convolution

Fast 2D convolution for DSP

由 限于喜欢 提交于 2019-12-03 07:50:24
问题 I want to implement some image-processing algorithms which are intended to run on a beagleboard. These algorithms use convolutions extensively. I'm trying to find a good C implementation for 2D convolution (probably using the Fast Fourier Transform). I also want the algorithm to be able to run on the beagleboard's DSP, because I've heard that the DSP is optimized for these kinds of operations (with its multiply-accumulate instruction). I have no background in the field so I think it won't be

1d linear convolution in ANSI C code?

由 你说的曾经没有我的故事 提交于 2019-12-03 05:13:39
问题 Rather than reinvent the wheel, I wonder if anyone could refer me to a 1D linear convolution code snippet in ANSI C? I did a search on google and in stack overflow, but couldn't find anything in C I could use. For example, for Arrays A, B, and C, all double-precision, where A and B are inputs and C is output, having lengths len_A , len_B , and len_C = len_A + len_B - 1 , respectively. My array sizes are small and so any speed increase in implementing fast convolution by FFT is not needed.

Difference between Tensorflow convolution and numpy convolution

由 我的未来我决定 提交于 2019-12-03 04:44:31
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 results of convolutions from Tensorflow to check if it is behaving as I intended. When I run the numpy

Keras input_shape for conv2d and manually loaded images

由 ぃ、小莉子 提交于 2019-12-03 04:11:10
I am manually creating my dataset from a number of 384x286 b/w images. I load an image like this: x = [] for f in files: img = Image.open(f) img.load() data = np.asarray(img, dtype="int32") x.append(data) x = np.array(x) this results in x being an array (num_samples, 286, 384) print(x.shape) => (100, 286, 384) reading the keras documentation, and checking my backend, i should provide to the convolution step an input_shape composed by ( rows, cols, channels ) since i don't arbitrarily know the sample size, i would have expected to pass as an input size, something similar to ( None, 286, 384, 1

Hyperparameter Tuning of Tensorflow Model

由 有些话、适合烂在心里 提交于 2019-12-03 03:54:29
问题 I've used Scikit-learn's GridSearchCV before to optimize the hyperparameters of my models, but just wondering if a similar tool exists to optimize hyperparameters for Tensorflow (for instance number of epochs, learning rate, sliding window size etc. ) And if not, how can I implement a snippet that effectively runs all different combinations? 回答1: Another viable (and documented) option for grid search with Tensorflow is Ray Tune. It's a scalable framework for hyperparameter tuning,

For what reason Convolution 1x1 is used in deep neural networks?

由 旧街凉风 提交于 2019-12-03 02:46:37
问题 I'm looking at InceptionV3 (GoogLeNet) architecture and cannot understand why do we need conv1x1 layers? I know how convolution works, but I see a profit with patch size > 1. 回答1: You can think about 1x1xD convolution as a dimensionality reduction technique when it's placed somewhere into a network. If you have an input volume of 100x100x512 and you convolve it with a set of D filters each one with size 1x1x512 you reduce the number of features from 512 to D. The output volume is, therefore,

Simple GLSL convolution shader is atrociously slow

由 不羁岁月 提交于 2019-12-03 02:27:41
问题 I'm trying to implement a 2D outline shader in OpenGL ES2.0 for iOS. It is insanely slow. As in 5fps slow. I've tracked it down to the texture2D() calls. However, without those any convolution shader is undoable. I've tried using lowp instead of mediump, but with that everything is just black, although it does give another 5fps, but it's still unusable. Here is my fragment shader. varying mediump vec4 colorVarying; varying mediump vec2 texCoord; uniform bool enableTexture; uniform sampler2D

Fastest method for calculating convolution

由 谁说胖子不能爱 提交于 2019-12-03 00:08:49
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? chappjc If your kernel is separable, the greatest speed gains will be realized by performing multiple sequential 1D convolutions. Steve Eddins of MathWorks describes how to take advantage of the associativity of convolution to speed up convolution

Is there a equivalent of scipy.signal.deconvolve for 2D arrays?

由 巧了我就是萌 提交于 2019-12-02 23:58:35
I would like to deconvolve a 2D image with a point spread function (PSF). I've seen there is a scipy.signal.deconvolve function that works for one-dimensional arrays, and scipy.signal.fftconvolve to convolve multi-dimensional arrays. Is there a specific function in scipy to deconvolve 2D arrays? I have defined a fftdeconvolve function replacing the product in fftconvolve by a divistion: def fftdeconvolve(in1, in2, mode="full"): """Deconvolve two N-dimensional arrays using FFT. See convolve. """ s1 = np.array(in1.shape) s2 = np.array(in2.shape) complex_result = (np.issubdtype(in1.dtype, np

Gaussian blur and convolution kernels

由 两盒软妹~` 提交于 2019-12-02 22:51:59
I do not understand what a convolution kernel is and how I would apply a convolution matrix to pixels in an image (I am talking about doing a Gaussian Blur operation on an image). Also could I get an explanation on how to create a kernel for a Gaussian Blur operation? I am reading this article but I cannot seem to understand how things are done... Thanks to anyone who takes time to explain this to me :), ExtremeCoder The basic idea is that the new pixels of the image are created by an weighted average of the pixels close to it (imagine drawing a circle around the pixel). For each pixel in the
订阅 convolution