## paper summary: “BROS: A Pre-trained Language Model Focusing on Text and Layout for Better Key Information Extraction from Documents”

arxiv: https://arxiv.org/abs/2108.04539 key points use text and spatial information. doesn’t utilize image feature a better spatial information encoding method compared to LayoutLM propose new pretraining task: Area Masked Language Model spatial information encoding method For each text box, get four Read more…

## list of python double underscores

https://docs.python.org/3/reference/datamodel.html

## paper summary “Perceiver IO: A General Architecture for Structured Inputs & Outputs”

arxiv: https://arxiv.org/abs/2107.14795 Key points developing upon the Perceiver idea, Perceiver IO proposes a Perceiver like structure but where output size can be much larger and still keep overall complexity linear. (Checkout summary on Perceiver here) same with Perceiver, this work use latent array Read more…

## paper summary: Swin Transformer: Hierarchical Vision Transformer using Shifted Windows

arxiv: https://arxiv.org/abs/2103.14030 Key points multi scale feature extraction. Could think of as adoption of FPN idea. restrict transformer operation to within each window and not the entire feature map → allows to keep overall complexity linear instead of quadratic apply shifted Read more…

## qtwindeploy output missing ‘libgcc_s_seh-1.dll’ error fix

While deploying qt in windows, the official docs recommend using windeployqt.exe However, once the outputs of windeployqt.exe are packaged and executed in a different machine without any qt installments, I encountered “msising libgcc_s_seh-1.dll” error. Solution When I ran windeployqt.exe, I Read more…

## Paper summary: “Perceiver : General Perception with Iterative Attention”

arxiv: https://arxiv.org/abs/2103.03206 key points use learnable latent array with a fixed size as query in transformer module in perceiver architecture raw inputs can be long since it will be use as key and value in transformer module do cross attention to Read more…

## fix ‘certificate apiserver-kubelet-client not signed by CA certificate ca: crypto/rsa: verification error’ error during minikube start

I tried some solutions from here but it did not work. I deleted ~/.kube directory and it just made matters worse. My solution is The ~/.kube directory was restored after doing this. I guess minikube takes care of initial .kube Read more…

## “ValueError: numpy.ndarray size changed, may indicate binary incompatibility.” error fix

After installing packages with python and running a torch training script, I encountered the following error. This error occurred in pycocotools package which was used by detectron2 package. My solution was to reinstall pycocotools package with special options. after this Read more…

## visual code debug configuration variables

from the official docs: https://code.visualstudio.com/docs/editor/variables-reference Predefined variables The following predefined variables are supported: ${workspaceFolder} – the path of the folder opened in VS Code${workspaceFolderBasename} – the name of the folder opened in VS Code without any slashes (/) \${file} – the current Read more…

## paper summary: “VarifocalNet: An IoU-aware Dense Object Detector”(VFNet)

arxiv: https://arxiv.org/abs/2008.13367 key points another anchor-free point based object detection network introduce new loss, varifocal loss which is a forked version from focal loss. Makes some changes from focal loss to compensate positive/negative imbalance futher. instead of prediction classification and Read more…