search

pathak22 / context-encoder

[CVPR 2016] Unsupervised Feature Learning by Image Inpainting using GANs
https://www.cs.cmu.edu/~dpathak/context_encoder/
Other
876 stars 204 forks source link

Download random region inpainting model #15

Open cryptedp opened 7 years ago

cryptedp commented 7 years ago

Hi In your paper you mentioned that you have implemented the 3 strategies, namely centre inpainting, random block inpainting and random region inpainting. However there is currently no way to download a inpaintRandomRegin model in t7 format. Can that be provided or does it need to be trained with train_random.lua?

pathak22 commented 7 years ago

Hi @cryptedp ! Yes, Sorry about that. I will have to retrain the train_random.lua and upload the model at some point. I will put on my todo list to run it. However, you can run train own model using train_random.lua on imagenet. Training should be super easy to launch as long as you have Torch and GPU. :)

cryptedp commented 7 years ago

Hi @pathak22 , how can one train it on imagenet and how long would it take ?

maryam089 commented 6 years ago

@pathak22 can you provide already trained model for random region inpainting ?

niloleart commented 6 years ago

@maryam089 @pathak22 does any one of you have a trained model for random region inpainting?

maryam089 commented 6 years ago

Well I spend 6 days and train the model but results were very bad for random region inpaint

pathak22 commented 6 years ago

@maryam089 can you post some results here?

pathak22 commented 6 years ago

@maryam089 Also see #22 (the second picture). Are your results worse than those?

maryam089 commented 6 years ago

I trained your network from strach for random region inpaint at input size 128x128 ... on imageNet 100k ... and results weren’t good then I realized that I should again train it on 64x64 size input.... but as it takes 6 days to train ... so can you provide already trained network of random region inpaint on input size 64x64 ... if possible?