Bringing-Old-Photos-Back-to-Life

Bringing-Old-Photos-Back-to-Life copied to clipboard

Can't get global restoration to work.

15

I keep getting `Mapping: You are using the mapping model without global restoration.` despite having unzipped the checkpoints correctly. Any idea why?

acc3d

how does it run witn option --GPU -1

1

Hello! i run this option on M1 macbook, but it shows: "Torch not compiled with CUDA enabled" how can i fix this problem thanks

wenbuliaoyi

Supports the restoration of high-resolution input broken?

1

Trying to process HR images 1974 x 2707 (top) and 1461x 2026 (bottom) using Colab. Restored images have noticeable defects. It looks like generated masks still low-res. If I lower...

semel1

Fix the the type cast error, issue #214

5

Without the change, there will be an error: numpy.core._exceptions.UFuncTypeError: Cannot cast ufunc 'multiply' output from dtype('float64') to dtype('uint8') with casting rule 'same_kind' [](https://github.com/microsoft/Bringing-Old-Photos-Back-to-Life/issues/214)

ruanqizhen

大家知道“Bringing Old Photos Back to Life”中GlobalGenerator_v2和ui_model的怎么定义？

shumile66

Don't know how to train VAE_B_scratch

CodeMadUser

output of domain B network varies in color

4

Hi I decided to start to train the domain B networtk first, beacause it seems to be the most easy part But I found there are usually color shifts on...

MengXinChengXuYuan

Can you release the training log ?

8

Can you release the training log (the loss log ),so i can track the training process.

maryhh

Traing the mapping with scratches

3

When I perform"python train_mapping.py --no_TTUR --NL_res --random_hole --use_SN --correlation_renormalize --training_dataset mapping --NL_use_mask --NL_fusion_method combine --non_local Setting_42 --use_v2_degradation --use_vae_which_epoch 200 --continue_train --name mapping_scratch --label_nc 0 --loadSize 256 --fineSize 256 --dataroot [your_data_folder]...

Estherisok666

fix: typo spelling grammar

1

fix typo speling grammar on documentation

slowy07