OwalnutO

Can't download the caption dataset

3

Dear experts I still have problem with the dataset "flowers_text_c10.tar.bz2" that I can't download it. It is hard for me to solve it with repo according to your explanation in...

How to download checkpoint_VOC_efficientdet-d1_34.pth

1

Hi, everyone~ It seems that the url for downloading the pretrained weights is broken. So how can I download the pretrained model checkpoint_VOC_efficientdet-d0_268.pth or checkpoint_VOC_efficientdet-d1_34.pth? Thanks!

How to select pretrained G epoch when training the full model

1

Thanks for your brilliant code. When I try to train a full model as you suggested: "# full (need a pretrained pose transfer model without pixel warping)" How do I...

I want use the code to train a model on my owen dataset. But I'm not sure about how to modify the code if I want to generate image with...

The code writting is SO COMFORTABLE for me, very brilliant work!

Wired loss and reconstruction results when training the autoencoder

4

I'm trying to train the AE on my own dataset (~10w) with the default config file autoencoder_kl_32x32x4.yaml. I only decrease the learning rate from 4.5e-6 to 1e-6 since I use...

Too large loss value, both G and D

7

I reproduce the main code with tf.slim and try to train a wgan-gp model on my own dataset, image size is 128*128. But I get very large loss values during...

Thanks for your implementation However, would you mind to share the code for R-precision score calcation in your paper? Thanks~

Thanks for your codes~ It's very easy to read. My question is how to draw all strokes in the canvases which have the same predifined image size. As the codes...