensor on which I apply 2D convolutions. Sometimes, this 3D is padded both in width and height to have a fixed size. How could I apply masking (like with RNNs) so that the gradients ...
3
votes
0answers
722 views

Are non-zero paddings used?

I currently tried to figure out which paddings are directly supported by the frameworks: Tensorflow (tf.nn.conv2d): ...
2
votes
0answers
25 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
151 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
27 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
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 ...
2
votes
0answers
22 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
42 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
85 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
270 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
0answers
216 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
350 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
501 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
553 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 ...
2
votes
1answer
146 views

Doing a fine tuning after a transfer learning

I read about fine tuning and transfer learning for CNNs and was wondering if we can do fine tuning after using transfer learning on the same CNN? If so, will this increase the performance of the model ...
2
votes
0answers
836 views

How to detect multiple digits in one image using CNN

The network in CNN recognize one digit for one image, how can I recognize two or more digits in one image. A proper way I've thought about is modifying the weights in the FC layer. In other words, ...
2
votes
0answers
142 views

What does it mean if performance of two different iterations of the same network (CNN model) varies a lot?

So I trained CNN model for people detection on caltech-pedestrian dataset: Then I was curious and evaluated the model in every 1000th iteration on Evaluation toolbox(I guarantee, there is no bug in ...
2
votes
0answers
95 views

ConvNet for Archery App

I'm looking at trying to build a model to score an archery end from a photo but i'm not sure about the optimal ConvNet architecture. What output neurons would I use given I can have an unknown number ...
2
votes
0answers
113 views

What are natural (computed) pre-images useful for?

I've just been reading Zeiler, M.D. and Fergus, R., 2014, September. Visualizing and understanding convolutional networks. In European Conference on Computer Vision (pp. 818-833). Springer ...
2
votes
0answers
79 views

Discrepancy in probability calculations in paper 'Multi-digit Number Recognition…'

In the paper, 'Goodfellow, I., et al. Multi-digit Number Recognition from Street View Imagery using Deep Convolutional Neural Networks. ICLR, 2014', on page 10 there is a table which calculate $\log(P(...
1
vote
0answers
12 views

Average loss is 0 when training dataset with darknet yolov4

I am currently training a dataset using yolov4 darknet from AlexeyAB Github found here: https://github.com/AlexeyAB/darknet The dataset I am training is called FishNet Open Images. The dataset has 86,...
1
vote
0answers
23 views

CNN + LSTM model for images performs poorly on validation data set

My training and loss curves look like below and yes, similar graphs have received comments like "Classic overfitting" and I get it. My model looks like below, ...
1
vote
0answers
9 views

What is the intuition behind transposed conv layers being able to upscale images?

I was reading the ZF Net paper and it used the term Deconvnet on some searching it seems this is the wrong term and rather we use transposed convolutions instead. I understood how transposed ...
1
vote
0answers
13 views

What should be the input shape for convLSTM if ResNet-50 is applied before?

I have a video dataset, extracted all its frames, and applied ResNet-50 to extract features from all frames. ResNet-50 provides feature map of (2534, 7, 7, 2048), 2534 are the number of frames. Now I ...
1
vote
0answers
28 views

What model to use for relative comparison between 3 figures?

I am working on a problem where I am given three images of different dishes (A,B,C) and the task is to figure out if figure B or ...
1
vote
0answers
23 views

Backpropagation on a CNN

I have tried searching for this, but it seems like no one addresses a key aspect of this problem (or maybe I'm overthinking this): So, first let's assume we have a 3x3 image with a single channel, and ...
1
vote
1answer
21 views

One hot vector output in classification task

I'm working on CNN model and I used one hot vector type of labels. The number of classes is 3: [1,0,0], [0,1,0], [0,0,1]. net(x) I'm getting such an output: [0....
1
vote
0answers
23 views

ROC and AUC curve for CNN multi-class classification problem

I have produced a convolutional neural network to classify images (malware images) into different classes/families. I have managed to produce a confusion matrix and classification report. My ...

1
2 3 4 5