Nishant Singh

What is the range of pixels in images that was used for training the models: a.) [0 to 255]. b.) [0 to 1]. c.)[-1 to 1]. I'm trying the train...

Embeddings are getting clustered together in a small region after training

2

Hi @tamerthamoqa, Thanks a lot for such a fantastic repo which we could use for our work. I was recently working on building a Face verification system using Siamese network....

Understanding the Model Architecture

2

What will happen and what kind of results do we get if we have a window size of more than one and switch the model to spatial architecture ?

Th following link in the "https://lanytek.com/models/{model_file_name}" is not working and throwing assertion error through download_to_memory function in lanyocr_utils.py 1 .) model_file_name = "lanyocr-en-ppocrv3-det.onnx" link : https://lanytek.com/models/lanyocr-en-ppocrv3-det.onnx 2.) model_file_name = "lanyocr-en-ppocrv3.onnx"...