ECCV18 Workshops - Enhanced SRGAN. Champion PIRM Challenge on Perceptual Super-Resolution. The training codes are in BasicSR.

Hi, I installed CUDAv10 on Windows 10, but I'm not able to run the test script:

x:\GIT\ESRGAN>python test.py models/RRDB_ESRGAN_x4.pth
THCudaCheck FAIL file=..\aten\src\THC\THCGeneral.cpp line=51 error=30 : unknown error
Traceback (most recent call last):
  File "test.py", line 21, in <module>
    model = model.to(device)
  File "c:\DEV\Utils\Python37\lib\site-packages\torch\nn\modules\module.py", line 381, in to
    return self._apply(convert)
  File "c:\DEV\Utils\Python37\lib\site-packages\torch\nn\modules\module.py", line 187, in _apply
    module._apply(fn)
  File "c:\DEV\Utils\Python37\lib\site-packages\torch\nn\modules\module.py", line 187, in _apply
    module._apply(fn)
  File "c:\DEV\Utils\Python37\lib\site-packages\torch\nn\modules\module.py", line 193, in _apply
    param.data = fn(param.data)
  File "c:\DEV\Utils\Python37\lib\site-packages\torch\nn\modules\module.py", line 379, in convert
    return t.to(device, dtype if t.is_floating_point() else None, non_blocking)
  File "c:\DEV\Utils\Python37\lib\site-packages\torch\cuda\__init__.py", line 162, in _lazy_init
    torch._C._cuda_init()
RuntimeError: cuda runtime error (30) : unknown error at ..\aten\src\THC\THCGeneral.cpp:51

Any idea why? (maybe using LSD instead? ;-)

In paper of edsr,rcan and so on, before residual there should be a conv. For example, in edsr , (conv-act-conv)*n_blocks-conv , and there is a residual before and after this. In rcan, (block1-block2-...-block20-conv) is a group , there is a residual before and after a group, which is called short residual, and the residual before and after (group1-group2-...-group10-conv) is called a long residual. In your paper (P5, figure4 right, RRDB), there is a conv for short residual in the dense block, but no another conv for long residual, do you think it should be a conv after the third dense block?

I have make myself lmdb HR and LR ,and run use code "BasicSR" python train.py -opt /BasicSR/codes/options/train/train_ESRGAN.json

but how to test my data image use my trained model?

in BasicSR test.py or ESRGAN test.py ? in fact all failed

I was testing ESRGAN out on a workstation when I realized CUDA 2.1 is not supported for PyTorch.

I'm assuming that also means ESRGAN is not supported because of CUDA 2.1.

But to be exact, I don't see any minimum requirements to run ESRGAN. Thus, I have to come to this conclusion the hard way.

To prevent such things from happening, I would like to request on the README.md to list out the minimum requirements to properly run ESRGAN.

• What Nvidia CUDA version is required?
• What Nvidia architecture is needed? (Fermi, Volta, Pascal, Turing, etc.?)
• What Nvidia card type and up can be used? (Quadro, NVS, GeForce?)

Thanks.

yolkis@YOLKIS:~/ESRGAN$ python3 test.py models/RRDB_ESRGAN_x4.pth THCudaCheck FAIL file=/pytorch/aten/src/THC/THCGeneral.cpp line=74 error=35 : CUDA driver version is insufficient for CUDA runtime version Traceback (most recent call last): File "test.py", line 19, in model = model.cuda() File "/home/yolkis/.local/lib/python3.6/site-packages/torch/nn/modules/module.py", line 258, in cuda return self._apply(lambda t: t.cuda(device)) File "/home/yolkis/.local/lib/python3.6/site-packages/torch/nn/modules/module.py", line 185, in _apply module._apply(fn) File "/home/yolkis/.local/lib/python3.6/site-packages/torch/nn/modules/module.py", line 185, in _apply module._apply(fn) File "/home/yolkis/.local/lib/python3.6/site-packages/torch/nn/modules/module.py", line 191, in _apply param.data = fn(param.data) File "/home/yolkis/.local/lib/python3.6/site-packages/torch/nn/modules/module.py", line 258, in return self._apply(lambda t: t.cuda(device)) RuntimeError: cuda runtime error (35) : CUDA driver version is insufficient for CUDA runtime version at /pytorch/aten/src/THC/THCGeneral.cpp:74

您好,首先感谢下您的代码,对我有很大的帮助,但现在有一个问题,想请教您一下,使用您提供的训练好的模型进行跑您的测试代码时,会出现如下问题 root@c07bd16360cb:/home/qiuyj/ESRGAN# python test.py models/RRDB_ESRGAN_x4.pth Traceback (most recent call last): File "test.py", line 17, in model.load_state_dict(torch.load(model_path), strict=True) File "/usr/local/lib/python2.7/dist-packages/torch/nn/modules/module.py", line 721, in load_state_dict self.class.name, "\n\t".join(error_msgs))) RuntimeError: Error(s) in loading state_dict for RRDB_Net: Missing key(s) in state_dict: "model.9.bias", "model.9.weight". Unexpected key(s) in state_dict: "model.1.sub.2.RDB1.conv1.0.weight", "model.1.sub.2.RDB1.conv1.0.bias", "model.1.sub.2.RDB1.conv2.0.weight", "model.1.sub.2.RDB1.conv2.0.bias", "model.1.sub.2.RDB1.conv3.0.weight", "model.1.sub.2.RDB1.conv3.0.bias", "model.1.sub.2.RDB1.conv4.0.weight", "model.1.sub.2.RDB1.conv4.0.bias", "model.1.sub.2.RDB1.conv5.0.weight", "model.1.sub.2.RDB1.conv5.0.bias", "model.1.sub.2.RDB2.conv1.0.weight", "model.1.sub.2.RDB2.conv1.0.bias", "model.1.sub.2.RDB2.conv2.0.weight", "model.1.sub.2.RDB2.conv2.0.bias", "

https://github.com/xinntao/ESRGAN/blob/ce16ee8e30f6ba980a092f76806ca60ccfdfc5f4/block.py#L208 it seems different between your code and paper.which is correct? thx!

Sorry, I am new to CUDA and things like this but every time I want to run ESRGAN on my GPU it gives me this error. Works fine on CPU.

Full output: ============================== RESTART: C:\Users\Masterbond7\Desktop\ESRGAN-master\test.py ============================= Model path models/RRDB_ESRGAN_x4.pth. Testing... 1 baboon Traceback (most recent call last): File "C:\Users\Masterbond7\Desktop\ESRGAN-master\test.py", line 34, in output = model(img_LR).data.squeeze().float().cpu().clamp_(0, 1).numpy() File "C:\Users\Masterbond7\AppData\Local\Programs\Python\Python38\lib\site-packages\torch\nn\modules\module.py", line 532, in call result = self.forward(*input, **kwargs) File "C:\Users\Masterbond7\Desktop\ESRGAN-master\RRDBNet_arch.py", line 71, in forward trunk = self.trunk_conv(self.RRDB_trunk(fea)) File "C:\Users\Masterbond7\AppData\Local\Programs\Python\Python38\lib\site-packages\torch\nn\modules\module.py", line 532, in call result = self.forward(*input, **kwargs) File "C:\Users\Masterbond7\AppData\Local\Programs\Python\Python38\lib\site-packages\torch\nn\modules\container.py", line 100, in forward input = module(input) File "C:\Users\Masterbond7\AppData\Local\Programs\Python\Python38\lib\site-packages\torch\nn\modules\module.py", line 532, in call result = self.forward(*input, **kwargs) File "C:\Users\Masterbond7\Desktop\ESRGAN-master\RRDBNet_arch.py", line 47, in forward out = self.RDB1(x) File "C:\Users\Masterbond7\AppData\Local\Programs\Python\Python38\lib\site-packages\torch\nn\modules\module.py", line 532, in call result = self.forward(*input, **kwargs) File "C:\Users\Masterbond7\Desktop\ESRGAN-master\RRDBNet_arch.py", line 30, in forward x2 = self.lrelu(self.conv2(torch.cat((x, x1), 1))) RuntimeError: error in LoadLibraryA

Hi, so i was building out an esrgan on my own and tried to keep it as faithful to the paper as possible. However, the thing is that the number of parameters is quite large(55M for 16 rrdb blocks) . I wanted to ask if what i was doing was right or is there some error, below i have attached my architecture for my rrdbnet

def rdb_block(model, kernal_size, filters, strides):
     
    gen = model
    model = Conv2D(filters = filters, kernel_size = kernal_size, strides = strides, padding = "same")(model)
    model = LeakyReLU(alpha = 0.2)(model)
    model = Concatenate()([gen, model])
    gen2 = model
    
    model = Conv2D(filters = filters, kernel_size = kernal_size, strides = strides, padding = "same")(model)
    model = LeakyReLU(alpha = 0.2)(model)
    model = Concatenate()([gen, gen2, model])
    gen3 = model
    
    model = Conv2D(filters = filters, kernel_size = kernal_size, strides = strides, padding = "same")(model)
    model = LeakyReLU(alpha = 0.2)(model)
    model = Concatenate()([gen, gen2,gen3, model])
    gen4 = model
    
    model = Conv2D(filters = filters, kernel_size = kernal_size, strides = strides, padding = "same")(model)
    model = LeakyReLU(alpha = 0.2)(model)
    model = Concatenate()([gen, gen2,gen3, gen4, model])
    
    model = Conv2D(filters = filters, kernel_size = kernal_size, strides = strides, padding = "same")(model)
    model = Lambda(lambda x: x*0.2)(model)
    return Add()([model, gen])

def rrdb_block(model, kernel_size, filters, strides):
    rdb1 = rdb_block(model, kernel_size, filters, strides)
    rdb2 = rdb_block(rdb1, kernel_size, filters, strides)
    rdb2 = rdb_block(rdb2, kernel_size, filters, strides)
    rdb2 = Lambda(lambda x: x*0.2)(rdb2)
    
    return Add()([rdb2, model])

def generator(self):
	    gen_input = Input(shape = self.input_shape)
	    model = Conv2D(filters = 64, kernel_size = 9, strides = 1, padding = "same")(gen_input)
	    gen_model = model
        # Using 16 Residual Blocks
	    for index in range(16):
	        model = rrdb_block(model, 3, 64, 1)
	    
	    model = Conv2D(filters = 64, kernel_size = 3, strides = 1, padding = "same")(model)
	    model = add([gen_model, model])
	    
	    # Using 2 UpSampling Blocks
	    for index in range(2):
	        model = up_sampling_block(model, 3, 256, 1)
	    
	    model = Conv2D(filters = 3, kernel_size = 9, strides = 1, padding = "same")(model)
      
  
	    generator_model = Model(inputs = gen_input, outputs = model)
        
	    return generator_model

After running the ESRGAN test on a 12" 240dpi 6000 pixel file the process fails with:

Killed: 9

Does anyone know what this means and how I can get the process to complete successfully?

问题出现在progress_bar.py文件中的update函数fps = self.completed / elapsed这里elapsed变成零了。我把elapsed = time.time() - self.start_time中的两个值打印出来发现是一样的： Read images... [ ] 0/36352, elapsed: 0s, ETA: Start... 1554711715.5890906 1554711715.5890906 0.0 Traceback (most recent call last): File "create_lmdb.py", line 22, in pbar.update('Read {}'.format(v)) File "D:\code\BasicSR\codes\utils\progress_bar.py", line 43, in update fps = self.completed / elapsed ZeroDivisionError: float division by zero 其中我的路径设置是这样的： img_folder = 'D:\code\BasicSR\codes\data\HR\*.png' lmdb_save_path = 'D:\code\BasicSR\codes\data\HR.lmdb' 需要您的帮助！谢谢

Hi @xinntao,

Kudos to you for your work on ISR. I worked on developing a simple streamlit based web-app on ESRGAN and I think it will be fruitful to have it as a part of README here as the motivation behind developing this came from your work 😄!

Title: Streamlit based ISR using ESRGAN Github Repo: https://github.com/prateekralhan/Streamlit-based-Image-Super-Resolution-using-ESRGAN

Happy opensourcing!

