wzhouxiff / restoreformerplusplus Goto Github PK

When will the code release

When the version of Basicsr is 1.4.2, "ModuleNotFoundError: No module named 'basicsr.losses.losses'"

When the version of Basicsr is 1.3.5, "RestoreFormer/modules/losses/vqperceptual.py", line 60. TypeError: '>' not supported between instances of 'ListConfig' and 'int'", I saw that in the RestoreFormerPlusPlus.yaml file, comp_weight is a list, It should be an int?

Hi, thanks for your remarkable work. I've several questions as follows:

1. How many epochs was the RestoreFormer++ model trained?

2. How long does it take to train the RestoreFormer++ model？

Thanks again and look forward to your feedback.

In the image degradation process, we use a mask map M. I want to know how this mask is generated, the code needs to directly provide the path of the mask.

Can you release the training weight of ROHQD?
And what is the epoch of training, the training epoch is not seen in the code and the paper, and the code defaults to training epoch to 1000.
Thanks for your help！

When I run sh scripts/run.sh:

(restore) F:\Users\liu'hao\Desktop\VIT键值对\RestoreFormerPlusPlus-main\RestoreFormerPlusPlus-main>sh scripts/run.sh
Running on GPUs 0,
Working with z of shape (1, 256, 16, 16) = 65536 dimensions.
D:\Anaconda\envs\restore\lib\site-packages\torch\utils\cpp_extension.py:322: UserWarning: Error checking compiler version for cl: [WinError 2] 系统找不到指定的文件。
warnings.warn(f'Error checking compiler version for {compiler}: {error}')
信息: 用提供的模式无法找到文件。
Traceback (most recent call last):
File "F:\Users\liu'hao\Desktop\VIT键值对\RestoreFormerPlusPlus-main\RestoreFormerPlusPlus-main\main.py", line 467, in
model = instantiate_from_config(config.model)
File "F:\Users\liu'hao\Desktop\VIT键值对\RestoreFormerPlusPlus-main\RestoreFormerPlusPlus-main\main.py", line 152, in instantiate_from_config
return get_obj_from_str(config["target"])(**config.get("params", dict()))
File "F:\Users\liu'hao\Desktop\VIT键值对\RestoreFormerPlusPlus-main\RestoreFormerPlusPlus-main\RestoreFormer\models\vqgan_v1.py", line 26, in init
self.loss = instantiate_from_config(lossconfig)
File "F:\Users\liu'hao\Desktop\VIT键值对\RestoreFormerPlusPlus-main\RestoreFormerPlusPlus-main\main.py", line 152, in instantiate_from_config
return get_obj_from_str(config["target"])(**config.get("params", dict()))
File "F:\Users\liu'hao\Desktop\VIT键值对\RestoreFormerPlusPlus-main\RestoreFormerPlusPlus-main\main.py", line 20, in get_obj_from_str
return getattr(importlib.import_module(module, package=None), cls)
File "D:\Anaconda\envs\restore\lib\importlib_init_.py", line 127, in import_module
return _bootstrap._gcd_import(name[level:], package, level)
File "", line 1030, in _gcd_import
File "", line 1007, in _find_and_load
File "", line 986, in _find_and_load_unlocked
File "", line 680, in load_unlocked
File "", line 850, in exec_module
File "", line 228, in call_with_frames_removed
File "F:\Users\liu'hao\Desktop\VIT键值对\RestoreFormerPlusPlus-main\RestoreFormerPlusPlus-main\RestoreFormer\modules\losses\vqperceptual.py", line 6, in
from basicsr.losses.basic_loss import L1Loss
File "D:\Anaconda\envs\restore\lib\site-packages\basicsr_init.py", line 3, in
from .archs import *
File "D:\Anaconda\envs\restore\lib\site-packages\basicsr\archs_init.py", line 16, in
arch_modules = [importlib.import_module(f'basicsr.archs.{file_name}') for file_name in arch_filenames]
File "D:\Anaconda\envs\restore\lib\site-packages\basicsr\archs_init.py", line 16, in
arch_modules = [importlib.import_module(f'basicsr.archs.{file_name}') for file_name in arch_filenames]
File "D:\Anaconda\envs\restore\lib\importlib_init.py", line 127, in import_module
return _bootstrap.gcd_import(name[level:], package, level)
File "D:\Anaconda\envs\restore\lib\site-packages\basicsr\archs\basicvsrpp_arch.py", line 7, in
from basicsr.archs.arch_util import flow_warp
File "D:\Anaconda\envs\restore\lib\site-packages\basicsr\archs\arch_util.py", line 13, in
from basicsr.ops.dcn import ModulatedDeformConvPack, modulated_deform_conv
File "D:\Anaconda\envs\restore\lib\site-packages\basicsr\ops\dcn_init.py", line 1, in
from .deform_conv import (DeformConv, DeformConvPack, ModulatedDeformConv, ModulatedDeformConvPack, deform_conv,
File "D:\Anaconda\envs\restore\lib\site-packages\basicsr\ops\dcn\deform_conv.py", line 14, in
deform_conv_ext = load(
File "D:\Anaconda\envs\restore\lib\site-packages\torch\utils\cpp_extension.py", line 1144, in load
return _jit_compile(
File "D:\Anaconda\envs\restore\lib\site-packages\torch\utils\cpp_extension.py", line 1357, in _jit_compile
_write_ninja_file_and_build_library(
File "D:\Anaconda\envs\restore\lib\site-packages\torch\utils\cpp_extension.py", line 1456, in _write_ninja_file_and_build_library
_write_ninja_file_to_build_library(
File "D:\Anaconda\envs\restore\lib\site-packages\torch\utils\cpp_extension.py", line 1898, in _write_ninja_file_to_build_library
_write_ninja_file(
File "D:\Anaconda\envs\restore\lib\site-packages\torch\utils\cpp_extension.py", line 2023, in _write_ninja_file
cl_paths = subprocess.check_output(['where',
File "D:\Anaconda\envs\restore\lib\subprocess.py", line 424, in check_output
return run(*popenargs, stdout=PIPE, timeout=timeout, check=True,
File "D:\Anaconda\envs\restore\lib\subprocess.py", line 528, in run
raise CalledProcessError(retcode, process.args,
subprocess.CalledProcessError: Command '['where', 'cl']' returned non-zero exit status 1.

Could you please assist me in resolving this issue?

hi, thanks for your awesome work! I try the online demo, the results are awesome. Then i download the code and run the inference pipeline with the default model ('https://github.com/xinntao/Real-ESRGAN/releases/download/v0.2.1/RealESRGAN_x2plus.pth'), the results seem a little worse than the online demo, mainly on the background. Could i know the background upsampler used in the online demo?

Hello, can you release the pretrained models in ONNX format?
Thanks.

Hello, may I ask if the base line result graphs in your paper are the result graphs obtained after training that model or the result graphs obtained through inference? Thank you for your answer!

Any update?

Model: Both pretrained models used for training and the trained model of our RestoreFormer and RestoreFormer++ can be attained from Google Driver. Link these models to ./experiments.

Can't download pre-trained dataset.
will there be fix soon?

As a windows user, I have difficulty running the .sh script. Can anyone help me with the anaconda virtual environment?