search

Canjie-Luo / Text-Image-Augmentation

Geometric Augmentation for Text Image
MIT License
480 stars 89 forks source link

About Joint Training #10

Open DongfeiJi opened 4 years ago

DongfeiJi commented 4 years ago

Thanks for your work, but I am wondering how to joint training, which is mentioned in the paper (Algorithm 1 Joint Learning Scheme).

yanfjz commented 3 years ago

I have two related questions as well:

  1. Is the "moving state" S the deltas between src_pts and dst_pts (src_pts - dst_pts) which contains 2(N+1) points?
  2. Is the loss function for joint learning cross-entropy loss? If so, what is the representation of GT for this loss function? Any explanation/idea/suggestion/discussion is welcomed :)
Canjie-Luo commented 3 years ago

@DongfeiJi This version is the default random augmentation. We guess it is sufficient for practical use.

Canjie-Luo commented 3 years ago

@yanfjz

  1. The "moving state" denotes the moving directions.
  2. Yes, we use cross-entropy loss. The GT is the moving state that increases difficulty.
zdz1997 commented 3 years ago

@Canjie-Luo I read the paper Learn to Augment: Joint Data Augmentation and Network Optimization for Text Recognition.
and I'm so interested in joint training (Algorithm 1 Joint Learning Scheme)，can I ask for the whole code of paper?There is something I can't understand and I want to retrain it .I'll appreciate it very much .Here's my email zdz1954@126.com

DaeHwanGi commented 3 years ago

@Canjie-Luo

I have some questions about the paper.

  1. Output size of the agent network is 2x(N+1)x2x2. Isn't just two coordinates enough to predict the direction of each point?
  2. In Algorithm 1, randomly select one point in S and switch to the opposite direction to make S prime. Does this mean choosing one moving state in a mini-batch?
shubham303 commented 2 years ago

I read the paper Learn to Augment: Joint Data Augmentation and Network Optimization for Text Recognition. and I'm so interested in joint training (Algorithm 1 Joint Learning Scheme)，can I ask for the whole code of paper? my email: cs20m064@smail.iitm.ac.in

firatkizilirmakk commented 2 years ago

@shubham303 Have you got the code?

I would be glad to get joint training code as well. my email: firatkizilirmak34@gmail.com

Thanks in advance!

matiascoronados commented 1 year ago

@shubham303
I would really appreciate if you can share that code with me!

my email: matias.coronado@usach.cl

Thanks :)

shubham303 commented 1 year ago

@matiascoronados I don't have the code.

Canjie-Luo commented 1 year ago

Hey guys, due to the intellectual property protocol, I cannot release the code.