As you can see here: https://github.com/rlaphoenix/VSGAN/blob/a81c177f00ee8cfb5bbc847c0da0ce2b5ad9d4ec/vsgan/archs/ESRGAN.py#L42

I need to manually do some key name replacing and regex checks to be able to support all models of all 3 types of RRDBNet archs you have done for: Original ESRGAN, Later ESRGAN (Near BasicSR), as well as Real-ESRGAN.

Please try not to change the state keys so much as it breaks compatibility with old models for testing and gives other devs a headache to try support them all. Thanks.

Hi @xinntao!

Really great work on ESRGAN, I still use it regularly for image upscaling.

This pull request makes it possible to run your model inside a Docker environment, which makes it easier for other people to run it. We're using an open source tool called Cog to make this process easier.

This also means we can make a web page where other people can try out your model! View it here: https://replicate.ai/xinntao/esrgan

You can claim your page by signing in with GitHub, and we'll feature it on Replicate.

In case you're wondering who I am, I'm from Replicate, where we're trying to make machine learning reproducible. We got frustrated that we couldn't run all the really interesting ML work being done. So, we're going round implementing models we like. 😊

If you think this is useful we can make a similar demo for Real-ESRGAN as well.

Hello, I have a problem. When I use RDN as the generator for training, the details of the generated image will appear R, G or B color spots. Have you encountered similar problems. BI down sampling is used for low resolution images, and this problem will not occur using residual network.

Hello. I'm a total newbie when it comes to python and this is the first program where I've gotten to the point of being halfway decently set up. What I want help with is this whole mess.

