tps_stn_pytorch

tps_stn_pytorch copied to clipboard

学长方便问问您，如果只想利用前面的tps部分让图片旋转，损失函数应该怎么取比较合适呢

mcshuishui

zhangzherui123

关于localization network的初始化问题

1

你好，很感谢你的工作。关于一篇论文《Robust scene Text recognition with automatic rectification》里面提到了得到tps的控制点 初始化时，有时候随机初始化时不work的，网络训练不会收敛。想问一下这个是什么情况呢？

aiboys

Awesome for your repo I have a question: I warped my image with grid point and noisy point and it work perfect. When i have many points on original image...

viet24dung

index shouldn't be a tensor,it should be int type, otherwise, it will report a error: > KeyError: tensor(x)

freepoet

run python mnist_visualize.py --model unbounded_stn --angle 90 --grid_size 4 error

3

hello! when I run python mnist_visualize.py --model unbounded_stn --angle 90 --grid_size 4, it appears following: create model with STN Traceback (most recent call last): File "mnist_visualize.py", line 47, in data_list...

KakaVlasic

run the training on wider input images (width=height>>28)

3

great project! i succeeded to run the code on my own images with input size=28. I was trying to run the code using a different input size (e.g widht=height=300) As...

kao123

Hi, Thanks for sharing the code. It’s very helpful for my own research project. Is it possible to add a license (Eg MIT) so that I can properly cite your...

hfslyc

liuzhuang1024

liuzhuang1024