Devashish Prasad

We don't remove the unwanted lines, rather we generate more lines in post processing module for border-less tables. You can find the post-processing modules in table structure recognition folder in...

@kshitijkapadni if you can have a look at this issue.

The model training is resuming from epoch 36 and in config file it is **total_epochs = 36**. So training has already reached its limit. You need to change the **total_epochs=50**...

You need to follow the pipeline. After this, you have to perform [Table Structure recongition](https://github.com/DevashishPrasad/CascadeTabNet/tree/master/Table%20Structure%20Recognition) Please Note, the results shown in that image are not derived using Cascadetabnet, we produced...

`weights = np.load('mtcnn_pytorch/src/weights/pnet.npy',allow_pickle=True)[()]` I did the same but still get the error

Thank you for the response knightlibra I was running the script in Google Colab, I refreshed the runtime and error was gone. It seems the changes were not reflected in...

Hello, First of all Thank you for this great repository, great work And, I could not find the face alignment code and implemented it myself I created an align() method...

"adding encoding="utf-8" in the call to open() resolved it." This worked for me as well. Thank you @Pcb21

This is happening because of version issues. You may find some solutions [here](https://stackoverflow.com/questions/39475125/compatibility-issue-with-contourarea-in-opencv-3)

Please go through the following link https://stackoverflow.com/questions/39475125/compatibility-issue-with-contourarea-in-opencv-3 In Opencv 3 API version the cv2.findContours() returns 3 objects Check you Opencv version