Closed NikitaKononov closed 2 years ago
Hi @NikitaKononov,
We only use 256x images for the pressure of computation. If you want to use larger images, you can consider adding several downsampling convolutional layers at the beginning of the network.
@harlanhong Thanks! So I should retrain model with additional layers? Or adding downsampling layers doesn't require model retraining? I am sorry, if my question is silly :)
If you add additional layers, you should retrain the whole network.
Hello Thanks for your great work! I have a question, does your model support input resolution higher, than 256px? 512px for example I see that in code input video and image are resized to 256px, so causes the loss of visual quality Is there a way to use 512x512 img/vid without losing quality?