(base) C:\Users\Journey.LAPTOP-6NGPTH4A\Programs\ESRGAN-master>python test.py models/Manga109Attempt_old_arch.pth Traceback (most recent call last): File "test.py", line 15, in model.load_state_dict(torch.load(model_path), strict=True) File "D:\Users\Programs\miniconda3\lib\site-packages\torch\nn\modules\module.py", line 1406, in load_state_dict raise RuntimeError('Error(s) in loading state_dict for {}:\n\t{}'.format( RuntimeError: Error(s) in loading state_dict for RRDBNet: Missing key(s) in state_dict: "conv_first.weight", "conv_first.bias", "RRDB_trunk.0.RDB1.conv1.weight", "RRDB_trunk.0.RDB1.conv1.bias", "RRDB_trunk.0.RDB1.conv2.weight", "RRDB_trunk.0.RDB1.conv2.bias", "RRDB_trunk.0.RDB1.conv3.weight", "RRDB_trunk.0.RDB1.conv3.bias", "RRDB_trunk.0.RDB1.conv4.weight", "RRDB_trunk.0.RDB1.conv4.bias", "RRDB_trunk.0.RDB1.conv5.weight", "RRDB_trunk.0.RDB1.conv5.bias", "RRDB_trunk.0.RDB2.conv1.weight", "RRDB_trunk.0.RDB2.conv1.bias", "RRDB_trunk.0.RDB2.conv2.weight", "RRDB_trunk.0.RDB2.conv2.bias", "RRDB_trunk.0.RDB2.conv3.weight", "RRDB_trunk.0.RDB2.conv3.bias", "RRDB_trunk.0.RDB2.conv4.weight", "RRDB_trunk.0.RDB2.conv4.bias", "RRDB_trunk.0.RDB2.conv5.weight", "RRDB_trunk.0.RDB2.conv5.bias", "RRDB_trunk.0.RDB3.conv1.weight", "RRDB_trunk.0.RDB3.conv1.bias", "RRDB_trunk.0.RDB3.conv2.weight", "RRDB_trunk.0.RDB3.conv2.bias", "RRDB_trunk.0.RDB3.conv3.weight", "RRDB_trunk.0.RDB3.conv3.bias", "RRDB_trunk.0.RDB3.conv4.weight", "RRDB_trunk.0.RDB3.conv4.bias", "RRDB_trunk.0.RDB3.conv5.weight", "RRDB_trunk.0.RDB3.conv5.bias", "RRDB_trunk.1.RDB1.conv1.weight", "RRDB_trunk.1.RDB1.conv1.bias", "RRDB_trunk.1.RDB1.conv2.weight", "RRDB_trunk.1.RDB1.conv2.bias", "RRDB_trunk.1.RDB1.conv3.weight", "RRDB_trunk.1.RDB1.conv3.bias", "RRDB_trunk.1.RDB1.conv4.weight", "RRDB_trunk.1.RDB1.conv4.bias", "RRDB_trunk.1.RDB1.conv5.weight", "RRDB_trunk.1.RDB1.conv5.bias", "RRDB_trunk.1.RDB2.conv1.weight", "RRDB_trunk.1.RDB2.conv1.bias", "RRDB_trunk.1.RDB2.conv2.weight", "RRDB_trunk.1.RDB2.conv2.bias", "RRDB_trunk.1.RDB2.conv3.weight", "RRDB_trunk.1.RDB2.conv3.bias", "RRDB_trunk.1.RDB2.conv4.weight", "RRDB_trunk.1.RDB2.conv4.bias", "RRDB_trunk.1.RDB2.conv5.weight", "RRDB_trunk.1.RDB2.conv5.bias", "RRDB_trunk.1.RDB3.conv1.weight", "RRDB_trunk.1.RDB3.conv1.bias", "RRDB_trunk.1.RDB3.conv2.weight", "RRDB_trunk.1.RDB3.conv2.bias", "RRDB_trunk.1.RDB3.conv3.weight", "RRDB_trunk.1.RDB3.conv3.bias", "RRDB_trunk.1.RDB3.conv4.weight", "RRDB_trunk.1.RDB3.conv4.bias", "RRDB_trunk.1.RDB3.conv5.weight", "RRDB_trunk.1.RDB3.conv5.bias", "RRDB_trunk.2.RDB1.conv1.weight", "RRDB_trunk.2.RDB1.conv1.bias", "RRDB_trunk.2.RDB1.conv2.weight", "RRDB_trunk.2.RDB1.conv2.bias", "RRDB_trunk.2.RDB1.conv3.weight", "RRDB_trunk.2.RDB1.conv3.bias", "RRDB_trunk.2.RDB1.conv4.weight", "RRDB_trunk.2.RDB1.conv4.bias", "RRDB_trunk.2.RDB1.conv5.weight", "RRDB_trunk.2.RDB1.conv5.bias", "RRDB_trunk.2.RDB2.conv1.weight", "RRDB_trunk.2.RDB2.conv1.bias", "RRDB_trunk.2.RDB2.conv2.weight", "RRDB_trunk.2.RDB2.conv2.bias", "RRDB_trunk.2.RDB2.conv3.weight", "RRDB_trunk.2.RDB2.conv3.bias", "RRDB_trunk.2.RDB2.conv4.weight", "RRDB_trunk.2.RDB2.conv4.bias", "RRDB_trunk.2.RDB2.conv5.weight", "RRDB_trunk.2.RDB2.conv5.bias", "RRDB_trunk.2.RDB3.conv1.weight", "RRDB_trunk.2.RDB3.conv1.bias", "RRDB_trunk.2.RDB3.conv2.weight", "RRDB_trunk.2.RDB3.conv2.bias", "RRDB_trunk.2.RDB3.conv3.weight", "RRDB_trunk.2.RDB3.conv3.bias", "RRDB_trunk.2.RDB3.conv4.weight", "RRDB_trunk.2.RDB3.conv4.bias", "RRDB_trunk.2.RDB3.conv5.weight", "RRDB_trunk.2.RDB3.conv5.bias", "RRDB_trunk.3.RDB1.conv1.weight", "RRDB_trunk.3.RDB1.conv1.bias", "RRDB_trunk.3.RDB1.conv2.weight", "RRDB_trunk.3.RDB1.conv2.bias", "RRDB_trunk.3.RDB1.conv3.weight", "RRDB_trunk.3.RDB1.conv3.bias", "RRDB_trunk.3.RDB1.conv4.weight", "RRDB_trunk.3.RDB1.conv4.bias", "RRDB_trunk.3.RDB1.conv5.weight", "RRDB_trunk.3.RDB1.conv5.bias", "RRDB_trunk.3.RDB2.conv1.weight", "RRDB_trunk.3.RDB2.conv1.bias", "RRDB_trunk.3.RDB2.conv2.weight", "RRDB_trunk.3.RDB2.conv2.bias", "RRDB_trunk.3.RDB2.conv3.weight", "RRDB_trunk.3.RDB2.conv3.bias", "RRDB_trunk.3.RDB2.conv4.weight", "RRDB_trunk.3.RDB2.conv4.bias", "RRDB_trunk.3.RDB2.conv5.weight", "RRDB_trunk.3.RDB2.conv5.bias", "RRDB_trunk.3.RDB3.conv1.weight", "RRDB_trunk.3.RDB3.conv1.bias", "RRDB_trunk.3.RDB3.conv2.weight", "RRDB_trunk.3.RDB3.conv2.bias", "RRDB_trunk.3.RDB3.conv3.weight", "RRDB_trunk.3.RDB3.conv3.bias", "RRDB_trunk.3.RDB3.conv4.weight", "RRDB_trunk.3.RDB3.conv4.bias", "RRDB_trunk.3.RDB3.conv5.weight", "RRDB_trunk.3.RDB3.conv5.bias", "RRDB_trunk.4.RDB1.conv1.weight", "RRDB_trunk.4.RDB1.conv1.bias", "RRDB_trunk.4.RDB1.conv2.weight", "RRDB_trunk.4.RDB1.conv2.bias", "RRDB_trunk.4.RDB1.conv3.weight", "RRDB_trunk.4.RDB1.conv3.bias", "RRDB_trunk.4.RDB1.conv4.weight", "RRDB_trunk.4.RDB1.conv4.bias", "RRDB_trunk.4.RDB1.conv5.weight", "RRDB_trunk.4.RDB1.conv5.bias", "RRDB_trunk.4.RDB2.conv1.weight", "RRDB_trunk.4.RDB2.conv1.bias", "RRDB_trunk.4.RDB2.conv2.weight", "RRDB_trunk.4.RDB2.conv2.bias", "RRDB_trunk.4.RDB2.conv3.weight", "RRDB_trunk.4.RDB2.conv3.bias", "RRDB_trunk.4.RDB2.conv4.weight", "RRDB_trunk.4.RDB2.conv4.bias", "RRDB_trunk.4.RDB2.conv5.weight", "RRDB_trunk.4.RDB2.conv5.bias", "RRDB_trunk.4.RDB3.conv1.weight", "RRDB_trunk.4.RDB3.conv1.bias", "RRDB_trunk.4.RDB3.conv2.weight", "RRDB_trunk.4.RDB3.conv2.bias", "RRDB_trunk.4.RDB3.conv3.weight", "RRDB_trunk.4.RDB3.conv3.bias", "RRDB_trunk.4.RDB3.conv4.weight", "RRDB_trunk.4.RDB3.conv4.bias", "RRDB_trunk.4.RDB3.conv5.weight", "RRDB_trunk.4.RDB3.conv5.bias", "RRDB_trunk.5.RDB1.conv1.weight", "RRDB_trunk.5.RDB1.conv1.bias", "RRDB_trunk.5.RDB1.conv2.weight", "RRDB_trunk.5.RDB1.conv2.bias", "RRDB_trunk.5.RDB1.conv3.weight", "RRDB_trunk.5.RDB1.conv3.bias", "RRDB_trunk.5.RDB1.conv4.weight", "RRDB_trunk.5.RDB1.conv4.bias", "RRDB_trunk.5.RDB1.conv5.weight", "RRDB_trunk.5.RDB1.conv5.bias", "RRDB_trunk.5.RDB2.conv1.weight", "RRDB_trunk.5.RDB2.conv1.bias", "RRDB_trunk.5.RDB2.conv2.weight", "RRDB_trunk.5.RDB2.conv2.bias", "RRDB_trunk.5.RDB2.conv3.weight", "RRDB_trunk.5.RDB2.conv3.bias", "RRDB_trunk.5.RDB2.conv4.weight", "RRDB_trunk.5.RDB2.conv4.bias", "RRDB_trunk.5.RDB2.conv5.weight", "RRDB_trunk.5.RDB2.conv5.bias", "RRDB_trunk.5.RDB3.conv1.weight", "RRDB_trunk.5.RDB3.conv1.bias", "RRDB_trunk.5.RDB3.conv2.weight", "RRDB_trunk.5.RDB3.conv2.bias", "RRDB_trunk.5.RDB3.conv3.weight", "RRDB_trunk.5.RDB3.conv3.bias", "RRDB_trunk.5.RDB3.conv4.weight", "RRDB_trunk.5.RDB3.conv4.bias", "RRDB_trunk.5.RDB3.conv5.weight", "RRDB_trunk.5.RDB3.conv5.bias", "RRDB_trunk.6.RDB1.conv1.weight", "RRDB_trunk.6.RDB1.conv1.bias", "RRDB_trunk.6.RDB1.conv2.weight", "RRDB_trunk.6.RDB1.conv2.bias", "RRDB_trunk.6.RDB1.conv3.weight", "RRDB_trunk.6.RDB1.conv3.bias", "RRDB_trunk.6.RDB1.conv4.weight", "RRDB_trunk.6.RDB1.conv4.bias", "RRDB_trunk.6.RDB1.conv5.weight", "RRDB_trunk.6.RDB1.conv5.bias", "RRDB_trunk.6.RDB2.conv1.weight", "RRDB_trunk.6.RDB2.conv1.bias", "RRDB_trunk.6.RDB2.conv2.weight", "RRDB_trunk.6.RDB2.conv2.bias", "RRDB_trunk.6.RDB2.conv3.weight", "RRDB_trunk.6.RDB2.conv3.bias", "RRDB_trunk.6.RDB2.conv4.weight", "RRDB_trunk.6.RDB2.conv4.bias", "RRDB_trunk.6.RDB2.conv5.weight", "RRDB_trunk.6.RDB2.conv5.bias", "RRDB_trunk.6.RDB3.conv1.weight", "RRDB_trunk.6.RDB3.conv1.bias", "RRDB_trunk.6.RDB3.conv2.weight", "RRDB_trunk.6.RDB3.conv2.bias", "RRDB_trunk.6.RDB3.conv3.weight", "RRDB_trunk.6.RDB3.conv3.bias", "RRDB_trunk.6.RDB3.conv4.weight", "RRDB_trunk.6.RDB3.conv4.bias", "RRDB_trunk.6.RDB3.conv5.weight", "RRDB_trunk.6.RDB3.conv5.bias", "RRDB_trunk.7.RDB1.conv1.weight", "RRDB_trunk.7.RDB1.conv1.bias", "RRDB_trunk.7.RDB1.conv2.weight", "RRDB_trunk.7.RDB1.conv2.bias", "RRDB_trunk.7.RDB1.conv3.weight", "RRDB_trunk.7.RDB1.conv3.bias", "RRDB_trunk.7.RDB1.conv4.weight", "RRDB_trunk.7.RDB1.conv4.bias", "RRDB_trunk.7.RDB1.conv5.weight", "RRDB_trunk.7.RDB1.conv5.bias", "RRDB_trunk.7.RDB2.conv1.weight", "RRDB_trunk.7.RDB2.conv1.bias", "RRDB_trunk.7.RDB2.conv2.weight", "RRDB_trunk.7.RDB2.conv2.bias", "RRDB_trunk.7.RDB2.conv3.weight", "RRDB_trunk.7.RDB2.conv3.bias", "RRDB_trunk.7.RDB2.conv4.weight", "RRDB_trunk.7.RDB2.conv4.bias", "RRDB_trunk.7.RDB2.conv5.weight", "RRDB_trunk.7.RDB2.conv5.bias", "RRDB_trunk.7.RDB3.conv1.weight", "RRDB_trunk.7.RDB3.conv1.bias", "RRDB_trunk.7.RDB3.conv2.weight", "RRDB_trunk.7.RDB3.conv2.bias", "RRDB_trunk.7.RDB3.conv3.weight", "RRDB_trunk.7.RDB3.conv3.bias", "RRDB_trunk.7.RDB3.conv4.weight", "RRDB_trunk.7.RDB3.conv4.bias", "RRDB_trunk.7.RDB3.conv5.weight", "RRDB_trunk.7.RDB3.conv5.bias", "RRDB_trunk.8.RDB1.conv1.weight", "RRDB_trunk.8.RDB1.conv1.bias", "RRDB_trunk.8.RDB1.conv2.weight", "RRDB_trunk.8.RDB1.conv2.bias", "RRDB_trunk.8.RDB1.conv3.weight", "RRDB_trunk.8.RDB1.conv3.bias", "RRDB_trunk.8.RDB1.conv4.weight", "RRDB_trunk.8.RDB1.conv4.bias", "RRDB_trunk.8.RDB1.conv5.weight", "RRDB_trunk.8.RDB1.conv5.bias", "RRDB_trunk.8.RDB2.conv1.weight", "RRDB_trunk.8.RDB2.conv1.bias", "RRDB_trunk.8.RDB2.conv2.weight", "RRDB_trunk.8.RDB2.conv2.bias", "RRDB_trunk.8.RDB2.conv3.weight", "RRDB_trunk.8.RDB2.conv3.bias", "RRDB_trunk.8.RDB2.conv4.weight", "RRDB_trunk.8.RDB2.conv4.bias", "RRDB_trunk.8.RDB2.conv5.weight", "RRDB_trunk.8.RDB2.conv5.bias", "RRDB_trunk.8.RDB3.conv1.weight", "RRDB_trunk.8.RDB3.conv1.bias", "RRDB_trunk.8.RDB3.conv2.weight", "RRDB_trunk.8.RDB3.conv2.bias", "RRDB_trunk.8.RDB3.conv3.weight", "RRDB_trunk.8.RDB3.conv3.bias", "RRDB_trunk.8.RDB3.conv4.weight", "RRDB_trunk.8.RDB3.conv4.bias", "RRDB_trunk.8.RDB3.conv5.weight", "RRDB_trunk.8.RDB3.conv5.bias", "RRDB_trunk.9.RDB1.conv1.weight", "RRDB_trunk.9.RDB1.conv1.bias", "RRDB_trunk.9.RDB1.conv2.weight", "RRDB_trunk.9.RDB1.conv2.bias", "RRDB_trunk.9.RDB1.conv3.weight", "RRDB_trunk.9.RDB1.conv3.bias", "RRDB_trunk.9.RDB1.conv4.weight", "RRDB_trunk.9.RDB1.conv4.bias", "RRDB_trunk.9.RDB1.conv5.weight", "RRDB_trunk.9.RDB1.conv5.bias", "RRDB_trunk.9.RDB2.conv1.weight", "RRDB_trunk.9.RDB2.conv1.bias", "RRDB_trunk.9.RDB2.conv2.weight", "RRDB_trunk.9.RDB2.conv2.bias", "RRDB_trunk.9.RDB2.conv3.weight", "RRDB_trunk.9.RDB2.conv3.bias", "RRDB_trunk.9.RDB2.conv4.weight", "RRDB_trunk.9.RDB2.conv4.bias", "RRDB_trunk.9.RDB2.conv5.weight", "RRDB_trunk.9.RDB2.conv5.bias", "RRDB_trunk.9.RDB3.conv1.weight", "RRDB_trunk.9.RDB3.conv1.bias", "RRDB_trunk.9.RDB3.conv2.weight", "RRDB_trunk.9.RDB3.conv2.bias", "RRDB_trunk.9.RDB3.conv3.weight", "RRDB_trunk.9.RDB3.conv3.bias", "RRDB_trunk.9.RDB3.conv4.weight", "RRDB_trunk.9.RDB3.conv4.bias", "RRDB_trunk.9.RDB3.conv5.weight", "RRDB_trunk.9.RDB3.conv5.bias", "RRDB_trunk.10.RDB1.conv1.weight", "RRDB_trunk.10.RDB1.conv1.bias", "RRDB_trunk.10.RDB1.conv2.weight", "RRDB_trunk.10.RDB1.conv2.bias", "RRDB_trunk.10.RDB1.conv3.weight", "RRDB_trunk.10.RDB1.conv3.bias", "RRDB_trunk.10.RDB1.conv4.weight", "RRDB_trunk.10.RDB1.conv4.bias", "RRDB_trunk.10.RDB1.conv5.weight", "RRDB_trunk.10.RDB1.conv5.bias", "RRDB_trunk.10.RDB2.conv1.weight", "RRDB_trunk.10.RDB2.conv1.bias", "RRDB_trunk.10.RDB2.conv2.weight", "RRDB_trunk.10.RDB2.conv2.bias", "RRDB_trunk.10.RDB2.conv3.weight", "RRDB_trunk.10.RDB2.conv3.bias", "RRDB_trunk.10.RDB2.conv4.weight", "RRDB_trunk.10.RDB2.conv4.bias", "RRDB_trunk.10.RDB2.conv5.weight", "RRDB_trunk.10.RDB2.conv5.bias", "RRDB_trunk.10.RDB3.conv1.weight", "RRDB_trunk.10.RDB3.conv1.bias", "RRDB_trunk.10.RDB3.conv2.weight", "RRDB_trunk.10.RDB3.conv2.bias", "RRDB_trunk.10.RDB3.conv3.weight", "RRDB_trunk.10.RDB3.conv3.bias", "RRDB_trunk.10.RDB3.conv4.weight", "RRDB_trunk.10.RDB3.conv4.bias", "RRDB_trunk.10.RDB3.conv5.weight", "RRDB_trunk.10.RDB3.conv5.bias", "RRDB_trunk.11.RDB1.conv1.weight", "RRDB_trunk.11.RDB1.conv1.bias", "RRDB_trunk.11.RDB1.conv2.weight", "RRDB_trunk.11.RDB1.conv2.bias", "RRDB_trunk.11.RDB1.conv3.weight", "RRDB_trunk.11.RDB1.conv3.bias", "RRDB_trunk.11.RDB1.conv4.weight", "RRDB_trunk.11.RDB1.conv4.bias", "RRDB_trunk.11.RDB1.conv5.weight", "RRDB_trunk.11.RDB1.conv5.bias", "RRDB_trunk.11.RDB2.conv1.weight", "RRDB_trunk.11.RDB2.conv1.bias", "RRDB_trunk.11.RDB2.conv2.weight", "RRDB_trunk.11.RDB2.conv2.bias", "RRDB_trunk.11.RDB2.conv3.weight", "RRDB_trunk.11.RDB2.conv3.bias", "RRDB_trunk.11.RDB2.conv4.weight", "RRDB_trunk.11.RDB2.conv4.bias", "RRDB_trunk.11.RDB2.conv5.weight", "RRDB_trunk.11.RDB2.conv5.bias", "RRDB_trunk.11.RDB3.conv1.weight", "RRDB_trunk.11.RDB3.conv1.bias", "RRDB_trunk.11.RDB3.conv2.weight", "RRDB_trunk.11.RDB3.conv2.bias", "RRDB_trunk.11.RDB3.conv3.weight", "RRDB_trunk.11.RDB3.conv3.bias", "RRDB_trunk.11.RDB3.conv4.weight", "RRDB_trunk.11.RDB3.conv4.bias", "RRDB_trunk.11.RDB3.conv5.weight", "RRDB_trunk.11.RDB3.conv5.bias", "RRDB_trunk.12.RDB1.conv1.weight", "RRDB_trunk.12.RDB1.conv1.bias", "RRDB_trunk.12.RDB1.conv2.weight", "RRDB_trunk.12.RDB1.conv2.bias", "RRDB_trunk.12.RDB1.conv3.weight", "RRDB_trunk.12.RDB1.conv3.bias", "RRDB_trunk.12.RDB1.conv4.weight", "RRDB_trunk.12.RDB1.conv4.bias", "RRDB_trunk.12.RDB1.conv5.weight", "RRDB_trunk.12.RDB1.conv5.bias", "RRDB_trunk.12.RDB2.conv1.weight", "RRDB_trunk.12.RDB2.conv1.bias", "RRDB_trunk.12.RDB2.conv2.weight", "RRDB_trunk.12.RDB2.conv2.bias", "RRDB_trunk.12.RDB2.conv3.weight", "RRDB_trunk.12.RDB2.conv3.bias", "RRDB_trunk.12.RDB2.conv4.weight", "RRDB_trunk.12.RDB2.conv4.bias", "RRDB_trunk.12.RDB2.conv5.weight", "RRDB_trunk.12.RDB2.conv5.bias", "RRDB_trunk.12.RDB3.conv1.weight", "RRDB_trunk.12.RDB3.conv1.bias", "RRDB_trunk.12.RDB3.conv2.weight", "RRDB_trunk.12.RDB3.conv2.bias", "RRDB_trunk.12.RDB3.conv3.weight", "RRDB_trunk.12.RDB3.conv3.bias", "RRDB_trunk.12.RDB3.conv4.weight", "RRDB_trunk.12.RDB3.conv4.bias", "RRDB_trunk.12.RDB3.conv5.weight", "RRDB_trunk.12.RDB3.conv5.bias", "RRDB_trunk.13.RDB1.conv1.weight", "RRDB_trunk.13.RDB1.conv1.bias", "RRDB_trunk.13.RDB1.conv2.weight", "RRDB_trunk.13.RDB1.conv2.bias", "RRDB_trunk.13.RDB1.conv3.weight", "RRDB_trunk.13.RDB1.conv3.bias", "RRDB_trunk.13.RDB1.conv4.weight", "RRDB_trunk.13.RDB1.conv4.bias", "RRDB_trunk.13.RDB1.conv5.weight", "RRDB_trunk.13.RDB1.conv5.bias", "RRDB_trunk.13.RDB2.conv1.weight", "RRDB_trunk.13.RDB2.conv1.bias", "RRDB_trunk.13.RDB2.conv2.weight", "RRDB_trunk.13.RDB2.conv2.bias", "RRDB_trunk.13.RDB2.conv3.weight", "RRDB_trunk.13.RDB2.conv3.bias", "RRDB_trunk.13.RDB2.conv4.weight", "RRDB_trunk.13.RDB2.conv4.bias", "RRDB_trunk.13.RDB2.conv5.weight", "RRDB_trunk.13.RDB2.conv5.bias", "RRDB_trunk.13.RDB3.conv1.weight", "RRDB_trunk.13.RDB3.conv1.bias", "RRDB_trunk.13.RDB3.conv2.weight", "RRDB_trunk.13.RDB3.conv2.bias", "RRDB_trunk.13.RDB3.conv3.weight", "RRDB_trunk.13.RDB3.conv3.bias", "RRDB_trunk.13.RDB3.conv4.weight", "RRDB_trunk.13.RDB3.conv4.bias", "RRDB_trunk.13.RDB3.conv5.weight", "RRDB_trunk.13.RDB3.conv5.bias", "RRDB_trunk.14.RDB1.conv1.weight", "RRDB_trunk.14.RDB1.conv1.bias", "RRDB_trunk.14.RDB1.conv2.weight", "RRDB_trunk.14.RDB1.conv2.bias", "RRDB_trunk.14.RDB1.conv3.weight", "RRDB_trunk.14.RDB1.conv3.bias", "RRDB_trunk.14.RDB1.conv4.weight", "RRDB_trunk.14.RDB1.conv4.bias", "RRDB_trunk.14.RDB1.conv5.weight", "RRDB_trunk.14.RDB1.conv5.bias", "RRDB_trunk.14.RDB2.conv1.weight", "RRDB_trunk.14.RDB2.conv1.bias", "RRDB_trunk.14.RDB2.conv2.weight", "RRDB_trunk.14.RDB2.conv2.bias", "RRDB_trunk.14.RDB2.conv3.weight", "RRDB_trunk.14.RDB2.conv3.bias", "RRDB_trunk.14.RDB2.conv4.weight", "RRDB_trunk.14.RDB2.conv4.bias", "RRDB_trunk.14.RDB2.conv5.weight", "RRDB_trunk.14.RDB2.conv5.bias", "RRDB_trunk.14.RDB3.conv1.weight", "RRDB_trunk.14.RDB3.conv1.bias", "RRDB_trunk.14.RDB3.conv2.weight", "RRDB_trunk.14.RDB3.conv2.bias", "RRDB_trunk.14.RDB3.conv3.weight", "RRDB_trunk.14.RDB3.conv3.bias", "RRDB_trunk.14.RDB3.conv4.weight", "RRDB_trunk.14.RDB3.conv4.bias", "RRDB_trunk.14.RDB3.conv5.weight", "RRDB_trunk.14.RDB3.conv5.bias", "RRDB_trunk.15.RDB1.conv1.weight", "RRDB_trunk.15.RDB1.conv1.bias", "RRDB_trunk.15.RDB1.conv2.weight", "RRDB_trunk.15.RDB1.conv2.bias", "RRDB_trunk.15.RDB1.conv3.weight", "RRDB_trunk.15.RDB1.conv3.bias", "RRDB_trunk.15.RDB1.conv4.weight", "RRDB_trunk.15.RDB1.conv4.bias", "RRDB_trunk.15.RDB1.conv5.weight", "RRDB_trunk.15.RDB1.conv5.bias", "RRDB_trunk.15.RDB2.conv1.weight", "RRDB_trunk.15.RDB2.conv1.bias", "RRDB_trunk.15.RDB2.conv2.weight", "RRDB_trunk.15.RDB2.conv2.bias", "RRDB_trunk.15.RDB2.conv3.weight", "RRDB_trunk.15.RDB2.conv3.bias", "RRDB_trunk.15.RDB2.conv4.weight", "RRDB_trunk.15.RDB2.conv4.bias", "RRDB_trunk.15.RDB2.conv5.weight", "RRDB_trunk.15.RDB2.conv5.bias", "RRDB_trunk.15.RDB3.conv1.weight", "RRDB_trunk.15.RDB3.conv1.bias", "RRDB_trunk.15.RDB3.conv2.weight", "RRDB_trunk.15.RDB3.conv2.bias", "RRDB_trunk.15.RDB3.conv3.weight", "RRDB_trunk.15.RDB3.conv3.bias", "RRDB_trunk.15.RDB3.conv4.weight", "RRDB_trunk.15.RDB3.conv4.bias", "RRDB_trunk.15.RDB3.conv5.weight", "RRDB_trunk.15.RDB3.conv5.bias", "RRDB_trunk.16.RDB1.conv1.weight", "RRDB_trunk.16.RDB1.conv1.bias", "RRDB_trunk.16.RDB1.conv2.weight", "RRDB_trunk.16.RDB1.conv2.bias", "RRDB_trunk.16.RDB1.conv3.weight", "RRDB_trunk.16.RDB1.conv3.bias", "RRDB_trunk.16.RDB1.conv4.weight", "RRDB_trunk.16.RDB1.conv4.bias", "RRDB_trunk.16.RDB1.conv5.weight", "RRDB_trunk.16.RDB1.conv5.bias", "RRDB_trunk.16.RDB2.conv1.weight", "RRDB_trunk.16.RDB2.conv1.bias", "RRDB_trunk.16.RDB2.conv2.weight", "RRDB_trunk.16.RDB2.conv2.bias", "RRDB_trunk.16.RDB2.conv3.weight", "RRDB_trunk.16.RDB2.conv3.bias", "RRDB_trunk.16.RDB2.conv4.weight", "RRDB_trunk.16.RDB2.conv4.bias", "RRDB_trunk.16.RDB2.conv5.weight", "RRDB_trunk.16.RDB2.conv5.bias", "RRDB_trunk.16.RDB3.conv1.weight", "RRDB_trunk.16.RDB3.conv1.bias", "RRDB_trunk.16.RDB3.conv2.weight", "RRDB_trunk.16.RDB3.conv2.bias", "RRDB_trunk.16.RDB3.conv3.weight", "RRDB_trunk.16.RDB3.conv3.bias", "RRDB_trunk.16.RDB3.conv4.weight", "RRDB_trunk.16.RDB3.conv4.bias", "RRDB_trunk.16.RDB3.conv5.weight", "RRDB_trunk.16.RDB3.conv5.bias", "RRDB_trunk.17.RDB1.conv1.weight", "RRDB_trunk.17.RDB1.conv1.bias", "RRDB_trunk.17.RDB1.conv2.weight", "RRDB_trunk.17.RDB1.conv2.bias", "RRDB_trunk.17.RDB1.conv3.weight", "RRDB_trunk.17.RDB1.conv3.bias", "RRDB_trunk.17.RDB1.conv4.weight", "RRDB_trunk.17.RDB1.conv4.bias", "RRDB_trunk.17.RDB1.conv5.weight", "RRDB_trunk.17.RDB1.conv5.bias", "RRDB_trunk.17.RDB2.conv1.weight", "RRDB_trunk.17.RDB2.conv1.bias", "RRDB_trunk.17.RDB2.conv2.weight", "RRDB_trunk.17.RDB2.conv2.bias", "RRDB_trunk.17.RDB2.conv3.weight", "RRDB_trunk.17.RDB2.conv3.bias", "RRDB_trunk.17.RDB2.conv4.weight", "RRDB_trunk.17.RDB2.conv4.bias", "RRDB_trunk.17.RDB2.conv5.weight", "RRDB_trunk.17.RDB2.conv5.bias", "RRDB_trunk.17.RDB3.conv1.weight", "RRDB_trunk.17.RDB3.conv1.bias", "RRDB_trunk.17.RDB3.conv2.weight", "RRDB_trunk.17.RDB3.conv2.bias", "RRDB_trunk.17.RDB3.conv3.weight", "RRDB_trunk.17.RDB3.conv3.bias", "RRDB_trunk.17.RDB3.conv4.weight", "RRDB_trunk.17.RDB3.conv4.bias", "RRDB_trunk.17.RDB3.conv5.weight", "RRDB_trunk.17.RDB3.conv5.bias", "RRDB_trunk.18.RDB1.conv1.weight", "RRDB_trunk.18.RDB1.conv1.bias", "RRDB_trunk.18.RDB1.conv2.weight", "RRDB_trunk.18.RDB1.conv2.bias", "RRDB_trunk.18.RDB1.conv3.weight", "RRDB_trunk.18.RDB1.conv3.bias", "RRDB_trunk.18.RDB1.conv4.weight", "RRDB_trunk.18.RDB1.conv4.bias", "RRDB_trunk.18.RDB1.conv5.weight", "RRDB_trunk.18.RDB1.conv5.bias", "RRDB_trunk.18.RDB2.conv1.weight", "RRDB_trunk.18.RDB2.conv1.bias", "RRDB_trunk.18.RDB2.conv2.weight", "RRDB_trunk.18.RDB2.conv2.bias", "RRDB_trunk.18.RDB2.conv3.weight", "RRDB_trunk.18.RDB2.conv3.bias", "RRDB_trunk.18.RDB2.conv4.weight", "RRDB_trunk.18.RDB2.conv4.bias", "RRDB_trunk.18.RDB2.conv5.weight", "RRDB_trunk.18.RDB2.conv5.bias", "RRDB_trunk.18.RDB3.conv1.weight", "RRDB_trunk.18.RDB3.conv1.bias", "RRDB_trunk.18.RDB3.conv2.weight", "RRDB_trunk.18.RDB3.conv2.bias", "RRDB_trunk.18.RDB3.conv3.weight", "RRDB_trunk.18.RDB3.conv3.bias", "RRDB_trunk.18.RDB3.conv4.weight", "RRDB_trunk.18.RDB3.conv4.bias", "RRDB_trunk.18.RDB3.conv5.weight", "RRDB_trunk.18.RDB3.conv5.bias", "RRDB_trunk.19.RDB1.conv1.weight", "RRDB_trunk.19.RDB1.conv1.bias", "RRDB_trunk.19.RDB1.conv2.weight", "RRDB_trunk.19.RDB1.conv2.bias", "RRDB_trunk.19.RDB1.conv3.weight", "RRDB_trunk.19.RDB1.conv3.bias", "RRDB_trunk.19.RDB1.conv4.weight", "RRDB_trunk.19.RDB1.conv4.bias", "RRDB_trunk.19.RDB1.conv5.weight", "RRDB_trunk.19.RDB1.conv5.bias", "RRDB_trunk.19.RDB2.conv1.weight", "RRDB_trunk.19.RDB2.conv1.bias", "RRDB_trunk.19.RDB2.conv2.weight", "RRDB_trunk.19.RDB2.conv2.bias", "RRDB_trunk.19.RDB2.conv3.weight", "RRDB_trunk.19.RDB2.conv3.bias", "RRDB_trunk.19.RDB2.conv4.weight", "RRDB_trunk.19.RDB2.conv4.bias", "RRDB_trunk.19.RDB2.conv5.weight", "RRDB_trunk.19.RDB2.conv5.bias", "RRDB_trunk.19.RDB3.conv1.weight", "RRDB_trunk.19.RDB3.conv1.bias", "RRDB_trunk.19.RDB3.conv2.weight", "RRDB_trunk.19.RDB3.conv2.bias", "RRDB_trunk.19.RDB3.conv3.weight", "RRDB_trunk.19.RDB3.conv3.bias", "RRDB_trunk.19.RDB3.conv4.weight", "RRDB_trunk.19.RDB3.conv4.bias", "RRDB_trunk.19.RDB3.conv5.weight", "RRDB_trunk.19.RDB3.conv5.bias", "RRDB_trunk.20.RDB1.conv1.weight", "RRDB_trunk.20.RDB1.conv1.bias", "RRDB_trunk.20.RDB1.conv2.weight", "RRDB_trunk.20.RDB1.conv2.bias", "RRDB_trunk.20.RDB1.conv3.weight", "RRDB_trunk.20.RDB1.conv3.bias", "RRDB_trunk.20.RDB1.conv4.weight", "RRDB_trunk.20.RDB1.conv4.bias", "RRDB_trunk.20.RDB1.conv5.weight", "RRDB_trunk.20.RDB1.conv5.bias", "RRDB_trunk.20.RDB2.conv1.weight", "RRDB_trunk.20.RDB2.conv1.bias", "RRDB_trunk.20.RDB2.conv2.weight", "RRDB_trunk.20.RDB2.conv2.bias", "RRDB_trunk.20.RDB2.conv3.weight", "RRDB_trunk.20.RDB2.conv3.bias", "RRDB_trunk.20.RDB2.conv4.weight", "RRDB_trunk.20.RDB2.conv4.bias", "RRDB_trunk.20.RDB2.conv5.weight", "RRDB_trunk.20.RDB2.conv5.bias", "RRDB_trunk.20.RDB3.conv1.weight", "RRDB_trunk.20.RDB3.conv1.bias", "RRDB_trunk.20.RDB3.conv2.weight", "RRDB_trunk.20.RDB3.conv2.bias", "RRDB_trunk.20.RDB3.conv3.weight", "RRDB_trunk.20.RDB3.conv3.bias", "RRDB_trunk.20.RDB3.conv4.weight", "RRDB_trunk.20.RDB3.conv4.bias", "RRDB_trunk.20.RDB3.conv5.weight", "RRDB_trunk.20.RDB3.conv5.bias", "RRDB_trunk.21.RDB1.conv1.weight", "RRDB_trunk.21.RDB1.conv1.bias", "RRDB_trunk.21.RDB1.conv2.weight", "RRDB_trunk.21.RDB1.conv2.bias", "RRDB_trunk.21.RDB1.conv3.weight", "RRDB_trunk.21.RDB1.conv3.bias", "RRDB_trunk.21.RDB1.conv4.weight", "RRDB_trunk.21.RDB1.conv4.bias", "RRDB_trunk.21.RDB1.conv5.weight", "RRDB_trunk.21.RDB1.conv5.bias", "RRDB_trunk.21.RDB2.conv1.weight", "RRDB_trunk.21.RDB2.conv1.bias", "RRDB_trunk.21.RDB2.conv2.weight", "RRDB_trunk.21.RDB2.conv2.bias", "RRDB_trunk.21.RDB2.conv3.weight", "RRDB_trunk.21.RDB2.conv3.bias", "RRDB_trunk.21.RDB2.conv4.weight", "RRDB_trunk.21.RDB2.conv4.bias", "RRDB_trunk.21.RDB2.conv5.weight", "RRDB_trunk.21.RDB2.conv5.bias", "RRDB_trunk.21.RDB3.conv1.weight", "RRDB_trunk.21.RDB3.conv1.bias", "RRDB_trunk.21.RDB3.conv2.weight", "RRDB_trunk.21.RDB3.conv2.bias", "RRDB_trunk.21.RDB3.conv3.weight", "RRDB_trunk.21.RDB3.conv3.bias", "RRDB_trunk.21.RDB3.conv4.weight", "RRDB_trunk.21.RDB3.conv4.bias", "RRDB_trunk.21.RDB3.conv5.weight", "RRDB_trunk.21.RDB3.conv5.bias", "RRDB_trunk.22.RDB1.conv1.weight", "RRDB_trunk.22.RDB1.conv1.bias", "RRDB_trunk.22.RDB1.conv2.weight", "RRDB_trunk.22.RDB1.conv2.bias", "RRDB_trunk.22.RDB1.conv3.weight", "RRDB_trunk.22.RDB1.conv3.bias", "RRDB_trunk.22.RDB1.conv4.weight", "RRDB_trunk.22.RDB1.conv4.bias", "RRDB_trunk.22.RDB1.conv5.weight", "RRDB_trunk.22.RDB1.conv5.bias", "RRDB_trunk.22.RDB2.conv1.weight", "RRDB_trunk.22.RDB2.conv1.bias", "RRDB_trunk.22.RDB2.conv2.weight", "RRDB_trunk.22.RDB2.conv2.bias", "RRDB_trunk.22.RDB2.conv3.weight", "RRDB_trunk.22.RDB2.conv3.bias", "RRDB_trunk.22.RDB2.conv4.weight", "RRDB_trunk.22.RDB2.conv4.bias", "RRDB_trunk.22.RDB2.conv5.weight", "RRDB_trunk.22.RDB2.conv5.bias", "RRDB_trunk.22.RDB3.conv1.weight", "RRDB_trunk.22.RDB3.conv1.bias", "RRDB_trunk.22.RDB3.conv2.weight", "RRDB_trunk.22.RDB3.conv2.bias", "RRDB_trunk.22.RDB3.conv3.weight", "RRDB_trunk.22.RDB3.conv3.bias", "RRDB_trunk.22.RDB3.conv4.weight", "RRDB_trunk.22.RDB3.conv4.bias", "RRDB_trunk.22.RDB3.conv5.weight", "RRDB_trunk.22.RDB3.conv5.bias", "trunk_conv.weight", "trunk_conv.bias", "upconv1.weight", "upconv1.bias", "upconv2.weight", "upconv2.bias", "HRconv.weight", "HRconv.bias", "conv_last.weight", "conv_last.bias". Unexpected key(s) in state_dict: "model.0.weight", "model.0.bias", "model.1.sub.0.RDB1.conv1.0.weight", "model.1.sub.0.RDB1.conv1.0.bias", "model.1.sub.0.RDB1.conv2.0.weight", "model.1.sub.0.RDB1.conv2.0.bias", "model.1.sub.0.RDB1.conv3.0.weight", "model.1.sub.0.RDB1.conv3.0.bias", "model.1.sub.0.RDB1.conv4.0.weight", "model.1.sub.0.RDB1.conv4.0.bias", "model.1.sub.0.RDB1.conv5.0.weight", "model.1.sub.0.RDB1.conv5.0.bias", "model.1.sub.0.RDB2.conv1.0.weight", "model.1.sub.0.RDB2.conv1.0.bias", "model.1.sub.0.RDB2.conv2.0.weight", "model.1.sub.0.RDB2.conv2.0.bias", "model.1.sub.0.RDB2.conv3.0.weight", "model.1.sub.0.RDB2.conv3.0.bias", "model.1.sub.0.RDB2.conv4.0.weight", "model.1.sub.0.RDB2.conv4.0.bias", "model.1.sub.0.RDB2.conv5.0.weight", "model.1.sub.0.RDB2.conv5.0.bias", "model.1.sub.0.RDB3.conv1.0.weight", "model.1.sub.0.RDB3.conv1.0.bias", "model.1.sub.0.RDB3.conv2.0.weight", "model.1.sub.0.RDB3.conv2.0.bias", "model.1.sub.0.RDB3.conv3.0.weight", "model.1.sub.0.RDB3.conv3.0.bias", "model.1.sub.0.RDB3.conv4.0.weight", "model.1.sub.0.RDB3.conv4.0.bias", "model.1.sub.0.RDB3.conv5.0.weight", "model.1.sub.0.RDB3.conv5.0.bias", "model.1.sub.1.RDB1.conv1.0.weight", "model.1.sub.1.RDB1.conv1.0.bias", "model.1.sub.1.RDB1.conv2.0.weight", "model.1.sub.1.RDB1.conv2.0.bias", "model.1.sub.1.RDB1.conv3.0.weight", "model.1.sub.1.RDB1.conv3.0.bias", "model.1.sub.1.RDB1.conv4.0.weight", "model.1.sub.1.RDB1.conv4.0.bias", "model.1.sub.1.RDB1.conv5.0.weight", "model.1.sub.1.RDB1.conv5.0.bias", "model.1.sub.1.RDB2.conv1.0.weight", "model.1.sub.1.RDB2.conv1.0.bias", "model.1.sub.1.RDB2.conv2.0.weight", "model.1.sub.1.RDB2.conv2.0.bias", "model.1.sub.1.RDB2.conv3.0.weight", "model.1.sub.1.RDB2.conv3.0.bias", "model.1.sub.1.RDB2.conv4.0.weight", "model.1.sub.1.RDB2.conv4.0.bias", "model.1.sub.1.RDB2.conv5.0.weight", "model.1.sub.1.RDB2.conv5.0.bias", "model.1.sub.1.RDB3.conv1.0.weight", "model.1.sub.1.RDB3.conv1.0.bias", "model.1.sub.1.RDB3.conv2.0.weight", "model.1.sub.1.RDB3.conv2.0.bias", "model.1.sub.1.RDB3.conv3.0.weight", "model.1.sub.1.RDB3.conv3.0.bias", "model.1.sub.1.RDB3.conv4.0.weight", "model.1.sub.1.RDB3.conv4.0.bias", "model.1.sub.1.RDB3.conv5.0.weight", "model.1.sub.1.RDB3.conv5.0.bias", "model.1.sub.2.RDB1.conv1.0.weight", "model.1.sub.2.RDB1.conv1.0.bias", "model.1.sub.2.RDB1.conv2.0.weight", "model.1.sub.2.RDB1.conv2.0.bias", "model.1.sub.2.RDB1.conv3.0.weight", "model.1.sub.2.RDB1.conv3.0.bias", "model.1.sub.2.RDB1.conv4.0.weight", "model.1.sub.2.RDB1.conv4.0.bias", "model.1.sub.2.RDB1.conv5.0.weight", "model.1.sub.2.RDB1.conv5.0.bias", "model.1.sub.2.RDB2.conv1.0.weight", "model.1.sub.2.RDB2.conv1.0.bias", "model.1.sub.2.RDB2.conv2.0.weight", "model.1.sub.2.RDB2.conv2.0.bias", "model.1.sub.2.RDB2.conv3.0.weight", "model.1.sub.2.RDB2.conv3.0.bias", "model.1.sub.2.RDB2.conv4.0.weight", "model.1.sub.2.RDB2.conv4.0.bias", "model.1.sub.2.RDB2.conv5.0.weight", "model.1.sub.2.RDB2.conv5.0.bias", "model.1.sub.2.RDB3.conv1.0.weight", "model.1.sub.2.RDB3.conv1.0.bias", "model.1.sub.2.RDB3.conv2.0.weight", "model.1.sub.2.RDB3.conv2.0.bias", "model.1.sub.2.RDB3.conv3.0.weight", "model.1.sub.2.RDB3.conv3.0.bias", "model.1.sub.2.RDB3.conv4.0.weight", "model.1.sub.2.RDB3.conv4.0.bias", "model.1.sub.2.RDB3.conv5.0.weight", "model.1.sub.2.RDB3.conv5.0.bias", "model.1.sub.3.RDB1.conv1.0.weight", "model.1.sub.3.RDB1.conv1.0.bias", "model.1.sub.3.RDB1.conv2.0.weight", "model.1.sub.3.RDB1.conv2.0.bias", "model.1.sub.3.RDB1.conv3.0.weight", "model.1.sub.3.RDB1.conv3.0.bias", "model.1.sub.3.RDB1.conv4.0.weight", "model.1.sub.3.RDB1.conv4.0.bias", "model.1.sub.3.RDB1.conv5.0.weight", "model.1.sub.3.RDB1.conv5.0.bias", "model.1.sub.3.RDB2.conv1.0.weight", "model.1.sub.3.RDB2.conv1.0.bias", "model.1.sub.3.RDB2.conv2.0.weight", "model.1.sub.3.RDB2.conv2.0.bias", "model.1.sub.3.RDB2.conv3.0.weight", "model.1.sub.3.RDB2.conv3.0.bias", "model.1.sub.3.RDB2.conv4.0.weight", "model.1.sub.3.RDB2.conv4.0.bias", "model.1.sub.3.RDB2.conv5.0.weight", "model.1.sub.3.RDB2.conv5.0.bias", "model.1.sub.3.RDB3.conv1.0.weight", "model.1.sub.3.RDB3.conv1.0.bias", "model.1.sub.3.RDB3.conv2.0.weight", "model.1.sub.3.RDB3.conv2.0.bias", "model.1.sub.3.RDB3.conv3.0.weight", "model.1.sub.3.RDB3.conv3.0.bias", "model.1.sub.3.RDB3.conv4.0.weight", "model.1.sub.3.RDB3.conv4.0.bias", "model.1.sub.3.RDB3.conv5.0.weight", "model.1.sub.3.RDB3.conv5.0.bias", "model.1.sub.4.RDB1.conv1.0.weight", "model.1.sub.4.RDB1.conv1.0.bias", "model.1.sub.4.RDB1.conv2.0.weight", "model.1.sub.4.RDB1.conv2.0.bias", "model.1.sub.4.RDB1.conv3.0.weight", "model.1.sub.4.RDB1.conv3.0.bias", "model.1.sub.4.RDB1.conv4.0.weight", "model.1.sub.4.RDB1.conv4.0.bias", "model.1.sub.4.RDB1.conv5.0.weight", "model.1.sub.4.RDB1.conv5.0.bias", "model.1.sub.4.RDB2.conv1.0.weight", "model.1.sub.4.RDB2.conv1.0.bias", "model.1.sub.4.RDB2.conv2.0.weight", "model.1.sub.4.RDB2.conv2.0.bias", "model.1.sub.4.RDB2.conv3.0.weight", "model.1.sub.4.RDB2.conv3.0.bias", "model.1.sub.4.RDB2.conv4.0.weight", "model.1.sub.4.RDB2.conv4.0.bias", "model.1.sub.4.RDB2.conv5.0.weight", "model.1.sub.4.RDB2.conv5.0.bias", "model.1.sub.4.RDB3.conv1.0.weight", "model.1.sub.4.RDB3.conv1.0.bias", "model.1.sub.4.RDB3.conv2.0.weight", "model.1.sub.4.RDB3.conv2.0.bias", "model.1.sub.4.RDB3.conv3.0.weight", "model.1.sub.4.RDB3.conv3.0.bias", "model.1.sub.4.RDB3.conv4.0.weight", "model.1.sub.4.RDB3.conv4.0.bias", "model.1.sub.4.RDB3.conv5.0.weight", "model.1.sub.4.RDB3.conv5.0.bias", "model.1.sub.5.RDB1.conv1.0.weight", "model.1.sub.5.RDB1.conv1.0.bias", "model.1.sub.5.RDB1.conv2.0.weight", "model.1.sub.5.RDB1.conv2.0.bias", "model.1.sub.5.RDB1.conv3.0.weight", "model.1.sub.5.RDB1.conv3.0.bias", "model.1.sub.5.RDB1.conv4.0.weight", "model.1.sub.5.RDB1.conv4.0.bias", "model.1.sub.5.RDB1.conv5.0.weight", "model.1.sub.5.RDB1.conv5.0.bias", "model.1.sub.5.RDB2.conv1.0.weight", "model.1.sub.5.RDB2.conv1.0.bias", "model.1.sub.5.RDB2.conv2.0.weight", "model.1.sub.5.RDB2.conv2.0.bias", "model.1.sub.5.RDB2.conv3.0.weight", "model.1.sub.5.RDB2.conv3.0.bias", "model.1.sub.5.RDB2.conv4.0.weight", "model.1.sub.5.RDB2.conv4.0.bias", "model.1.sub.5.RDB2.conv5.0.weight", "model.1.sub.5.RDB2.conv5.0.bias", "model.1.sub.5.RDB3.conv1.0.weight", "model.1.sub.5.RDB3.conv1.0.bias", "model.1.sub.5.RDB3.conv2.0.weight", "model.1.sub.5.RDB3.conv2.0.bias", "model.1.sub.5.RDB3.conv3.0.weight", "model.1.sub.5.RDB3.conv3.0.bias", "model.1.sub.5.RDB3.conv4.0.weight", "model.1.sub.5.RDB3.conv4.0.bias", "model.1.sub.5.RDB3.conv5.0.weight", "model.1.sub.5.RDB3.conv5.0.bias", "model.1.sub.6.RDB1.conv1.0.weight", "model.1.sub.6.RDB1.conv1.0.bias", "model.1.sub.6.RDB1.conv2.0.weight", "model.1.sub.6.RDB1.conv2.0.bias", "model.1.sub.6.RDB1.conv3.0.weight", "model.1.sub.6.RDB1.conv3.0.bias", "model.1.sub.6.RDB1.conv4.0.weight", "model.1.sub.6.RDB1.conv4.0.bias", "model.1.sub.6.RDB1.conv5.0.weight", "model.1.sub.6.RDB1.conv5.0.bias", "model.1.sub.6.RDB2.conv1.0.weight", "model.1.sub.6.RDB2.conv1.0.bias", "model.1.sub.6.RDB2.conv2.0.weight", "model.1.sub.6.RDB2.conv2.0.bias", "model.1.sub.6.RDB2.conv3.0.weight", "model.1.sub.6.RDB2.conv3.0.bias", "model.1.sub.6.RDB2.conv4.0.weight", "model.1.sub.6.RDB2.conv4.0.bias", "model.1.sub.6.RDB2.conv5.0.weight", "model.1.sub.6.RDB2.conv5.0.bias", "model.1.sub.6.RDB3.conv1.0.weight", "model.1.sub.6.RDB3.conv1.0.bias", "model.1.sub.6.RDB3.conv2.0.weight", "model.1.sub.6.RDB3.conv2.0.bias", "model.1.sub.6.RDB3.conv3.0.weight", "model.1.sub.6.RDB3.conv3.0.bias", "model.1.sub.6.RDB3.conv4.0.weight", "model.1.sub.6.RDB3.conv4.0.bias", "model.1.sub.6.RDB3.conv5.0.weight", "model.1.sub.6.RDB3.conv5.0.bias", "model.1.sub.7.RDB1.conv1.0.weight", "model.1.sub.7.RDB1.conv1.0.bias", "model.1.sub.7.RDB1.conv2.0.weight", "model.1.sub.7.RDB1.conv2.0.bias", "model.1.sub.7.RDB1.conv3.0.weight", "model.1.sub.7.RDB1.conv3.0.bias", "model.1.sub.7.RDB1.conv4.0.weight", "model.1.sub.7.RDB1.conv4.0.bias", "model.1.sub.7.RDB1.conv5.0.weight", "model.1.sub.7.RDB1.conv5.0.bias", "model.1.sub.7.RDB2.conv1.0.weight", "model.1.sub.7.RDB2.conv1.0.bias", "model.1.sub.7.RDB2.conv2.0.weight", "model.1.sub.7.RDB2.conv2.0.bias", "model.1.sub.7.RDB2.conv3.0.weight", "model.1.sub.7.RDB2.conv3.0.bias", "model.1.sub.7.RDB2.conv4.0.weight", "model.1.sub.7.RDB2.conv4.0.bias", "model.1.sub.7.RDB2.conv5.0.weight", "model.1.sub.7.RDB2.conv5.0.bias", "model.1.sub.7.RDB3.conv1.0.weight", "model.1.sub.7.RDB3.conv1.0.bias", "model.1.sub.7.RDB3.conv2.0.weight", "model.1.sub.7.RDB3.conv2.0.bias", "model.1.sub.7.RDB3.conv3.0.weight", "model.1.sub.7.RDB3.conv3.0.bias", "model.1.sub.7.RDB3.conv4.0.weight", "model.1.sub.7.RDB3.conv4.0.bias", "model.1.sub.7.RDB3.conv5.0.weight", "model.1.sub.7.RDB3.conv5.0.bias", "model.1.sub.8.RDB1.conv1.0.weight", "model.1.sub.8.RDB1.conv1.0.bias", "model.1.sub.8.RDB1.conv2.0.weight", "model.1.sub.8.RDB1.conv2.0.bias", "model.1.sub.8.RDB1.conv3.0.weight", "model.1.sub.8.RDB1.conv3.0.bias", "model.1.sub.8.RDB1.conv4.0.weight", "model.1.sub.8.RDB1.conv4.0.bias", "model.1.sub.8.RDB1.conv5.0.weight", "model.1.sub.8.RDB1.conv5.0.bias", "model.1.sub.8.RDB2.conv1.0.weight", "model.1.sub.8.RDB2.conv1.0.bias", "model.1.sub.8.RDB2.conv2.0.weight", "model.1.sub.8.RDB2.conv2.0.bias", "model.1.sub.8.RDB2.conv3.0.weight", "model.1.sub.8.RDB2.conv3.0.bias", "model.1.sub.8.RDB2.conv4.0.weight", "model.1.sub.8.RDB2.conv4.0.bias", "model.1.sub.8.RDB2.conv5.0.weight", "model.1.sub.8.RDB2.conv5.0.bias", "model.1.sub.8.RDB3.conv1.0.weight", "model.1.sub.8.RDB3.conv1.0.bias", "model.1.sub.8.RDB3.conv2.0.weight", "model.1.sub.8.RDB3.conv2.0.bias", "model.1.sub.8.RDB3.conv3.0.weight", "model.1.sub.8.RDB3.conv3.0.bias", "model.1.sub.8.RDB3.conv4.0.weight", "model.1.sub.8.RDB3.conv4.0.bias", "model.1.sub.8.RDB3.conv5.0.weight", "model.1.sub.8.RDB3.conv5.0.bias", "model.1.sub.9.RDB1.conv1.0.weight", "model.1.sub.9.RDB1.conv1.0.bias", "model.1.sub.9.RDB1.conv2.0.weight", "model.1.sub.9.RDB1.conv2.0.bias", "model.1.sub.9.RDB1.conv3.0.weight", "model.1.sub.9.RDB1.conv3.0.bias", "model.1.sub.9.RDB1.conv4.0.weight", "model.1.sub.9.RDB1.conv4.0.bias", "model.1.sub.9.RDB1.conv5.0.weight", "model.1.sub.9.RDB1.conv5.0.bias", "model.1.sub.9.RDB2.conv1.0.weight", "model.1.sub.9.RDB2.conv1.0.bias", "model.1.sub.9.RDB2.conv2.0.weight", "model.1.sub.9.RDB2.conv2.0.bias", "model.1.sub.9.RDB2.conv3.0.weight", "model.1.sub.9.RDB2.conv3.0.bias", "model.1.sub.9.RDB2.conv4.0.weight", "model.1.sub.9.RDB2.conv4.0.bias", "model.1.sub.9.RDB2.conv5.0.weight", "model.1.sub.9.RDB2.conv5.0.bias", "model.1.sub.9.RDB3.conv1.0.weight", "model.1.sub.9.RDB3.conv1.0.bias", "model.1.sub.9.RDB3.conv2.0.weight", "model.1.sub.9.RDB3.conv2.0.bias", "model.1.sub.9.RDB3.conv3.0.weight", "model.1.sub.9.RDB3.conv3.0.bias", "model.1.sub.9.RDB3.conv4.0.weight", "model.1.sub.9.RDB3.conv4.0.bias", "model.1.sub.9.RDB3.conv5.0.weight", "model.1.sub.9.RDB3.conv5.0.bias", "model.1.sub.10.RDB1.conv1.0.weight", "model.1.sub.10.RDB1.conv1.0.bias", "model.1.sub.10.RDB1.conv2.0.weight", "model.1.sub.10.RDB1.conv2.0.bias", "model.1.sub.10.RDB1.conv3.0.weight", "model.1.sub.10.RDB1.conv3.0.bias", "model.1.sub.10.RDB1.conv4.0.weight", "model.1.sub.10.RDB1.conv4.0.bias", "model.1.sub.10.RDB1.conv5.0.weight", "model.1.sub.10.RDB1.conv5.0.bias", "model.1.sub.10.RDB2.conv1.0.weight", "model.1.sub.10.RDB2.conv1.0.bias", "model.1.sub.10.RDB2.conv2.0.weight", "model.1.sub.10.RDB2.conv2.0.bias", "model.1.sub.10.RDB2.conv3.0.weight", "model.1.sub.10.RDB2.conv3.0.bias", "model.1.sub.10.RDB2.conv4.0.weight", "model.1.sub.10.RDB2.conv4.0.bias", "model.1.sub.10.RDB2.conv5.0.weight", "model.1.sub.10.RDB2.conv5.0.bias", "model.1.sub.10.RDB3.conv1.0.weight", "model.1.sub.10.RDB3.conv1.0.bias", "model.1.sub.10.RDB3.conv2.0.weight", "model.1.sub.10.RDB3.conv2.0.bias", "model.1.sub.10.RDB3.conv3.0.weight", "model.1.sub.10.RDB3.conv3.0.bias", "model.1.sub.10.RDB3.conv4.0.weight", "model.1.sub.10.RDB3.conv4.0.bias", "model.1.sub.10.RDB3.conv5.0.weight", "model.1.sub.10.RDB3.conv5.0.bias", "model.1.sub.11.RDB1.conv1.0.weight", "model.1.sub.11.RDB1.conv1.0.bias", "model.1.sub.11.RDB1.conv2.0.weight", "model.1.sub.11.RDB1.conv2.0.bias", "model.1.sub.11.RDB1.conv3.0.weight", "model.1.sub.11.RDB1.conv3.0.bias", "model.1.sub.11.RDB1.conv4.0.weight", "model.1.sub.11.RDB1.conv4.0.bias", "model.1.sub.11.RDB1.conv5.0.weight", "model.1.sub.11.RDB1.conv5.0.bias", "model.1.sub.11.RDB2.conv1.0.weight", "model.1.sub.11.RDB2.conv1.0.bias", "model.1.sub.11.RDB2.conv2.0.weight", "model.1.sub.11.RDB2.conv2.0.bias", "model.1.sub.11.RDB2.conv3.0.weight", "model.1.sub.11.RDB2.conv3.0.bias", "model.1.sub.11.RDB2.conv4.0.weight", "model.1.sub.11.RDB2.conv4.0.bias", "model.1.sub.11.RDB2.conv5.0.weight", "model.1.sub.11.RDB2.conv5.0.bias", "model.1.sub.11.RDB3.conv1.0.weight", "model.1.sub.11.RDB3.conv1.0.bias", "model.1.sub.11.RDB3.conv2.0.weight", "model.1.sub.11.RDB3.conv2.0.bias", "model.1.sub.11.RDB3.conv3.0.weight", "model.1.sub.11.RDB3.conv3.0.bias", "model.1.sub.11.RDB3.conv4.0.weight", "model.1.sub.11.RDB3.conv4.0.bias", "model.1.sub.11.RDB3.conv5.0.weight", "model.1.sub.11.RDB3.conv5.0.bias", "model.1.sub.12.RDB1.conv1.0.weight", "model.1.sub.12.RDB1.conv1.0.bias", "model.1.sub.12.RDB1.conv2.0.weight", "model.1.sub.12.RDB1.conv2.0.bias", "model.1.sub.12.RDB1.conv3.0.weight", "model.1.sub.12.RDB1.conv3.0.bias", "model.1.sub.12.RDB1.conv4.0.weight", "model.1.sub.12.RDB1.conv4.0.bias", "model.1.sub.12.RDB1.conv5.0.weight", "model.1.sub.12.RDB1.conv5.0.bias", "model.1.sub.12.RDB2.conv1.0.weight", "model.1.sub.12.RDB2.conv1.0.bias", "model.1.sub.12.RDB2.conv2.0.weight", "model.1.sub.12.RDB2.conv2.0.bias", "model.1.sub.12.RDB2.conv3.0.weight", "model.1.sub.12.RDB2.conv3.0.bias", "model.1.sub.12.RDB2.conv4.0.weight", "model.1.sub.12.RDB2.conv4.0.bias", "model.1.sub.12.RDB2.conv5.0.weight", "model.1.sub.12.RDB2.conv5.0.bias", "model.1.sub.12.RDB3.conv1.0.weight", "model.1.sub.12.RDB3.conv1.0.bias", "model.1.sub.12.RDB3.conv2.0.weight", "model.1.sub.12.RDB3.conv2.0.bias", "model.1.sub.12.RDB3.conv3.0.weight", "model.1.sub.12.RDB3.conv3.0.bias", "model.1.sub.12.RDB3.conv4.0.weight", "model.1.sub.12.RDB3.conv4.0.bias", "model.1.sub.12.RDB3.conv5.0.weight", "model.1.sub.12.RDB3.conv5.0.bias", "model.1.sub.13.RDB1.conv1.0.weight", "model.1.sub.13.RDB1.conv1.0.bias", "model.1.sub.13.RDB1.conv2.0.weight", "model.1.sub.13.RDB1.conv2.0.bias", "model.1.sub.13.RDB1.conv3.0.weight", "model.1.sub.13.RDB1.conv3.0.bias", "model.1.sub.13.RDB1.conv4.0.weight", "model.1.sub.13.RDB1.conv4.0.bias", "model.1.sub.13.RDB1.conv5.0.weight", "model.1.sub.13.RDB1.conv5.0.bias", "model.1.sub.13.RDB2.conv1.0.weight", "model.1.sub.13.RDB2.conv1.0.bias", "model.1.sub.13.RDB2.conv2.0.weight", "model.1.sub.13.RDB2.conv2.0.bias", "model.1.sub.13.RDB2.conv3.0.weight", "model.1.sub.13.RDB2.conv3.0.bias", "model.1.sub.13.RDB2.conv4.0.weight", "model.1.sub.13.RDB2.conv4.0.bias", "model.1.sub.13.RDB2.conv5.0.weight", "model.1.sub.13.RDB2.conv5.0.bias", "model.1.sub.13.RDB3.conv1.0.weight", "model.1.sub.13.RDB3.conv1.0.bias", "model.1.sub.13.RDB3.conv2.0.weight", "model.1.sub.13.RDB3.conv2.0.bias", "model.1.sub.13.RDB3.conv3.0.weight", "model.1.sub.13.RDB3.conv3.0.bias", "model.1.sub.13.RDB3.conv4.0.weight", "model.1.sub.13.RDB3.conv4.0.bias", "model.1.sub.13.RDB3.conv5.0.weight", "model.1.sub.13.RDB3.conv5.0.bias", "model.1.sub.14.RDB1.conv1.0.weight", "model.1.sub.14.RDB1.conv1.0.bias", "model.1.sub.14.RDB1.conv2.0.weight", "model.1.sub.14.RDB1.conv2.0.bias", "model.1.sub.14.RDB1.conv3.0.weight", "model.1.sub.14.RDB1.conv3.0.bias", "model.1.sub.14.RDB1.conv4.0.weight", "model.1.sub.14.RDB1.conv4.0.bias", "model.1.sub.14.RDB1.conv5.0.weight", "model.1.sub.14.RDB1.conv5.0.bias", "model.1.sub.14.RDB2.conv1.0.weight", "model.1.sub.14.RDB2.conv1.0.bias", "model.1.sub.14.RDB2.conv2.0.weight", "model.1.sub.14.RDB2.conv2.0.bias", "model.1.sub.14.RDB2.conv3.0.weight", "model.1.sub.14.RDB2.conv3.0.bias", "model.1.sub.14.RDB2.conv4.0.weight", "model.1.sub.14.RDB2.conv4.0.bias", "model.1.sub.14.RDB2.conv5.0.weight", "model.1.sub.14.RDB2.conv5.0.bias", "model.1.sub.14.RDB3.conv1.0.weight", "model.1.sub.14.RDB3.conv1.0.bias", "model.1.sub.14.RDB3.conv2.0.weight", "model.1.sub.14.RDB3.conv2.0.bias", "model.1.sub.14.RDB3.conv3.0.weight", "model.1.sub.14.RDB3.conv3.0.bias", "model.1.sub.14.RDB3.conv4.0.weight", "model.1.sub.14.RDB3.conv4.0.bias", "model.1.sub.14.RDB3.conv5.0.weight", "model.1.sub.14.RDB3.conv5.0.bias", "model.1.sub.15.RDB1.conv1.0.weight", "model.1.sub.15.RDB1.conv1.0.bias", "model.1.sub.15.RDB1.conv2.0.weight", "model.1.sub.15.RDB1.conv2.0.bias", "model.1.sub.15.RDB1.conv3.0.weight", "model.1.sub.15.RDB1.conv3.0.bias", "model.1.sub.15.RDB1.conv4.0.weight", "model.1.sub.15.RDB1.conv4.0.bias", "model.1.sub.15.RDB1.conv5.0.weight", "model.1.sub.15.RDB1.conv5.0.bias", "model.1.sub.15.RDB2.conv1.0.weight", "model.1.sub.15.RDB2.conv1.0.bias", "model.1.sub.15.RDB2.conv2.0.weight", "model.1.sub.15.RDB2.conv2.0.bias", "model.1.sub.15.RDB2.conv3.0.weight", "model.1.sub.15.RDB2.conv3.0.bias", "model.1.sub.15.RDB2.conv4.0.weight", "model.1.sub.15.RDB2.conv4.0.bias", "model.1.sub.15.RDB2.conv5.0.weight", "model.1.sub.15.RDB2.conv5.0.bias", "model.1.sub.15.RDB3.conv1.0.weight", "model.1.sub.15.RDB3.conv1.0.bias", "model.1.sub.15.RDB3.conv2.0.weight", "model.1.sub.15.RDB3.conv2.0.bias", "model.1.sub.15.RDB3.conv3.0.weight", "model.1.sub.15.RDB3.conv3.0.bias", "model.1.sub.15.RDB3.conv4.0.weight", "model