YiYi Xu

> Hi: so cifar10 contains tiny pictures `32x32` - it is naturally going to look blurry if you resize to `128x128`

https://github.com/google/automl/blob/master/efficientnetv2/main_tf2.py#L256 ```python for stage in range(total_stages): ratio = float(stage + 1) / float(total_stages) start_epoch = int( float(stage) / float(total_stages) * config.train.epochs) end_epoch = int(ratio * config.train.epochs) image_size = int(ibase +...

I saw many people complain about `cifar10` output being blurry here - just curious did you change 'image_size' to `32`? by default it resize the training data to 128 and...

see paper here https://arxiv.org/abs/2208.04202

@patrickvonplaten @pcuenca Can I work on this? I went through this model during my break and want to give it a try. If it's ok with you I will open...

Thanks @pcuenca @patrickvonplaten! I'm excited to work on this. I will start with the Unet. I've started to go through `UNet2DConditionModel` in detail and will compile a list of changes...

so far I've found 4 changes we need to make to `UNet2DConditionModel`. listing here and I will go over them in detail: 1. the process to create `emb` 2. the...

yes it make sense. Thanks! @patrickvonplaten I had this goal in mind that I want to change as little code as possible - I guess what we actually want here...

@patrickvonplaten One more summary/questions and I think I'm ready to start implementing this :) Here are 3 basic abstractions that compose the downsample and upsample blocks in upscaler `Unet`, and...

thanks @pcuenca I think it's an excellent suggestion! I'd like to use the existing API for blocks but I can wait to do that after I get everything working:)