逗比学长
I config my vscode following this [blog](https://blog.csdn.net/qq_34488177/article/details/88990894) , and I changed the “code run - setting.json” like ``` "cpp": "cd $dir && g++ $fileName -o $fileNameWithoutExt -fopenmp -l msmpi -L...
``` Namespace(activation='elu', baseroot='/data/lifengjun/inpainting_dataset/paris_train_original/', batch_size=4, bbox_shape=30, checkpoint_interval=1, cudnn_benchmark=True, epochs=40, gan_type='WGAN', gpu_ids='0', imgsize=512, init_gain=0.2, init_type='kaiming', lambda_l1=300.0, lambda_perceptual=100.0, latent_channels=32, load_name_d='', load_name_g='', lr_d=0.0004, lr_decrease_epoch=10, lr_decrease_factor=0.5, lr_g=0.0001, margin=10, mask_type='free_form', multi_gpu=False, norm='none', norm1='none', num_workers=16, pad_type='replicate', sample_path='./samples',...
 The paper mentioned that "The first image in each row shows the cluster heads, which are digits generated by fixing the style variable to zero and setting the label...
which is defined on [loss.py](https://github.com/openai/improved-diffusion/blob/main/improved_diffusion/losses.py#L50) and used on [gaussian_diffusion.py](https://github.com/openai/improved-diffusion/blob/main/improved_diffusion/gaussian_diffusion.py#L666) to calculate L[0](seems like)
Thanks for your brilliant work !!! I have a few questions regarding the design of StableSR. It seems that the design of StableSR is similar to [GLEAN](https://arxiv.org/pdf/2012.00739.pdf), which uses a...
Thanks for your brilliant work!!! I have some questions for more details. Are the weights of "vqgan_cfw_00011.ckpt" the same as the weight of encoder-decoder on "v2-1_512-nonema-pruned.ckpt". If it is, have...