.1.sub.15.RDB3.conv4.0.bias", "model.1.sub.15.RDB3.conv5.0.weight", "model.1.sub.15.RDB3.conv5.0.bias", "model.1.sub.16.RDB1.conv1.0.weight", "model.1.sub.16.RDB1.conv1.0.bias", "model.1.sub.16.RDB1.conv2.0.weight", "model.1.sub.16.RDB1.conv2.0.bias", "model.1.sub.16.RDB1.conv3.0.weight", "model.1.sub.16.RDB1.conv3.0.bias", "model.1.sub.16.RDB1.conv4.0.weight", "model.1.sub.16.RDB1.conv4.0.bias", "model.1.sub.16.RDB1.conv5.0.weight", "model.1.sub.16.RDB1.conv5.0.bias", "model.1.sub.16.RDB2.conv1.0.weight", "model.1.sub.16.RDB2.conv1.0.bias", "model.1.sub.16.RDB2.conv2.0.weight", "model.1.sub.16.RDB2.conv2.0.bias", "model.1.sub.16.RDB2.conv3.0.weight", "model.1.sub.16.RDB2.conv3.0.bias", "model.1.sub.16.RDB2.conv4.0.weight", "model.1.sub.16.RDB2.conv4.0.bias", "model.1.sub.16.RDB2.conv5.0.weight", "model.1.sub.16.RDB2.conv5.0.bias", "model.1.sub.16.RDB3.conv1.0.weight", "model.1.sub.16.RDB3.conv1.0.bias", "model.1.sub.16.RDB3.conv2.0.weight", "model.1.sub.16.RDB3.conv2.0.bias", "model.1.sub.16.RDB3.conv3.0.weight", "model.1.sub.16.RDB3.conv3.0.bias", "model.1.sub.16.RDB3.conv4.0.weight", "model.1.sub.16.RDB3.conv4.0.bias", "model.1.sub.16.RDB3.conv5.0.weight", "model.1.sub.16.RDB3.conv5.0.bias", "model.1.sub.17.RDB1.conv1.0.weight", "model.1.sub.17.RDB1.conv1.0.bias", "model.1.sub.17.RDB1.conv2.0.weight", "model.1.sub.17.RDB1.conv2.0.bias", "model.1.sub.17.RDB1.conv3.0.weight", "model.1.sub.17.RDB1.conv3.0.bias", "model.1.sub.17.RDB1.conv4.0.weight", "model.1.sub.17.RDB1.conv4.0.bias", "model.1.sub.17.RDB1.conv5.0.weight", "model.1.sub.17.RDB1.conv5.0.bias", "model.1.sub.17.RDB2.conv1.0.weight", "model.1.sub.17.RDB2.conv1.0.bias", "model.1.sub.17.RDB2.conv2.0.weight", "model.1.sub.17.RDB2.conv2.0.bias", "model.1.sub.17.RDB2.conv3.0.weight", "model.1.sub.17.RDB2.conv3.0.bias", "model.1.sub.17.RDB2.conv4.0.weight", "model.1.sub.17.RDB2.conv4.0.bias", "model.1.sub.17.RDB2.conv5.0.weight", "model.1.sub.17.RDB2.conv5.0.bias", "model.1.sub.17.RDB3.conv1.0.weight", "model.1.sub.17.RDB3.conv1.0.bias", "model.1.sub.17.RDB3.conv2.0.weight", "model.1.sub.17.RDB3.conv2.0.bias", "model.1.sub.17.RDB3.conv3.0.weight", "model.1.sub.17.RDB3.conv3.0.bias", "model.1.sub.17.RDB3.conv4.0.weight", "model.1.sub.17.RDB3.conv4.0.bias", "model.1.sub.17.RDB3.conv5.0.weight", "model.1.sub.17.RDB3.conv5.0.bias", "model.1.sub.18.RDB1.conv1.0.weight", "model.1.sub.18.RDB1.conv1.0.bias", "model.1.sub.18.RDB1.conv2.0.weight", "model.1.sub.18.RDB1.conv2.0.bias", "model.1.sub.18.RDB1.conv3.0.weight", "model.1.sub.18.RDB1.conv3.0.bias", "model.1.sub.18.RDB1.conv4.0.weight", "model.1.sub.18.RDB1.conv4.0.bias", "model.1.sub.18.RDB1.conv5.0.weight", "model.1.sub.18.RDB1.conv5.0.bias", "model.1.sub.18.RDB2.conv1.0.weight", "model.1.sub.18.RDB2.conv1.0.bias", "model.1.sub.18.RDB2.conv2.0.weight", "model.1.sub.18.RDB2.conv2.0.bias", "model.1.sub.18.RDB2.conv3.0.weight", "model.1.sub.18.RDB2.conv3.0.bias", "model.1.sub.18.RDB2.conv4.0.weight", "model.1.sub.18.RDB2.conv4.0.bias", "model.1.sub.18.RDB2.conv5.0.weight", "model.1.sub.18.RDB2.conv5.0.bias", "model.1.sub.18.RDB3.conv1.0.weight", "model.1.sub.18.RDB3.conv1.0.bias", "model.1.sub.18.RDB3.conv2.0.weight", "model.1.sub.18.RDB3.conv2.0.bias", "model.1.sub.18.RDB3.conv3.0.weight", "model.1.sub.18.RDB3.conv3.0.bias", "model.1.sub.18.RDB3.conv4.0.weight", "model.1.sub.18.RDB3.conv4.0.bias", "model.1.sub.18.RDB3.conv5.0.weight", "model.1.sub.18.RDB3.conv5.0.bias", "model.1.sub.19.RDB1.conv1.0.weight", "model.1.sub.19.RDB1.conv1.0.bias", "model.1.sub.19.RDB1.conv2.0.weight", "model.1.sub.19.RDB1.conv2.0.bias", "model.1.sub.19.RDB1.conv3.0.weight", "model.1.sub.19.RDB1.conv3.0.bias", "model.1.sub.19.RDB1.conv4.0.weight", "model.1.sub.19.RDB1.conv4.0.bias", "model.1.sub.19.RDB1.conv5.0.weight", "model.1.sub.19.RDB1.conv5.0.bias", "model.1.sub.19.RDB2.conv1.0.weight", "model.1.sub.19.RDB2.conv1.0.bias", "model.1.sub.19.RDB2.conv2.0.weight", "model.1.sub.19.RDB2.conv2.0.bias", "model.1.sub.19.RDB2.conv3.0.weight", "model.1.sub.19.RDB2.conv3.0.bias", "model.1.sub.19.RDB2.conv4.0.weight", "model.1.sub.19.RDB2.conv4.0.bias", "model.1.sub.19.RDB2.conv5.0.weight", "model.1.sub.19.RDB2.conv5.0.bias", "model.1.sub.19.RDB3.conv1.0.weight", "model.1.sub.19.RDB3.conv1.0.bias", "model.1.sub.19.RDB3.conv2.0.weight", "model.1.sub.19.RDB3.conv2.0.bias", "model.1.sub.19.RDB3.conv3.0.weight", "model.1.sub.19.RDB3.conv3.0.bias", "model.1.sub.19.RDB3.conv4.0.weight", "model.1.sub.19.RDB3.conv4.0.bias", "model.1.sub.19.RDB3.conv5.0.weight", "model.1.sub.19.RDB3.conv5.0.bias", "model.1.sub.20.RDB1.conv1.0.weight", "model.1.sub.20.RDB1.conv1.0.bias", "model.1.sub.20.RDB1.conv2.0.weight", "model.1.sub.20.RDB1.conv2.0.bias", "model.1.sub.20.RDB1.conv3.0.weight", "model.1.sub.20.RDB1.conv3.0.bias", "model.1.sub.20.RDB1.conv4.0.weight", "model.1.sub.20.RDB1.conv4.0.bias", "model.1.sub.20.RDB1.conv5.0.weight", "model.1.sub.20.RDB1.conv5.0.bias", "model.1.sub.20.RDB2.conv1.0.weight", "model.1.sub.20.RDB2.conv1.0.bias", "model.1.sub.20.RDB2.conv2.0.weight", "model.1.sub.20.RDB2.conv2.0.bias", "model.1.sub.20.RDB2.conv3.0.weight", "model.1.sub.20.RDB2.conv3.0.bias", "model.1.sub.20.RDB2.conv4.0.weight", "model.1.sub.20.RDB2.conv4.0.bias", "model.1.sub.20.RDB2.conv5.0.weight", "model.1.sub.20.RDB2.conv5.0.bias", "model.1.sub.20.RDB3.conv1.0.weight", "model.1.sub.20.RDB3.conv1.0.bias", "model.1.sub.20.RDB3.conv2.0.weight", "model.1.sub.20.RDB3.conv2.0.bias", "model.1.sub.20.RDB3.conv3.0.weight", "model.1.sub.20.RDB3.conv3.0.bias", "model.1.sub.20.RDB3.conv4.0.weight", "model.1.sub.20.RDB3.conv4.0.bias", "model.1.sub.20.RDB3.conv5.0.weight", "model.1.sub.20.RDB3.conv5.0.bias", "model.1.sub.21.RDB1.conv1.0.weight", "model.1.sub.21.RDB1.conv1.0.bias", "model.1.sub.21.RDB1.conv2.0.weight", "model.1.sub.21.RDB1.conv2.0.bias", "model.1.sub.21.RDB1.conv3.0.weight", "model.1.sub.21.RDB1.conv3.0.bias", "model.1.sub.21.RDB1.conv4.0.weight", "model.1.sub.21.RDB1.conv4.0.bias", "model.1.sub.21.RDB1.conv5.0.weight", "model.1.sub.21.RDB1.conv5.0.bias", "model.1.sub.21.RDB2.conv1.0.weight", "model.1.sub.21.RDB2.conv1.0.bias", "model.1.sub.21.RDB2.conv2.0.weight", "model.1.sub.21.RDB2.conv2.0.bias", "model.1.sub.21.RDB2.conv3.0.weight", "model.1.sub.21.RDB2.conv3.0.bias", "model.1.sub.21.RDB2.conv4.0.weight", "model.1.sub.21.RDB2.conv4.0.bias", "model.1.sub.21.RDB2.conv5.0.weight", "model.1.sub.21.RDB2.conv5.0.bias", "model.1.sub.21.RDB3.conv1.0.weight", "model.1.sub.21.RDB3.conv1.0.bias", "model.1.sub.21.RDB3.conv2.0.weight", "model.1.sub.21.RDB3.conv2.0.bias", "model.1.sub.21.RDB3.conv3.0.weight", "model.1.sub.21.RDB3.conv3.0.bias", "model.1.sub.21.RDB3.conv4.0.weight", "model.1.sub.21.RDB3.conv4.0.bias", "model.1.sub.21.RDB3.conv5.0.weight", "model.1.sub.21.RDB3.conv5.0.bias", "model.1.sub.22.RDB1.conv1.0.weight", "model.1.sub.22.RDB1.conv1.0.bias", "model.1.sub.22.RDB1.conv2.0.weight", "model.1.sub.22.RDB1.conv2.0.bias", "model.1.sub.22.RDB1.conv3.0.weight", "model.1.sub.22.RDB1.conv3.0.bias", "model.1.sub.22.RDB1.conv4.0.weight", "model.1.sub.22.RDB1.conv4.0.bias", "model.1.sub.22.RDB1.conv5.0.weight", "model.1.sub.22.RDB1.conv5.0.bias", "model.1.sub.22.RDB2.conv1.0.weight", "model.1.sub.22.RDB2.conv1.0.bias", "model.1.sub.22.RDB2.conv2.0.weight", "model.1.sub.22.RDB2.conv2.0.bias", "model.1.sub.22.RDB2.conv3.0.weight", "model.1.sub.22.RDB2.conv3.0.bias", "model.1.sub.22.RDB2.conv4.0.weight", "model.1.sub.22.RDB2.conv4.0.bias", "model.1.sub.22.RDB2.conv5.0.weight", "model.1.sub.22.RDB2.conv5.0.bias", "model.1.sub.22.RDB3.conv1.0.weight", "model.1.sub.22.RDB3.conv1.0.bias", "model.1.sub.22.RDB3.conv2.0.weight", "model.1.sub.22.RDB3.conv2.0.bias", "model.1.sub.22.RDB3.conv3.0.weight", "model.1.sub.22.RDB3.conv3.0.bias", "model.1.sub.22.RDB3.conv4.0.weight", "model.1.sub.22.RDB3.conv4.0.bias", "model.1.sub.22.RDB3.conv5.0.weight", "model.1.sub.22.RDB3.conv5.0.bias", "model.1.sub.23.weight", "model.1.sub.23.bias", "model.3.weight", "model.3.bias", "model.6.weight", "model.6.bias", "model.8.weight", "model.8.bias", "model.10.weight", "model.10.bias". < I've tried looking for help online for how to fix it, but there isn't any information that can help me. I've tried the _old_arch.pth trick before anyone asks about that. Can someone help me out here?