convolution

问题 I would like to compute circular convolution of Input Concentration values with Output concentration equation and plot accordingly, following are my functions The function for Input Concentration is computed as follows and the plot of Concentration Vs time is plotted function c = Input_function(t, a1, a2, a3, b1, b2, b3, td, tmax) c = zeros(size(t)); ind = (t > td) & (t < tmax); c(ind) = (t(ind) - td) ./ (tmax - td) * (a1 + a2 + a3); ind = (t >= tmax); c(ind) = a1 * exp(-b1 * (t(ind) - tmax))

问题 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? 回答1: 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

问题 So I am aware that a convolution by FFT has a lower computational complexity than a convolution in real space. But what are the downsides of an FFT convolution? Does the kernel size always have to match the image size, or are there functions that take care of this, for example in pythons numpy and scipy packages? And what about anti-aliasing effects? 回答1: FFT convolutions are based on the convolution theorem, which states that givem two functions f and g , if Fd() and Fi() denote the direct

问题 Say we have a single channel image (5x5) A = [ 1 2 3 4 5 6 7 8 9 2 1 4 5 6 3 4 5 6 7 4 3 4 5 6 2 ] And a filter K (2x2) K = [ 1 1 1 1 ] An example of applying convolution (let us take the first 2x2 from A) would be 1*1 + 2*1 + 6*1 + 7*1 = 16 This is very straightforward. But let us introduce a depth factor to matrix A i.e., RGB image with 3 channels or even conv layers in a deep network (with depth = 512 maybe). How would the convolution operation be done with the same filter ? A similiar

问题 import numpy as np import tensorflow as tf X_node = tf.placeholder('float',[1,10,1]) filter_tf = tf.Variable( tf.truncated_normal([3,1,1],stddev=0.1) ) Xconv_tf_tensor = tf.nn.conv1d(X_node, filter_tf,1,'SAME') X = np.random.normal(0,1,[1,10,1]) with tf.Session() as sess: tf.global_variables_initializer().run() feed_dict = {X_node: X} filter_np = filter_tf.eval() Xconv_tf = sess.run(Xconv_tf_tensor,feed_dict) Xconv_np = np.convolve(X[0,:,0],filter_np[:,0,0],'SAME') I am trying to see the

问题 import numpy as np import tensorflow as tf X_node = tf.placeholder('float',[1,10,1]) filter_tf = tf.Variable( tf.truncated_normal([3,1,1],stddev=0.1) ) Xconv_tf_tensor = tf.nn.conv1d(X_node, filter_tf,1,'SAME') X = np.random.normal(0,1,[1,10,1]) with tf.Session() as sess: tf.global_variables_initializer().run() feed_dict = {X_node: X} filter_np = filter_tf.eval() Xconv_tf = sess.run(Xconv_tf_tensor,feed_dict) Xconv_np = np.convolve(X[0,:,0],filter_np[:,0,0],'SAME') I am trying to see the

问题 Anybody know about the fastest method for calculating convolution? Unfortunately the matrix which I deal with is very large (500x500x200) and if I use convn in MATLAB it takes a long time (I have to iterate this calculation in a nested loop). So, I used convolution with FFT and it is faster now. But, I am still looking for a faster method. Any idea? 回答1: If your kernel is separable, the greatest speed gains will be realized by performing multiple sequential 1D convolutions. Steve Eddins of

问题 Anybody know about the fastest method for calculating convolution? Unfortunately the matrix which I deal with is very large (500x500x200) and if I use convn in MATLAB it takes a long time (I have to iterate this calculation in a nested loop). So, I used convolution with FFT and it is faster now. But, I am still looking for a faster method. Any idea? 回答1: If your kernel is separable, the greatest speed gains will be realized by performing multiple sequential 1D convolutions. Steve Eddins of

问题 i'm trying to apply a box blur to an transparent image, and i'm getting a "dark halo" around the edges. Jerry Huxtable has a short mention of the problem, and a very good demonstration showing the problem happen: But i, for the life of me, cannot understand how " pre-multiplied alpha " can fix the problem. Now for a very simple example. i have a 3x3 image, containing one red and one green pixel: In reality the remaining pixels are transparent: Now we will apply a 3x3 Box Blur to the image.

问题 I am very confused by these two parameters in the conv1d layer from keras: https://keras.io/layers/convolutional/#conv1d the documentation says: filters: Integer, the dimensionality of the output space (i.e. the number output of filters in the convolution). kernel_size: An integer or tuple/list of a single integer, specifying the length of the 1D convolution window. But that does not seem to relate to the standard terminologies I see on many tutorials such as https://adeshpande3.github.io