aditya1709
aditya1709
Logic tells me that both these counts should have a considerable affect on the mAP value. However only true positive seems to matter when I run this code. Even when...
board.resize only works when width changes, but when the height of the browser window changes the chess board is not resized. Is there a way to achieve this?
I tried converting the EfficientNet-b4 model to TensorRT for optimized inference. It looks like there are some layers that don't have converters implemented and throws - AttributeError: 'Tensor' object has...
I tried only the STN head with TPS for just rectification and this was the output.  Can someone please suggest why this would be happening? Should I be changing...
Has anyone tried to train SqueezeDet from scratch? If yes how long does it take to converge? I have some multimodal features I am using hence cannot use the ImageNet...
Why is the IoU layer associated with a batch size? Is there a way to make it independent of the batch size? It prevents us from analyzing the learned model...
Just a little confused on how the network would function. If I used the pre-trained model on say a video recording of the shoe that I just made would it...
Is there any method to rectify curved text polygons to straightened text bounding box to ease the recognition process?
The labels being generated in pascal_voc.py in load_pascal_annotation() - 1. The standard being followed in the paper is [x,y,w,h,c] where c is the confidence score. This is not being followed...
The paper mentions visualizing general CNN features as well, is the code for the same available?