deconvolution

Here is my problem: I am going to process data coming from a system for which I will have a good idea of the impulse response. Having used Python for some basic scripting before, I am getting to know the scipy.signal.convolve and scipy.signal.deconvolve functions. In order to get some confidence in my final solution, I would like to understand their requirements and limitations. I used the following test: 1. I built a basic signal made of two Gaussians. 2. I built a Gaussian impulse response. 3. I convolved my initial signal with this impulse response. 4. I deconvolved this convolved signal. 5

In the paper 'Fully Convolutional Networks for Semantic Segmentation' the author distinguishes between input stride and output stride in the context of deconvolution. How do these terms differ from each other? Input stride is the stride of the filter . How much you shift the filter in the output . Output Stride this is actually a nominal value . We get feature map in a CNN after doing several convolution , max-pooling operations . Let's say our input image is 224 * 224 and our final feature map is 7*7 . Then we say our output stride is : 224/7 = 32 (Approximate of what happened to the image

weights = tf.placeholder("float",[5,5,1,1]) imagein = tf.placeholder("float",[1,32,32,1]) conv = tf.nn.conv2d(imagein,weights,strides=[1,1,1,1],padding="SAME") deconv = tf.nn.conv2d_transpose(conv, weights, [1,32,32,1], [1,1,1,1],padding="SAME") dw = np.random.rand(5,5,1,1) noise = np.random.rand(1,32,32,1) sess = tf.InteractiveSession() convolved = conv.eval(feed_dict={imagein: noise, weights: dw}) deconvolved = deconv.eval(feed_dict={imagein: noise, weights: dw}) I've been trying to figure out conv2d_transpose in order to reverse a convolution in Tensorflow. My understanding is that

I have two images o1 & o2 , and I have blurred the two images using the same Gaussian blurring kernel. Then I have found kernel k1 = DFT(b1) / DFT (o1) , where b1 is the image obtained by blurring o1 . I have used this kernal ( k1 ) to perform deconvolution on b2 , where b2 is obtained by blurring o2 . But deblurred output is not correct (the output image does not have any relation with original) what is the problem in my code ? int main(int argc, char** argv) { Mat orig1 = imread(argv[1], 0); Mat orig2 = imread(argv[2], 0); Mat blur1, blur2; GaussianBlur(orig1, blur1, Size(11, 11), 0, 0 );

I am trying to implement a convolutional neural netwrok and I don't understand why using im2col operation is more efficient. It basically stores the input to be multiplied by filter in separate columns. But why shouldn't loops be used directly to calculate convolution instead of first performing im2col ? Well, you are thinking in the right way, In Alex Net almost 95% of the GPU time and 89% on CPU time is spent on the Convolutional Layer and Fully Connected Layer. The Convolutional Layer and Fully Connected Layer are implemented using GEMM that stands for General Matrix to Matrix