search

foamliu / Deep-Image-Matting-PyTorch

Deep Image Matting implementation in PyTorch
MIT License
820 stars 185 forks source link

my own datasets are all full human body images #38

Closed lfxx closed 4 years ago

lfxx commented 4 years ago

Hi,thanks for your excellent work.Now i prepare my own datasets.This datasets are consists of thounds of high resolution image(average 4000*4000).They are all full human body images.When i process these images,i meet a questions: When i crop the trimap(generated from alpha),often crop some places which are not include hair.Such as foot,leg.Is it ok to input these images into model?@foamliu

lfxx commented 4 years ago

Hi,thanks for your excellent work.Now i prepare my own datasets.This datasets are consists of thounds of high resolution image(average 4000*4000).They are all full human body images.When i process these images,i meet a questions: When i crop the trimap(generated from alpha),often crop some places which are not include hair.Such as foot,leg.Is it ok to input these images into model?@foamliu

i tried to train the model using those samples,find that model hard to converage.In my opinion,the images inputted to model must include hair.Am i right?

polly-morphism commented 4 years ago

Hi,thanks for your excellent work.Now i prepare my own datasets.This datasets are consists of thounds of high resolution image(average 4000*4000).They are all full human body images.When i process these images,i meet a questions: When i crop the trimap(generated from alpha),often crop some places which are not include hair.Such as foot,leg.Is it ok to input these images into model?@foamliu

i tried to train the model using those samples,find that model hard to converage.In my opinion,the images inputted to model must include hair.Am i right?

Hi. I have a similar dataset (2k full body images with masks 2.5k*3k pixels). Were you able to successfully train the model? I don't have hair in my dataset at all. How long did it take to train the model? What GPU did you use? I will be so grateful for any information)

xiankgx commented 4 years ago

These CNN models are usually not trained on full sized images. For 2k images, and around 50 epochs, training will probably only take a few hours on a GPU.

xiankgx commented 4 years ago

If you don't mind, can you share your dataset?

foamliu commented 4 years ago

The model is highly dependent on trimaps.