Stack Exchange Network

Stack Exchange network consists of 174 Q&A communities including Stack Overflow, the largest, most trusted online community for developers to learn, share their knowledge, and build their careers.

Visit Stack Exchange

Questions tagged [convnet]

For questions regarding "Convolutional Neural Networks" (CNN)

0
votes
1answer
21 views

How would you a apply a cnn to do age estimation on static images? [on hold]

After doing some reading on age estimation using the IMDB wiki dataset I wanted to try it out myself on a smaller scale but I dont quite understand the application of the CNN. Any clarification would ...
0
votes
0answers
12 views

TimeDistributed Layers vs. ConvLSTM-2D

Could anyone explains for me the differences between Time-Distributed Layers (from Keras Wrapper) and ConvLSTM-2D (Convolutional LSTM), for purposes, usage, etc.?
0
votes
0answers
9 views

What kind of layer can do a channel number reduction?

I have a tensor of (1, 1, 1000, 64), i.e. a vector of 1x1000 with depth=64 channels. I'd like to transform this into a vector with a single channel (1, 1, 1000, 1): Using: a ...
0
votes
1answer
16 views

How to increase accuracy of model from tensorflow model zoo?

Situation: My dataset is 70k images of people wearing clothes. Images are labeled: bbox position and class. There are 10 classes. I did 80:20 split. Categories are balanced with exception of one ...
0
votes
0answers
21 views

Mask RCNN with Imagenet pretrained weights

Does anyone know are there pretrained imagenet weights for Mask-RCNN? I was that you can call model.get_imagenet_weights() from https://www.kaggle.com/c/data-science-bowl-2018/discussion/51216 but ...
1
vote
1answer
17 views

How can I create a pixel labelled image for Semantic Segmentation?

I am following the Semantic Segmentation Examples tutorial by MathWorks. I understand that I can load pixel labeled images ...
0
votes
1answer
29 views

CNN backpropagation between layers

I have this CNN architecture: I know how to calculate error for weights based on the output and update weights between output<-->hidden and hidden<-->input layers. The problem is that I have ...
0
votes
1answer
10 views

Subsequent convolution layers

Note: I've read How do subsequent convolution layers work? a few times, but it's still difficult to understand because of the parameters $k_1$, $k_2$, and many proposals (1, 2.1, 2.2) in the question. ...
0
votes
0answers
8 views

Encoder Decoder networks with varying image sizes

Encoder Decoder Network - Computerphile : At the very beginning of this video, Michael Pound goes on to say: So it (encoder decoder network) makes no assumptions about the size of the input the ...
1
vote
0answers
36 views

How to train a multi inputs deep learning model using every combination of inputs? [closed]

I am beginner in deep learning. I want to create a multi inputs CNN model in Keras. The model takes two inputs of images to give the two images class. The two images from differnt datasets that have ...
0
votes
1answer
27 views

Print the prediction of convolutional neural network

I have designed a convolutional neural network using tensorflow which looks as follows ...
0
votes
0answers
32 views

CNN - Is this a Toeplitz Matrix?

I have been reading through Chapter 9 of www.deeplearningbbook.org, where convolutional networks are being described. The following image represents the output of a 2D convolution, without kernel ...
0
votes
0answers
14 views

Why is this convolution equation easier to apply than it's commutative counterpart?

The convolution is an operation on two functions of a real- valued argument. The convolution operation is typically denoted with an asterisk: s(t) = (x ∗ w)(t) ...
1
vote
0answers
16 views

Convolutional neural network for gray images

I am using vgg16 to design a CNN that takes gray input images. The model give me good results without changing anything related to colors. I am not sure if what I did is correct or not. I want to ...
1
vote
0answers
14 views

Deep Learning ROC and Average Precision Curve Results

I used Vgg16 to create a deep learning model and the dataset is imbalanced so, I used class_weight argument in fit_generator method. The model result as the following: accuracy= 98.9% and loss= 0....
2
votes
1answer
37 views

Does CNN take care of zoom in images?

Suppose a convolution neural network is trained on small images of an object, say flower, as in following 3 training images: Will this CNN correctly classify if the same object is present in zoomed ...
0
votes
1answer
53 views

Keras ImageDataGenerator.flow_from_directory doesn't find images

I'm working on a deep learning (CNN) problem. I have structured my images into folders correctly (I think), like this: ...
0
votes
1answer
240 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
1answer
122 views

How to make two parallel convolutional neural networks in Keras?

I created two convolutional neural networks (CNN), and I want to make these networks work in parallel. Each network takes different type of images and they join in the last fully connected layer. ...
0
votes
1answer
32 views

Check Overfitting in CNN

I am kind of new to NLP and text classification with Convolutional Neural Nets, and I have trained my first models quite recently. I am a little bit concerned with overfitting. I am doing multilabel ...
2
votes
1answer
16 views

Relation between amount of training samples and model depth?

When I add more hidden layers to my CNN (e.g. Dense Layers) it seems that the model needs more training samples to produce good results for classes with few training samples. In the single layer case ...
2
votes
0answers
13 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 ...
0
votes
0answers
17 views

Why is network in network architecture significant?

