search

xinntao / Real-ESRGAN

Real-ESRGAN aims at developing Practical Algorithms for General Image/Video Restoration.
BSD 3-Clause "New" or "Revised" License
28.63k stars 3.59k forks source link

local variable 'img_bytes' referenced before assignment #470

Open heraldob opened 2 years ago

heraldob commented 2 years ago

Hi, I'm new to programming, and maybe this problem is simple to solve. When running training with a single GPU:

!python reals great/train.py -opt options/train_realesrnet_x4plus.yml --debug

I get the following error:

Disable distributed. Path already exists. Rename it to /content/Real-ESRGAN/experiments/debug_train_RealESRNetx4plus_1000k_B12G4_archived_20221016_042439 2022-10-16 04:24:39,583 INFO: 

           / __ ) ____ _ _____ (_)_____/ ___/ / __ \
          / __  |/ __ `// ___// // ___/\__ \ / /_/ /
         / /_/ // /_/ /(__  )/ // /__ ___/ // _, _/
        /_____/ \__,_//____//_/ \___//____//_/ |_|
 ______                   __   __                 __      __
/ ____/____   ____   ____/ /  / /   __  __ _____ / /__   / /

/ / / \ / \ / / / / / / / // // /// / / / // // // // // // // / / /__/ // // / / /< // __/ __/ __/ __/ /____/_/ \///|| (_)

Version Information: BasicSR: 1.4.2 PyTorch: 1.12.1+cu113 TorchVision: 0.13.1+cu113 2022-10-16 04:24:39,583 INFO: name: debug_train_RealESRNetx4plus_1000k_B12G4 model_type: RealESRNetModel scale: 4 num_gpu: 1 manual_seed: 0 gt_usm: True resize_prob: [0.2, 0.7, 0.1] resize_range: [0.15, 1.5] gaussian_noise_prob: 0.5 noise_range: [1, 30] poisson_scale_range: [0.05, 3] gray_noise_prob: 0.4 jpeg_range: [30, 95] second_blur_prob: 0.8 resize_prob2: [0.3, 0.4, 0.3] resize_range2: [0.3, 1.2] gaussian_noise_prob2: 0.5 noise_range2: [1, 25] poisson_scale_range2: [0.05, 2.5] gray_noise_prob2: 0.4 jpeg_range2: [30, 95] gt_size: 256 queue_size: 180 datasets:[ train:[ name: DF2K+OST type: RealESRGANDataset dataroot_gt: /content/Real-ESRGAN/datasets/DF2K/DF2K_HR meta_info: /content/Real-ESRGAN/datasets/DF2K/meta_info/meta_info_DF2Kmultiscale.txt io_backend:[ type: disk ] blur_kernel_size: 21 kernel_list: ['iso', 'aniso', 'generalized_iso', 'generalized_aniso', 'plateau_iso', 'plateau_aniso'] kernel_prob: [0.45, 0.25, 0.12, 0.03, 0.12, 0.03] sinc_prob: 0.1 blur_sigma: [0.2, 3] betag_range: [0.5, 4] betap_range: [1, 2] blur_kernel_size2: 21 kernel_list2: ['iso', 'aniso', 'generalized_iso', 'generalized_aniso', 'plateau_iso', 'plateau_aniso'] kernel_prob2: [0.45, 0.25, 0.12, 0.03, 0.12, 0.03] sinc_prob2: 0.1 blur_sigma2: [0.2, 1.5] betag_range2: [0.5, 4] betap_range2: [1, 2] final_sinc_prob: 0.8 gt_size: 256 use_hflip: True use_rot: False use_shuffle: True num_worker_per_gpu: 5 batch_size_per_gpu: 12 dataset_enlarge_ratio: 1 prefetch_mode: None phase: train scale: 4 ] ] network_g:[ type: RRDBNet num_in_ch: 3 num_out_ch: 3 num_feat: 64 num_block: 23 num_grow_ch: 32 ] path:[ pretrain_network_g: experiments/pretrained_models/ESRGAN_SRx4_DF2KOST_official-ff704c30.pth param_key_g: params_ema strict_load_g: True resume_state: None experiments_root: /content/Real-ESRGAN/experiments/debug_train_RealESRNetx4plus_1000k_B12G4 models: /content/Real-ESRGAN/experiments/debug_train_RealESRNetx4plus_1000k_B12G4/models training_states: /content/Real-ESRGAN/experiments/debug_train_RealESRNetx4plus_1000k_B12G4/training_states log: /content/Real-ESRGAN/experiments/debug_train_RealESRNetx4plus_1000k_B12G4 visualization: /content/Real-ESRGAN/experiments/debug_train_RealESRNetx4plus_1000k_B12G4/visualization ] train:[ ema_decay: 0.999 optim_g:[ type: Adam lr: 0.0002 weight_decay: 0 betas: [0.9, 0.99] ] scheduler:[ type: MultiStepLR milestones: [1000000] gamma: 0.5 ] total_iter: 1000000 warmup_iter: -1 pixel_opt:[ type: L1Loss loss_weight: 1.0 reduction: mean ] ] logger:[ print_freq: 1 save_checkpoint_freq: 8 use_tb_logger: True wandb:[ project: None resume_id: None ] ] dist_params:[ backend: nccl port: 29500 ] dist: False rank: 0 world_size: 1 auto_resume: False is_train: True root_path: /content/Real-ESRGAN

2022-10-16 04:24:39,584 INFO: Dataset [RealESRGANDataset] - DF2K+OST is built. /usr/local/lib/python3.7/dist-packages/torch/utils/data/dataloader.py:566: UserWarning: This DataLoader will create 5 worker processes in total. Our suggested max number of worker in current system is 2, which is smaller than what this DataLoader is going to create. Please be aware that excessive worker creation might get DataLoader running slow or even freeze, lower the worker number to avoid potential slowness/freeze if necessary. cpuset_checked)) 2022-10-16 04:24:39,585 INFO: Training statistics: Number of train images: 90 Dataset enlarge ratio: 1 Batch size per gpu: 12 World size (gpu number): 1 Require iter number per epoch: 8 Total epochs: 125000; iters: 1000000. 2022-10-16 04:24:39,919 INFO: Network [RRDBNet] is created. 