Stack Exchange Network

Stack Exchange network consists of 175 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 [transposed-convolution]

Transposed convolution (a.k.a. deconvolution) is an upsampling operation in a neural network that works by swapping the forward and backward passes of a convolution.

-1
votes
1answer
20 views

How to use convolutions of pictures instead of FC layers? [closed]

How to use convolutions of pictures instead of FC layers? How can i do this effectively and efficiently.
2
votes
0answers
134 views

How do upsampling layers work for coarse-to-fine output in semantic segmentation?

Here is a figure illustrating the Fully Convolutionnal Network (FCN) of the Fully Convolutionnal Paper for Semantic Segmentation : The upsampling layer at the end confuses me. I cannot understand how ...
1
vote
0answers
129 views

How to add bias in convolution transpose?

My question is regarding the transposed convolution operation (also commonly called deconvolution or upconvolution). In TensorFlow, for instance, I refer to this layer. My question is, how / when do ...
1
vote
1answer
388 views

Concatentation of feature maps in U-net

I am looking at the following snippet of code: ...
1
vote
0answers
41 views

Short Sentence Generation using CNNs

I am investigating whether building a classifier for sentence classification using CNN can be used for sentence generation. Say, we are classifying news articles' titles (classes such as sports, ...
2
votes
0answers
273 views

How to define a loss function for discrete fourier series?

In each batch there are 8000 sample points, and I apply discrete Fourier transform on them. The original samples are real valued, so only the half of the result is needed. The end result is 4000 ...
1
vote
0answers
179 views

How do I model a pixel-wise regression convnet? What kind of loss should I use?

Given an input of (HxWxD), I want to output a confidence map of size (HxW) where each value is a probability. I'll try to be concise. I have 2 inputs: input_image of size (HxWx3) input_map of size (...
10
votes
4answers
12k views

In CNN, does upsampling and transpose convolution the same?

Both the term "upsampling" and "transpose convolution" are used when you are doing "deconvolution" (<-- not a good term, but let me use it here). Originally, I thought they mean the same things, ...
1
vote
0answers
183 views

Using Transposed Convolutions (DeConvolutions) instead of a Dense layer when predicting Depth Maps

I'm using Keras to try and learn how to predict Depth from images. I have the NYU v2 dataset and was playing with some Neural Networks designs to see how each architecture can learn differently. I ...