Questions tagged [convnet]

For questions regarding "Convolutional Neural Networks" (CNN)

Filter by
Sorted by
Tagged with
1
vote
2answers
98 views

data pre-processing before feeding into a deep learning model

Generally speaking, when training a deep learning model, like MLP, what kind of data pre-processing operation has to be conducted when the input is a numerical sequence.
4
votes
3answers
4k views

Number of Fully connected layers in standard CNNs

I have a question targeting some basics of CNN. I came across various CNN networks like AlexNet, GoogLeNet and LeNet. I read at a lot of places that AlexNet has 3 Fully Connected layers with 4096, ...
1
vote
0answers
41 views

My weight matrix converged to zeros

So I was training a fairly shallow convnet, because my deepnet based on vgg19 wasn't working. 2 conv layers and 2 flat layers, the second flat layer was the output. It converged quickly to all zeros ...
6
votes
4answers
1k views

Why choose TensorFlow?

I have noticed that most of the deep learning developers use TensorFlow. So why choose TensorFlow? What is the advantage of TensorFlow over Theano and CNTK?
2
votes
1answer
1k 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
57 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 ...
0
votes
1answer
44 views

How can we create neural net to detect false predictions?

I created a convolutional network to recognise certain substrings. For example, the following phrases would be mapped to the "What" class: ...
2
votes
1answer
1k views

How to implement PCA color augmentation as discussed in AlexNet

I read through "ImageNet Classification with Deep Convolutional Neural Networks" again specifically for details on how to implement PCA color augmentation. I am unsure if I have it right. Here is how ...
0
votes
1answer
557 views

What if my validation set is worse than my training?

I am running a CNN, on the 1st epoch my training set accuracy is 15% and validation set is 12%, by the 51st epoch my training accuracy is 87% and validation set is 13%. What is happening? What does it ...
5
votes
3answers
10k views

How to improve loss and avoid overfitting

I'm trying to build a 2 class image classifier using the architecture suggested in first part of this blog https://blog.keras.io/building-powerful-image-classification-models-using-very-little-data....
3
votes
1answer
372 views

How to deal with skewed imbalanced image dataset to work with CNN?

I am working on multi-class classification problem on an image dataset. There is one class with 80% of the images and rest 20% is divided into rest 6 remaining classes. If I have to apply the image-...
1
vote
0answers
57 views

How to estimate Distance to Obstacles using Lidar's BEV(Bir's Eye view ) Representation?

I am using a implementation that use both camera and Lidar for 3D obstacle detection for self driving cars but I have no idea how to calculate the distance to the obstacles since the Lidar uses the ...
1
vote
0answers
877 views

How to change learning rate of MomentumOptimizer in tensorflow

I am trying to implement VGG-16 architecture in TensorFlow. As mentioned in the paper, they changed the learning rate 3 time during their 74 epochs of training. ...
1
vote
1answer
102 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. ...
1
vote
0answers
25 views

Variable TimeStep in Spatio Temporal 3DConvNet

I'm working on a new project on climate data. I suppose my output $Y(H*W*1)$ is a consequence of a given data scenario $X(C=4*T*H*W)$ and an initial state $Y0(H*W*1)$. I've chosen a temporal ...
0
votes
1answer
171 views

Training Error decreasing with each epoch

I am trying to train a VGG-19 neural network on STL-10 dataset containing 5000 images(500 for each class). And the number of output classes is 10. I have made no changes to the architecture except ...
0
votes
1answer
27 views

Fine train a convnet on difficult data only?

I use a convnet to classify two types of objects: class A and B. I created the data set myself and have around 1000 examples per class. Some are really obvious and clear, some others are very ...
1
vote
1answer
274 views

The sum of probabilities is more than 1

I have CNN architecture for object detection ( one object in image ) in KERAS. It has 22 Convolutional layers ( layer includes max pool , LeakyRelu and Batchnorm ) The last layes are following ...
4
votes
2answers
2k views

How to sort numbers using Convolutional Neural Network?

Recently, in an interview I got this question: Design a convnet that sorts numbers. Operators are ReLU, Conv, and Pooling. E.g. input: 5, 3, 6, 2; output: 2, 3, 5, 6 I am not sure how can you sort a ...
4
votes
1answer
5k views

What is the input size of Alex net

In the paper ImageNet Classification with Deep Convolutional Neural Networks, the size of input image is 224x224. The following figure shows the input size. From caffe, deploy.prototxt file from the ...
4
votes
2answers
546 views

In a convolutional neural network (CNN), when convolving the image, is the operation used the dot product or the sum of element-wise multiplication?

The example below is taken from the lectures in deeplearning.ai shows that the result is the sum of the element-by-element product (or "element-wise multiplication". The red numbers represent the ...
0
votes
1answer
24 views

has anybody created interesting ConvNets on 3D movie data?

In the last video of his course on Convolutional Neural Networks, Andrew Ng was discussing using ConvNets on 3D input data. He mostly discussed cat scans, but also mentioned you could treat a movie as ...
0
votes
1answer
604 views

Text analysis - classification, parsing

Excuse if this has been answered before. I need to extract features and parse from a piece of text and run some analysis. For e.g. "Plot the past 5-year sales of Apple" should give me the following ...
1
vote
0answers
38 views

Understand the shape of this Convolutional Neural Network

I'm trying to implement what is explained in a paper on audio signal processing. The guys who wrote this paper tried a Convolutional Neural Network and here is how they explain it : "The CNN are ...
1
vote
0answers
60 views

How to get intuitive understanding which deep learning architecture suits for my problem

I'm working on a research problem where I need to perform classification for coarse prediction in a feature space and then fine grained regression for getting more precise values. I know that this way ...
4
votes
4answers
1k views

How to fix these vanishing gradients?

I am trying to train a deep network for twitter sentiment classification. It consists of an embedding layer (word2vec), an RNN (GRU) layer, followed by 2 conv layers, followed by 2 dense layers. Using ...
2
votes
1answer
3k views

Watermark detection in Python

I have a lot of images and I would like to be able to classify them into two groups: one containing images with watermarks and one containing images without any watermark. There are about 40 ...
11
votes
1answer
3k views

Using a pre trained CNN classifier and apply it on a different image dataset

How would you optimize a pre-trained neural network to apply it to a separate problem? Would you just add more layers to the pre-trained model and test it on your ...
1
vote
0answers
89 views

How to interpret sudden jumps of improvement in training error vs. iteration?

In the Residual learning paper by He et al., there are a number of plots of training/test error vs. backprop iteration. I've only ever seen "smooth" curves on these plots, while in this paper's ...
5
votes
2answers
3k views

Convolutional Neural Networks layer sizes

I am trying to understand an article Backpropagation In Convolutional Neural Networks But I can not wrap my head around that diagram: The first layer has 3 feature maps with dimensions 32x32. The ...
0
votes
1answer
715 views

Reinforcement Deep Learning for object detection [closed]

After reading the state of the Art of object detection using the CNN's(R-CNN,Faster R-CNN,YOLO,YOLOv2,SSD) I was wondering if there is an efficient method that use deep learning with reinforcement ...
1
vote
1answer
49 views

Training a Convnet on 300GB data

I have a large training set of ~300GB (which is a subset of an even larger dataset ~15TB). I am trying train a Convnet with Keras (Tensorflow backend) to do something similar to semantic ...
4
votes
4answers
3k views

Is There any RNN method used for Object detection

after reading the state of the art about object detection using CNN (R-CNN Faster R-CNN ,YOLO, SSD...) I was wondering if there is a method that use RNN's or that combine the use of CNN's and RNN's ...
3
votes
2answers
3k views

a Deep Learning approach that can calculate distance to obstacles

After reading the most famous object detection CNN based methods : YOLO ,YOLO 9000, r-cnn, faster r-cnn...., I was wondering if there is an architecture that can calculate the distance to the ...
1
vote
2answers
84 views
14
votes
3answers
6k views

Is there a person class in ImageNet? Are there any classes related to humans?

If I look at one of the many sources for the Imagenet classes on the Internet I cannot find a single class related to human beings (and no, harvestman is not someone who harvests, but it's what I knew ...
3
votes
1answer
716 views

How to apply my deep learning model to a new dataset?

I am doing semantic segmentation (multi-class classification of image pixels) using convolutional neural networks (CNN) in Keras. In particular, I am applying this to aerial images of crops (...
8
votes
1answer
17k views

Can the number of epochs influence overfitting?

I am using a convolution neural network ,CNN. At a specific epoch, I only save the best CNN model weights based on improved validation accuracy over previous epochs....
14
votes
1answer
11k views

back propagation in CNN

I have the following CNN: I start with an input image of size 5x5 Then I apply convolution using 2x2 kernel and stride = 1, that produces feature map of size 4x4. Then I apply 2x2 max-pooling with ...
5
votes
3answers
3k views

Faster-RCNN how anchor work with slider in RPN layer?

I am trying to understand the whole Faster-RCNN, From https://www.quora.com/How-does-the-region-proposal-network-RPN-in-Faster-R-CNN-work Then a sliding window is run spatially on these feature ...
2
votes
1answer
828 views

Layer notation for convolutional neural networks

When reading about convolutional neural networks (CNNs), I often come across a special notation used in the community and in scientific papers, describing the architecture of the network in terms of ...
3
votes
2answers
737 views

What is the state-of-the art ANN architecture for MNIST?

What is actually the best neural network architecture for the classic MNIST digit classifying task? I couldn't find any that would claim to be the winner...
3
votes
0answers
450 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 ...
8
votes
4answers
14k views

how to get predicted class labels in convolution neural network?

I have built a convolutional neural network which is needed to classify the test data into either 0 or 1. I am training the CNN with labels either 0 or 1 but while running the below code I am getting ...
4
votes
2answers
3k views

Should there be a flat layer in between the conv layers and dense layer in YOLO?

Should there be a flat layer in between the conv layers and dense layer in YOLO? It's something not specified in the paper, but I see most implementations of YOLO on github do this. In my ...
1
vote
2answers
1k views

How to understand conv layer to another same conv layer in VGG16?

VGG16 struct is: ...
3
votes
1answer
8k 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 ...
1
vote
0answers
43 views

What principle is behind semantic segmenation with CNNs?

I have been learning about segmentation models recently and was reading this paper today: Dense Transformer Networks. On page 2, it describes segmentation as: Given the success of deep learning ...
1
vote
1answer
102 views

Doing a fine tuning after a transfer learning

I red about fine tuning and transfer learning for CNNs and I 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 ...
7
votes
4answers
15k views

how to calculate the output shape of conv2d_transpose?

Currently I code a GAN to generate MNIST numbers but the generator doesnt want to work. First I choose z with shape 100 per Batch, put into a layer to get into the shape (7,7, 256). Then ...