2022-10-16 04:24:41,709 INFO: Network: RRDBNet, with parameters: 16,697,987 2022-10-16 04:24:41,710 INFO: RRDBNet( (conv_first): Conv2d(3, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (body): Sequential( (0): RRDB( (rdb1): ResidualDenseBlock( (conv1): Conv2d(64, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (conv2): Conv2d(96, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (conv3): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (conv4): Conv2d(160, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (conv5): Conv2d(192, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (lrelu): LeakyReLU(negative_slope=0.2, inplace=True) ) (rdb2): ResidualDenseBlock( (conv1): Conv2d(64, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (conv2): Conv2d(96, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (conv3): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (conv4): Conv2d(160, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (conv5): Conv2d(192, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (lrelu): LeakyReLU(negative_slope=0.2, inplace=True) ) (rdb3): ResidualDenseBlock( (conv1): Conv2d(64, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (conv2): Conv2d(96, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (conv3): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (conv4): Conv2d(160, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (conv5): Conv2d(192, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (lrelu): LeakyReLU(negative_slope=0.2, inplace=True) ) ) (1): RRDB( (rdb1): ResidualDenseBlock( (conv1): Conv2d(64, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (conv2): Conv2d(96, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (conv3): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (conv4): Conv2d(160, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (conv5): Conv2d(192, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (lrelu): LeakyReLU(negative_slope=0.2, inplace=True) ) (rdb2): ResidualDenseBlock( (conv1): Conv2d(64, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (conv2): Conv2d(96, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (conv3): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (conv4): Conv2d(160, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (conv5): Conv2d(192, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (lrelu): LeakyReLU(negative_slope=0.2, inplace=True) ) (rdb3): ResidualDenseBlock( (conv1): Conv2d(64, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (conv2): Conv2d(96, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (conv3): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (conv4): Conv2d(160, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (conv5): Conv2d(192, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (lrelu): LeakyReLU(negative_slope=0.2, inplace=True) ) ) (2): RRDB( (rdb1): ResidualDenseBlock( (conv1): Conv2d(64, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (conv2): Conv2d(96, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (conv3): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (conv4): Conv2d(160, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (conv5): Conv2d(192, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (lrelu): LeakyReLU(negative_slope=0.2, inplace=True) ) (rdb2): ResidualDenseBlock( (conv1): Conv2d(64, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (conv2): Conv2d(96, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (conv3): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (conv4): Conv2d(160, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (conv5): Conv2d(192, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (lrelu): LeakyReLU(negative_slope=0.2, inplace=True) ) (rdb3): ResidualDenseBlock( (conv1): Conv2d(64, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (conv2): Conv2d(96, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (conv3): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (conv4): Conv2d(160, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (conv5): Conv2d(192, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (lrelu): LeakyReLU(negative_slope=0.2, inplace=True) ) ) (3): RRDB( (rdb1): ResidualDenseBlock( (conv1): Conv2d(64, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (conv2): Conv2d(96, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (conv3): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (conv4): Conv2d(160, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (conv5): Conv2d(192, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (lrelu): LeakyReLU(negative_slope=0.2, inplace=True) ) (rdb2): ResidualDenseBlock( (conv1): Conv2d(64, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (conv2): Conv2d(96, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (conv3): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (conv4): Conv2d(160, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (conv5): Conv2d(192, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (lrelu): LeakyReLU(negative_slope=0.2, inplace=True) ) (rdb3): ResidualDenseBlock( (conv1): Conv2d(64, