ConvE | ConvE proposed by Dettmers et al | Machine Learning library

As fmw42 suggested, you need to restrict the problem more. There are way too many variables to build a "works under all circumstances" solution. A possible, very basic, solution would be to try and get the convex hull of the page.

Another, more robust approach, would be to search for the four vertices of the corners and extrapolate lines to approximate the paper edges. That way you don't need perfect, clean edges, because you would reconstruct them using the four (maybe even three) corners.

To find the vertices you can run Hough Line detector or a Corner Detector on the edges and get at least four discernible clusters of end/starting points. From that you can average the four clusters to get a pair of (x, y) points per corner and extrapolate lines using those points.

That solution would be hypothetical and pretty laborious for a Stack Overflow question, so let me try the first proposal - detection via convex hull. Here are the steps:

1. Threshold the input image
2. Get edges from the input
3. Get the external contours of the edges using a minimum area filter
4. Get the convex hull of the filtered image
5. Get the corners of the convex hull

Let's see the code:

I've been waiting for answers, but i couldn't even get a comment. I figured out myself the solution, maybe this can help someone in the future.

When you apply one-hot-encoding for binary classification these metrics mess up. Here is an example:

Your labels looks like this after one hot encoding: [ ... [1,0], [0,1], [1,0] ... ]

If you pay attention your TP equals TN. When it is correctly predicted as class 0, it is TP for class 0, also TN for class 1. That's why they are equal.

Don't apply one hot encoding and change:

When you use OpenCV's imshow(), it needs to be followed with a call to waitKey(). The HighGUI's event loop wont run until waitKey() is called.

In your case, the process gets to the end, meaning the programme ends, and so the window you create is immediately destroyed.

You should have a look at darknet_images.py and darknet_video.py in the darknet repo.

Thank for the details.
For this issue I would try to convert each line separately and stream that through your process:

Simply cast the string to the enum type.

You should get the neural network out of DataParallel first.

Assuming your DataParallel is named model you could do:

this will work

I don't know It's me or Pytorch but the error message is trying to say convert into float somehow. Therefore I in forward pass I resolved the problem by converting dataX to float as following: outputs = model(dataX.float())