When talking about convolutions, we have seen networks carrying out the network in network architectures (1x1 convolutions), What is the significance of this process and how does it affect the network ...
1
vote
1answer
27 views

How does training a ConvNet with huge number of parameters on a smaller number of images work?

I have two questions: I am wondering why is that a very deep model such as VGG-16 which has approximately 138 million parameters (Source) can be used as a model to be trained on just 1.3 million ...
1
vote
0answers
76 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 ...
0
votes
1answer
176 views

Keras Conv1D for simple data target prediction

I am trying to use conv1D layer from Keras for predicting Species in iris dataset (which has 4 numeric features and one categorical target). Following is my code: ...
2
votes
1answer
39 views

Too little or too much maxpooling?

I am creating a CNN in Keras where model.summary() shows: ...
2
votes
1answer
85 views

Overfitting in Siamese Network

I am trying to train a Siamese network for an application very similar to this and this. From what I have read about training Siamese networks dissimilar pairs of images outnumber the similar pairs ...
0
votes
0answers
22 views

Why different results on repeated runs

I find that if I run my convolution neural network repeatedly on same data, I get train accuracy varying from 5% to 95%. Is this common or usual? What could be causing it and how can it be reduced? ...
2
votes
3answers
286 views

Unbalanced training data for different classes

What precautions do I need to take while trying to develop a CNN for classification of images if there is much more training data for one label. For example: ...
1
vote
0answers
15 views

Magnification factor in image classification

If a CNN is trained on images focusing on an object, will it also recognize when multiple such objects are present in the image? For example can a network trained on single flower images also ...
5
votes
1answer
280 views

1x1 Convolution. How does the math work?

So I stumbled upon Andrew Ng course on 1x1 convolutions. There he explains that you can use 1x1x192 convolution to shrink it. But when I do ...
2
votes
0answers
303 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 ...
1
vote
0answers
31 views

how to load label data presented in raster format into Keras/Tensorflow

I want to use CNN network to segment 2 objects (binary: "0: object not present 1: object present") into shapes but I have an issue with data. The train data is 150 images and in "jpg" format and the ...
2
votes
0answers
72 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
2answers
100 views

What is the difference between using numpy array images and using images files in deep learning?

What is the difference between using numpy array images and using images files in deep learning? Which way is better?
1
vote
0answers
25 views

How to implement facial attendance system using less number of images of particulars

I have a project to implement facial Attendance where I have 5-6 images of particular and when individual comes, model should map the current image with person's earlier available images so if ...
2
votes
1answer
50 views

Should I use rescale parameters for data augmentation? [closed]

I am using Keras library to build a CNN model. I want to use data augmentation for training data. Should I use rescale parameters for data augmentation? ...
5
votes
1answer
43 views

Data augmentation parameters

When I use data augmentation to increase the train dataset, should I use all augmentation techniques (parameters in keras)? Which data augmentation parameters should use with flow_from_directory?
7
votes
1answer
41 views

keras' ModelCheckpoint not working

I'm trying to train a model in keras and I'm using ModelCheckpoint to save the best model according to a monitored validation metric (in my case the Jaccard index). While I can see the model ...
5
votes
1answer
95 views

Optimizer for Convolutional neural network

What is the best optimizer for Convolutional neural network (CNN)? Can I use RMSProp for CNN or only for RNN?
1
vote
1answer
134 views

Data augmentation in deep learning

I am working on a deep learning project for face recognition. I am using the pre-trained model VGG16. The dataset has around 100 classes, and each class have 80 images. I split the dataset 60% ...
6
votes
1answer
58 views

CNN or Viola-Jones for facial detection

I was wondering since CNNs have dominated every image-related task. Is the Viola-Jones face detector still considered state-of-the-art, or have CNNs surpassed its performance?
3
votes
1answer
233 views

Data augmentation: ImageDataGenerator vs openCV

I want to increase the data in my dataset to create a CNN deep learning classification model. Which is better for the model using data augmentation by ...
4
votes
0answers
49 views

Neural Network Architecture for Identifying Image Copies

I have a large image collection and wish to identify the images within that collection that appear to copy other images from the collection. To give you a sense of the kinds of image pairs that I ...
2
votes
1answer
155 views

L2 regularization increase the loss rate of the deep learning model

When I add L2 regularization to my deep learning model the training and validation loss rate is increased. Why ????
3
votes
0answers
109 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?
1
vote
0answers
11 views

Relationship between objects - ConvNets

Is there some interesting work on modeling relationship between objects in images? This seems like a natural extension to object detection/segmentation, but I couldn't find anything well-cited. I'm ...
2
votes
1answer
29 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?...
10
votes
1answer
100 views

What is the difference between upsampling and bi-linear upsampling in a CNN?

I am trying to understand this paper and am unsure of what bi-linear upsampling is. Can anyone explain this at a high-level? https://arxiv.org/abs/1606.00915