deblur | deblur images on GPU | GPU library

i saw this video about debluring images using fourier transform in matlab video

and i want to convert the code in emgu cv

my code in emgucv :

I'm trying to deploy my Tensorflow Model using Docker, Tensorflow Serving and Heroku. Everything goes fine, but when the TF Serving Container is ending the initialization (when it outputs "Entering the event loop") the Heroku Web Dyno suddenly crashes. Then it restarts and tries again, but when it reaches the Event Loop again, it crashes. The third time, Heroku simply never spins up the dyno again.

First, I just deploy the image, no problem:

Im building a GAN on Tensorflow for Image Deblurring, its an implementation of DeblurGANv2. I setup the GAN in a way it have two inputs, a batch of blurred images, and a batch of sharp images. Following this lines, I design the input to be a Python Dictionary with two Keys ['sharp', 'blur'], each one have a tensor of shape [batch_size, 512, 512, 3], this make it easy for feed the blurred images batch to the generator, and then feed the output of generator and the sharp images batch to the discriminator.

Based on the last requirements, i create a tf.data.Dataset that outputs exactly that, a dict containing the two tensors, each one with their batch dimension. this complements perfectly with my GAN implementation, everything work fine and smoothly.

So keep in mind, my input is not a tensor, but a python dict, that has no batch dimension, this will be relevant for explain my problem later.

Recently, i decided to add support for distributed training using Tensorflow Distribution Strategies. This feature of Tensorflow allows to distribute the training over multiple devices, inclusively over multiple machines. There is a feature with some of the implementations, for example MirroredStrategy, that takes the input tensor, splits it in equal parts, and feed each slice to different devices, that means, if you have a batch size of 16 and 4 GPUs, each GPU will end taking a local batch of 4 datapoints, after this there is some magic for aggregate the results and other stuff that is not relevant to my problem.

As you already notice, is critical for distribution strategies to have a tensor as input, or at least some sort of input with an exterior batch dimension, and what i have is a Python dict, with the batch dimension of the inputs in the internal dictionary tensor values. This is a huge problem, my current implementation is not compatible with distributed training.

I was looking for workarounds, but i cant wrap my head very well around this, maybe just make the input a huge tensor of shape=[batch_size, 2, 512, 512, 3] and slice it? not sure this just come to my mind right now lol. Anyways i see this very ambiguous, i cant not differentiate the two inputs, at least not with the clarity of the dictionary keys. Edit: The problem with this solution is that make my dataset transformations very expensive, hence makes the dataset throughput lot slower, taking into account this is an image loading pipeline, this is a major point.

Maybe my explanation of how distributed strategies work is not the most rigorous one, if im not seeing something feel free to correct me pls.

PD: This is not a bug question or a code error, mostly a "System Design Query", hope this is not illegal here

Im trying to import the latest rc2 version of Tensorflow (2.2.0rc2 at this date) in Google Colab, but cant do it when installed from my setup.py install script.

When i install Tensorflow manually using !pip install tensorflow==2.2.0rc2 from a Colab cell, everything is ok and im able to import Tensorflow.

The next is how i have my dependencies installation setup in Google Colab:

When i try to install tensorflow>=2.2.0rc0 from setup.py running python setup.py install from a Github Actions Workflow, the output sendme this:

So I have been asked to motion deblur a frame captured from a video, I am kind of new to this deblur filters so need help. The video does not contain any noise, just a vertical motion blur. I am not allowed to use skimage, or any other library except cv2. It would be a great help even if what technique or function I have to use comes to know. Thanks!

Update as suggestion from @Fix that I should BGR to RGB, but the outputs are still not the same as the paper's output.

(Small note: this post already post on https://dsp.stackexchange.com/posts/60670 but since I need help quickly so I think I reposted here, hope this doesn't violate to any policy)

I tried to create synthetic blurred image from ground-truth image using PSF kernels (in png format), some paper only mentioned that I need to do convolve operation on it, but it's seem to be I need more than that. What I did

I have read an article Here and its pretty nice enough to understand. Given its implementation on GitHub. When I am trying to train at my own using given code it gives me an Import Error in this file at line 117 like following. I am using google Colab environment. Having some search over the error i got that the following line is compatible to keras version==2.2.2. I have also installed that yet not solved with the error. Please help me to get over it. By default keras version installed in colab is 2.2.4

I'm working on a program that takes in a video, splits the video into a sequence of images, applies a cleaning filter to the images (denoise/deblur/etc.), then puts it back together into a video.

I wanted to use Scikit Image's "Unsupervised_wiener" restoration on the images to de-blur them, but I haven't been able to get it and I don't understand the documentation.

This is what I have, copied from the documentation: