minar09 / cp-vton-plus

Official implementation for "CP-VTON+: Clothing Shape and Texture Preserving Image-Based Virtual Try-On", CVPRW 2020
https://minar09.github.io/cpvtonplus/
MIT License
355 stars 122 forks source link

why the size is must be crop/resize to 192 x 256 #83

Open Testhjf opened 2 years ago

Testhjf commented 2 years ago

@minar09 hello ,i have question ,why the size is must be crop/resize to 192 x 256?if i use bigger size as input image ,the network can be work well?

minar09 commented 2 years ago

Hi, @Testhjf , the current model is trained and designed for this fixed resolution. If you need a different size, you need to re-design and re-train the model.

Testhjf commented 2 years ago

@minar09 thanks

greykoalacode commented 2 years ago

@minar09 Hello I am a beginner in Machine learning, can you help me in actually trying this project locally ? The steps mentioned in readme.md seemed little above

syedhaideralizaidi commented 8 months ago

@minar09 What do you mean by redesign, can't we just train the model on bigger size input? or do we need to make some changes in code too, to accept bigger images and give us as an output?