BasicSR

BasicSR copied to clipboard

issues in training the ESRGAN code for x2 upscaling

1

i am trying to train the ESRGAN model for x2 upscaling factor but it is given me error. I have installed the Basicsr module using the" Install from a local...

shashikantdeepak

XLA support

1

I'm working on this for my own use, so I can train in Google Cloud TPU instances. So far I've done the minimum adjustments necessary to make it work for...

pcuenca

Upload is controlled by a new option `logger`/`wandb`/`log_model`. When enabled, model files are uploaded to W&B as artifacts attached to the current run, at the frequency specified by `save_checkpoint_freq`. I'm...

pcuenca

This is useful for users that belong to several W&B teams.

pcuenca

No module name : torch

1

While using the package in GfpGan to deploy on Heroku. Getting torch module not find error.

tumunshaily

I tried with different module sets to install the package with CUDA c++ extension code but couldn't build it with C++ extension compiled during installation. How can I install BasicSR...

varghaei

Multiples of 96 / 384 ESRGAN

1

So I am using BasicSR to upscale the output of Wav2Lip to a more usable size. By training my own model every use gives me accurate teeth and eyes and...

davidvfx07

Colab Implementation. PLEASE HELP WITH IMPLEMENTATION OF EDVR

2

Apparently, I am trying since a week to implement EDVR algorithm on colab, but as the documentation is really intricate to understand, I am just not getting it. If possible,...

jaivanti

Any suggestions on supporting FID using METRIC_REGISTRY?

4

Hi @xinntao, I've been running some test on my latest HiFaceGAN merge. Your project was amazingly easy for development, except the metrics package --- Currently it only supports PSNR and...

Lotayou

训练ESRGAN scale=2的模型报错

1

你好， 训练ESRGAN scale=2的模型报错，报错信息如下： **/data1/lishaoxiong/sr/ESRGAN/BasicSR/basicsr/losses/losses.py:16: UserWarning: Using a target size (torch.Size([2, 3, 128, 128])) that is different to the input size (torch.Size([2, 3, 256, 256])). This will likely lead to incorrect...

xiaoxiongli