deconvolution

问题 The TF documentation has an output_shape parameter in tf.conv2d_transpose. Why is this needed? Don't the strides, filter size and padding parameters of the layer decide the output shape of that layer, similar to how it is decided during convolution? 回答1: This question was already asked on TF github and received an answer: output_shape is needed because the shape of the output can't necessarily be computed from the shape of the input, specifically if the output is smaller than the filter and

问题 I am new to tensorflow for deep learning and interested in deconvolution (convolution transpose) operation in tensorflow. I need to take a look at the source code for operating deconvolution. The function is I guess conv2d_transpose() in nn_ops.py. However, in the function it calls another function called gen_nn_ops.conv2d_backprop_input() . I need to take a look at what is inside this function, but I am unable to find it in the repository. Any help would be appreciated. 回答1: You can't find

问题 I'm trying to understand scipy.signal.deconvolve. From the mathematical point of view a convolution is just the multiplication in fourier space so I would expect that for two functions f and g : Deconvolve(Convolve(f,g) , g) == f In numpy/scipy this is either not the case or I'm missing an important point. Although there are some questions related to deconvolve on SO already (like here and here) they do not address this point, others remain unclear (this) or unanswered (here). There are also

问题 Some one may prefer to call it the transposed convolution, as introduced here. I'm looking forward to an implementation of the transposed convolution, in Python or C/C++. Thank you all for helping me! 回答1: Even I am searching for an implementation of transposed convolution. I could only find one in tensorflow module. I am trying to get this working for my problem. Link to Tensor flow API for transposed convolution If it helps, you can also use the regular 2d convolution to do transposed

问题 I know that original_image * filter = blur_image , where * is the convolution. Thus, filter = ifft(fft(blur)/fft(original)) I have an original image, the known filter, and the known blurred image. I tried the following code. I just want to compare the computed filter using fft and ifft and compare it with the known filter. I tried in Matlab: orig = imread("orig.png") blur = imread("blur.png") fftorig = fft(orig) fftblur = fft(blur) div = fftblur/fftorig conv = ifft(div) The result doesn't

问题 I'm doing an image segmentation with UNet-like CNN architecture by Pytorch 0.4.0.It mark foreground as 1 and background as 0 in the final segmentation result.I use a pre-trained VGG's feature extractor as my encoder, so I need to upsampling the encoder output many times.But the result shows a weird lattice parttern in the result like this: I suspect these different shape of black parttern were caused by the deconvolutional layers.It's said that deconv layer add (s-1) zeros between the input

问题 I am attempting to use tf.nn.conv3d_transpose , however, I am getting an error indicating that my filter and output shape is not compatible. I have a tensor of size [1,16,16,4,192] I am attempting to use a filter of [1,1,1,192,192] I believe that the output shape would be [1,16,16,4,192] I am using "same" padding and a stride of 1. Eventually, I want to have an output shape of [1,32,32,7,"does not matter"], but I am attempting to get a simple case to work first. Since these tensors are

问题 This layer in not ready documented very well and I'm having a bit of trouble figuring out exactly how to use it. I'm Trying something like: input_img = Input(shape=(1, h, w)) x = Convolution2D(16, 7, 7, activation='relu', border_mode='valid')(input_img) d = Deconvolution2D(1, 7, 7, (None, 1, 2*h, 2*w)) x = d(x) but when I try to write d.output_shape , I get the original shape of the image instead of twice that size (which is what I was expecting). Any help will be greatly appreciated! 回答1:

问题 This is a really weird error, partly a follow-up to the previous question(Deconvolution layer FCN initialization - loss drops too fast). However I init Deconv layers (bilinear or gaussian), I get the same situation: 1) Weights are updated, I checked this for multiple iterations . The size of deconvolution/upsample layers is the same: (2,2,8,8) First of all, net_mcn.layers[idx].blobs[0].diff return matrices with floats, the last Deconv layer ( upscore5 ) produces two array with the same

问题 I'm new in image analysis (with Python) and I would like to apply the richardson_lucy deconvolution (from skimage) on my data (CT scans). For this reason, I estimated the PSF in "number of voxels" by means of a specific software. Its value is roughly 6.73 voxels, but I don't know how to use it as a paramter in the function. The function uses the PSF parameter as a ndarray, so I tried in this way: from skimage import io from pylab import array img = io.imread ("Slice1.tif") import skimage