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (conv2): Conv2d(96, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (conv3): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (conv4): Conv2d(160, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (conv5): Conv2d(192, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (lrelu): LeakyReLU(negative_slope=0.2, inplace=True) ) ) (4): RRDB( (rdb1): ResidualDenseBlock( (conv1): Conv2d(64, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (conv2): Conv2d(96, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (conv3): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (conv4): Conv2d(160, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (conv5): Conv2d(192, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (lrelu): LeakyReLU(negative_slope=0.2, inplace=True) ) (rdb2): ResidualDenseBlock( (conv1): Conv2d(64, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (conv2): Conv2d(96, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (conv3): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (conv4): Conv2d(160, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (conv5): Conv2d(192, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (lrelu): LeakyReLU(negative_slope=0.2, inplace=True) ) (rdb3): ResidualDenseBlock( (conv1): Conv2d(64, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (conv2): Conv2d(96, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (conv3): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (conv4): Conv2d(160, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (conv5): Conv2d(192, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (lrelu): LeakyReLU(negative_slope=0.2, inplace=True) ) ) (5): RRDB( (rdb1): ResidualDenseBlock( (conv1): Conv2d(64, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (conv2): Conv2d(96, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (conv3): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (conv4): Conv2d(160, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (conv5): Conv2d(192, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (lrelu): LeakyReLU(negative_slope=0.2, inplace=True) ) (rdb2): ResidualDenseBlock( (conv1): Conv2d(64, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (conv2): Conv2d(96, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (conv3): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (conv4): Conv2d(160, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (conv5): Conv2d(192, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (lrelu): LeakyReLU(negative_slope=0.2, inplace=True) ) (rdb3): ResidualDenseBlock( (conv1): Conv2d(64, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (conv2): Conv2d(96, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (conv3): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (conv4): Conv2d(160, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (conv5): Conv2d(192, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (lrelu): LeakyReLU(negative_slope=0.2, inplace=True) ) ) (6): RRDB( (rdb1): ResidualDenseBlock( (conv1): Conv2d(64, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (conv2): Conv2d(96, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (conv3): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (conv4): Conv2d(160, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (conv5): Conv2d(192, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (lrelu): LeakyReLU(negative_slope=0.2, inplace=True) ) (rdb2): ResidualDenseBlock( (conv1): Conv2d(64, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (conv2): Conv2d(96, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (conv3): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (conv4): Conv2d(160, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (conv5): Conv2d(192, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (lrelu): LeakyReLU(negative_slope=0.2, inplace=True) ) (rdb3): ResidualDenseBlock( (conv1): Conv2d(64, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (conv2): Conv2d(96, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (conv3): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (conv4): Conv2d(160, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (conv5): Conv2d(192, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (lrelu): LeakyReLU(negative_slope=0.2, inplace=True) ) ) (7): RRDB( (rdb1): ResidualDenseBlock( (conv1): Conv2d(64, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (conv2): Conv2d(96, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (conv3): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (conv4): Conv2d(160, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (conv5): Conv2d(192, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (lrelu): LeakyReLU(negative_slope=0.2, inplace=True) ) (rdb2): ResidualDenseBlock( (conv1): Conv2d(64, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (conv2): Conv2d(96, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (conv3): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (conv4): Conv2d(160, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (conv5): Conv2d(192, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (lrelu): LeakyReLU(negative_slope=0.2, inplace=True) ) (rdb3): ResidualDenseBlock( (conv1): Conv2d(64, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (conv2): Conv2d(96, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (conv3): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (conv4): Conv2d(160, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (conv5): Conv2d(192, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (lrelu): LeakyReLU(negative_slope=0.2, inplace=True) ) ) (8): RRDB( (rdb1): ResidualDenseBlock( (conv1): Conv2d(64, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (conv2): Conv2d(96, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (conv3): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (conv4): Conv2d(160, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (conv5): Conv2d(192, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (lrelu): LeakyReLU(negative_slope=0.2, inplace=True) ) (rdb2): ResidualDenseBlock( (conv1): Conv2d(64, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (conv2): Conv2d(96, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (conv3): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (conv4): Conv2d(160, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (conv5): Conv2d(192, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (lrelu): LeakyReLU(negative_slope=0.2, inplace=True) ) (rdb3): ResidualDenseBlock( (conv1): Conv2d(64, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (conv2): Conv2d(96, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (conv3): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (conv4): Conv2d(160, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (conv5): Conv2d(192, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (lrelu): LeakyReLU(negative_slope=0.2, inplace=True) ) ) (9): RRDB( (rdb1): ResidualDenseBlock( (conv1): Conv2d(64, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (conv2): Conv2d(96, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (conv3): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (conv4): Conv2d(160, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (conv5): Conv2d(192, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (lrelu): LeakyReLU(negative_slope=0.2, inplace=True) ) (rdb2): ResidualDenseBlock( (conv1): Conv2d(64, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (conv2): Conv2d(96, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (conv3): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (conv4): Conv2d(160, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (conv5): Conv2d(192, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (lrelu): LeakyReLU(negative_slope=0.2, inplace=True) ) (rdb3): ResidualDenseBlock( (conv1): Conv2d(64, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (conv2): Conv2d(96, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (conv3): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (conv4): Conv2d(160, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (conv5): Conv2d(192, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (lrelu): LeakyReLU(negative_slope=0.2, inplace=True) ) ) (10): RRDB( (rdb1): ResidualDenseBlock( (conv1): Conv2d(64, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (conv2): Conv2d(96, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (conv3): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (conv4): Conv2d(160, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (conv5): Conv2d(192, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (lrelu): LeakyReLU(negative_slope=0.2, inplace=True) ) (rdb2): ResidualDenseBlock( (conv1): Conv2d(64, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (conv2): Conv2d(96, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (conv3): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (conv4): Conv2d(160, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (conv5): Conv2d(192, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (lrelu): LeakyReLU(negative_slope=0.2, inplace=True) ) (rdb3): ResidualDenseBlock( (conv1): Conv2d(64, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (conv2): Conv2d(96, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (conv3): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (conv4): Conv2d(160, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (conv5): Conv2d(192, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (lrelu): LeakyReLU(negative_slope=0.2, inplace=True) ) ) (11): RRDB( (rdb1): ResidualDenseBlock( (conv1): Conv2d(64, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (conv2): Conv2d(96, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (conv3): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (conv4): Conv2d(160, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (conv5): Conv2d(192, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (lrelu): LeakyReLU(negative_slope=0.2, inplace=True) ) (rdb2): ResidualDenseBlock( (conv1): Conv2d(64, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (conv2): Conv2d(96, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (conv3): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (conv4): Conv2d(160, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (conv5): Conv2d(192, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (lrelu): LeakyReLU(negative_slope=0.2, inplace=True) ) (rdb3): ResidualDenseBlock( (conv1): Conv2d(64, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (conv2): Conv2d(96, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (conv3): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (conv4): Conv2d(160, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (conv5): Conv2d(192, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (lrelu): LeakyReLU(negative_slope=0.2, inplace=True) ) ) (12): RRDB( (rdb1): ResidualDenseBlock( (conv1): Conv2d(64, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (conv2): Conv2d(96, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (conv3): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (conv4): Conv2d(160, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (conv5): Conv2d(192, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (lrelu): LeakyReLU(negative_slope=0.2, inplace=True) ) (rdb2): ResidualDenseBlock( (conv1): Conv2d(64, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (conv2): Conv2d(96, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (conv3): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (conv4): Conv2d(160, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (conv5): Conv2d(192, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (lrelu): LeakyReLU(negative_slope=0.2, inplace=True) ) (rdb3): ResidualDenseBlock( (conv1): Conv2d(64, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (conv2): Conv2d(96, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (conv3): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (conv4): Conv2d(160, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (conv5): Conv2d(192, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (lrelu): LeakyReLU(negative_slope=0.2, inplace=True) ) ) (13): RRDB( (rdb1): ResidualDenseBlock( (conv1): Conv2d(64, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (conv2): Conv2d(96, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (conv3): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (conv4): Conv2d(160, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (conv5): Conv2d(192, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (lrelu): LeakyReLU(negative_slope=0.2, inplace=True) ) (rdb2): ResidualDenseBlock( (conv1): Conv2d(64, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (conv2): Conv2d(96, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (conv3): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (conv4): Conv2d(160, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (conv5): Conv2d(192, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (lrelu): LeakyReLU(negative_slope=0.2, inplace=True) ) (rdb3): ResidualDenseBlock( (conv1): Conv2d(64, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (conv2): Conv2d(96, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (conv3): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (conv4): Conv2d(160, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (conv5): Conv2d(192, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (lrelu): LeakyReLU(negative_slope=0.2, inplace=True) ) ) (14): RRDB( (rdb1): ResidualDenseBlock( (conv1): Conv2d(64, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (conv2): Conv2d(96, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (conv3): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (conv4): Conv2d(160, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (conv5): Conv2d(192, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (lrelu): LeakyReLU(negative_slope=0.2, inplace=True) ) (rdb2): ResidualDenseBlock( (conv1): Conv2d(64, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (conv2): Conv2d(96, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (conv3): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (conv4): Conv2d(160, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (conv5): Conv2d(192, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (lrelu): LeakyReLU(negative_slope=0.2, inplace=True) ) (rdb3): ResidualDenseBlock( (conv1): Conv2d(64, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (conv2): Conv2d(96, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (conv3): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (conv4): Conv2d(160, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (conv5): Conv2d(192, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (lrelu): LeakyReLU(negative_slope=0.2, inplace=True) ) ) (15): RRDB( (rdb1): ResidualDenseBlock( (conv1): Conv2d(64, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (conv2): Conv2d(96, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (conv3): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (conv4): Conv2d(160, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (conv5): Conv2d(192, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (lrelu): LeakyReLU(negative_slope=0.2, inplace=True) ) (rdb2): ResidualDenseBlock( (conv1): Conv2d(64, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (conv2): Conv2d(96, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (conv3): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (conv4): Conv2d(160, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (conv5): Conv2d(192, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (lrelu): LeakyReLU(negative_slope=0.2, inplace=True) ) (rdb3): ResidualDenseBlock( (conv1): Conv2d(64, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (conv2): Conv2d(96, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (conv3): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (conv4): Conv2d(160, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (conv5): Conv2d(192, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (lrelu): LeakyReLU(negative_slope=0.2, inplace=True) ) ) (16): RRDB( (rdb1): ResidualDenseBlock( (conv1): Conv2d(64, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (conv2): Conv2d(96, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (conv3): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (conv4): Conv2d(160, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (conv5): Conv2d(192, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (lrelu): LeakyReLU(negative_slope=0.2, inplace=True) ) (rdb2): ResidualDenseBlock( (conv1): Conv2d(64, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (conv2): Conv2d(96, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (conv3): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (conv4): Conv2d(160, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (conv5): Conv2d(192, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (lrelu): LeakyReLU(negative_slope=0.2, inplace=True) ) (rdb3): ResidualDenseBlock( (conv1): Conv2d(64, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (conv2): Conv2d(96, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (conv3): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (conv4): Conv2d(160, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (conv5): Conv2d(192, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (lrelu): LeakyReLU(negative_slope=0.2, inplace=True) ) ) (17): RRDB( (rdb1): ResidualDenseBlock( (conv1): Conv2d(64, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (conv2): Conv2d(96, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (conv3): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (conv4): Conv2d(160, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (conv5): Conv2d(192, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (lrelu): LeakyReLU(negative_slope=0.2, inplace=True) ) (rdb2): ResidualDenseBlock( (conv1): Conv2d(64, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (conv2): Conv2d(96, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (conv3): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (conv4): Conv2d(160, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (conv5): Conv2d(192, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (lrelu): LeakyReLU(negative_slope=0.2, inplace=True) ) (rdb3): ResidualDenseBlock( (conv1): Conv2d(64, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (conv2): Conv2d(96, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (conv3): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (conv4): Conv2d(160, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (conv5): Conv2d(192, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (lrelu): LeakyReLU(negative_slope=0.2, inplace=True) ) ) (18): RRDB( (rdb1): ResidualDenseBlock( (conv1): Conv2d(64, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (conv2): Conv2d(96, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (conv3): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (conv4): Conv2d(160, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (conv5): Conv2d(192, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (lrelu): LeakyReLU(negative_slope=0.2, inplace=True) ) (rdb2): ResidualDenseBlock( (conv1): Conv2d(64, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (conv2): Conv2d(96, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (conv3): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (conv4): Conv2d(160, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (conv5): Conv2d(192, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (lrelu): LeakyReLU(negative_slope=0.2, inplace=True) ) (rdb3): ResidualDenseBlock( (conv1): Conv2d(64, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (conv2): Conv2d(96, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (conv3): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (conv4): Conv2d(160, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (conv5): Conv2d(192, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (lrelu): LeakyReLU(negative_slope=0.2, inplace=True) ) ) (19): RRDB( (rdb1): ResidualDenseBlock( (conv1): Conv2d(64, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (conv2): Conv2d(96, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (conv3): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (conv4): Conv2d(160, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (conv5): Conv2d(192, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (lrelu): LeakyReLU(negative_slope=0.2, inplace=True) ) (rdb2): ResidualDenseBlock( (conv1): Conv2d(64, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (conv2): Conv2d(96, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (conv3): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (conv4): Conv2d(160, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (conv5): Conv2d(192, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (lrelu): LeakyReLU(negative_slope=0.2, inplace=True) ) (rdb3): ResidualDenseBlock( (conv1): Conv2d(64, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (conv2): Conv2d(96, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (conv3): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (conv4): Conv2d(160, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (conv5): Conv2d(192, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (lrelu): LeakyReLU(negative_slope=0.2, inplace=True) ) ) (20): RRDB( (rdb1): ResidualDenseBlock( (conv1): Conv2d(64, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (conv2): Conv2d(96, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (conv3): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (conv4): Conv2d(160, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (conv5): Conv2d(192, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (lrelu): LeakyReLU(negative_slope=0.2, inplace=True) ) (rdb2): ResidualDenseBlock( (conv1): Conv2d(64, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (conv2): Conv2d(96, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (conv3): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (conv4): Conv2d(160, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (conv5): Conv2d(192, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (lrelu): LeakyReLU(negative_slope=0.2, inplace=True) ) (rdb3): ResidualDenseBlock( (conv1): Conv2d(64, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (conv2): Conv2d(96, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (conv3): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (conv4): Conv2d(160, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (conv5): Conv2d(192, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (lrelu): LeakyReLU(negative_slope=0.2, inplace=True) ) ) (21): RRDB( (rdb1): ResidualDenseBlock( (conv1): Conv2d(64, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (conv2): Conv2d(96, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (conv3): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (conv4): Conv2d(160, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (conv5): Conv2d(192, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (lrelu): LeakyReLU(negative_slope=0.2, inplace=True) ) (rdb2): ResidualDenseBlock( (conv1): Conv2d(64, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (conv2): Conv2d(96, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (conv3): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (conv4): Conv2d(160, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (conv5): Conv2d(192, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (lrelu): LeakyReLU(negative_slope=0.2, inplace=True) ) (rdb3): ResidualDenseBlock( (conv1): Conv2d(64, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (conv2): Conv2d(96, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (conv3): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (conv4): Conv2d(160, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (conv5): Conv2d(192, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (lrelu): LeakyReLU(negative_slope=0.2, inplace=True) ) ) (22): RRDB( (rdb1): ResidualDenseBlock( (conv1): Conv2d(64, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (conv2): Conv2d(96, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (conv3): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (conv4): Conv2d(160, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (conv5): Conv2d(192, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (lrelu): LeakyReLU(negative_slope=0.2, inplace=True) ) (rdb2): ResidualDenseBlock( (conv1): Conv2d(64, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (conv2): Conv2d(96, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (conv3): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (conv4): Conv2d(160, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (conv5): Conv2d(192, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (lrelu): LeakyReLU(negative_slope=0.2, inplace=True) ) (rdb3): ResidualDenseBlock( (conv1): Conv2d(64, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (conv2): Conv2d(96, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (conv3): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (conv4): Conv2d(160, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (conv5): Conv2d(192, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (lrelu): LeakyReLU(negative_slope=0.2, inplace=True) ) ) ) (conv_body): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (conv_up1): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (conv_up2): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (conv_hr): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (conv_last): Conv2d(64, 3, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (lrelu): LeakyReLU(negative_slope=0.2, inplace=True) ) 2022-10-16 04:24:41,876 INFO: Loading: params_ema does not exist, use params. 2022-10-16 04:24:41,877 INFO: Loading RRDBNet model from experiments/pretrained_models/ESRGAN_SRx4_DF2KOST_official-ff704c30.pth, with param key: [params]. 2022-10-16 04:24:42,040 INFO: Use Exponential Moving Average with decay: 0.999 2022-10-16 04:24:42,341 INFO: Network [RRDBNet] is created. 2022-10-16 04:24:42,433 INFO: Loading: params_ema does not exist, use params. 2022-10-16 04:24:42,433 INFO: Loading RRDBNet model from experiments/pretrained_models/ESRGAN_SRx4_DF2KOST_official-ff704c30.pth, with param key: [params]. 2022-10-16 04:24:42,572 INFO: Loss [L1Loss] is created. 2022-10-16 04:24:42,597 INFO: Model [RealESRNetModel] is created. 2022-10-16 04:24:42,704 WARNING: File client error: [Errno 2] No such file or directory: '/content/Real-ESRGAN/datasets/DF2K/DF2K_HR/DF2K_multiscale/000001_s0015T2.png', remaining retry times: 2 2022-10-16 04:24:42,706 WARNING: File client error: [Errno 2] No such file or directory: '/content/Real-ESRGAN/datasets/DF2K/DF2K_HR/DF2K_multiscale/000001_s0018T0.png', remaining retry times: 2 2022-10-16 04:24:42,707 WARNING: File client error: [Errno 2] No such file or directory: '/content/Real-ESRGAN/datasets/DF2K/DF2K_HR/DF2K_multiscale/000001_s006T2.png', remaining retry times: 2 2022-10-16 04:24:42,707 WARNING: File client error: [Errno 2] No such file or directory: '/content/Real-ESRGAN/datasets/DF2K/DF2K_HR/DF2K_multiscale/000001_s002T2.png', remaining retry times: 2 2022-10-16 04:24:42,708 INFO: Start training from epoch: 0, iter: 0 2022-10-16 04:24:42,709 WARNING: File client error: [Errno 2] No such file or directory: '/content/Real-ESRGAN/datasets/DF2K/DF2K_HR/DF2K_multiscale/000001_s0010T2.png', remaining retry times: 2 2022-10-16 04:24:43,003 WARNING: File client error: [Errno 2] No such file or directory: '/content/Real-ESRGAN/datasets/DF2K/DF2K_HR/DF2K_multiscale/000001_s0015T2.png', remaining retry times: 2 2022-10-16 04:24:43,004 WARNING: File client error: [Errno 2] No such file or directory: '/content/Real-ESRGAN/datasets/DF2K/DF2K_HR/DF2K_multiscale/000001_s0018T0.png', remaining retry times: 2 2022-10-16 04:24:43,005 WARNING: File client error: [Errno 2] No such file or directory: '/content/Real-ESRGAN/datasets/DF2K/DF2K_HR/DF2K_multiscale/000001_s006T2.png', remaining retry times: 2 2022-10-16 04:24:43,005 WARNING: File client error: [Errno 2] No such file or directory: '/content/Real-ESRGAN/datasets/DF2K/DF2K_HR/DF2K_multiscale/000001_s002T2.png', remaining retry times: 2 2022-10-16 04:24:43,013 WARNING: File client error: [Errno 2] No such file or directory: '/content/Real-ESRGAN/datasets/DF2K/DF2K_HR/DF2K_multiscale/000001_s0010T2.png', remaining retry times: 2 2022-10-16 04:24:43,705 WARNING: File client error: [Errno 2] No such file or directory: '/content/Real-ESRGAN/datasets/DF2K/DF2K_HR/DF2K_multiscale/000001_s0016T3.png', remaining retry times: 1 2022-10-16 04:24:43,707 WARNING: File client error: [Errno 2] No such file or directory: '/content/Real-ESRGAN/datasets/DF2K/DF2K_HR/DF2K_HR/000001_s008.png', remaining retry times: 1 2022-10-16 04:24:43,709 WARNING: File client error: [Errno 2] No such file or directory: '/content/Real-ESRGAN/datasets/DF2K/DF2K_HR/DF2K_HR/000001_s0015.png', remaining retry times: 1 2022-10-16 04:24:43,709 WARNING: File client error: [Errno 2] No such file or directory: '/content/Real-ESRGAN/datasets/DF2K/DF2K_HR/DF2K_multiscale/000001_s0012T0.png', remaining retry times: 1 2022-10-16 04:24:43,711 WARNING: File client error: [Errno 2] No such file or directory: '/content/Real-ESRGAN/datasets/DF2K/DF2K_HR/DF2K_multiscale/000001_s0012T0.png', remaining retry times: 1 2022-10-16 04:24:44,004 WARNING: File client error: [Errno 2] No such file or directory: '/content/Real-ESRGAN/datasets/DF2K/DF2K_HR/DF2K_multiscale/000001_s0016T3.png', remaining retry times: 1 2022-10-16 04:24:44,006 WARNING: File client error: [Errno 2] No such file or directory: '/content/Real-ESRGAN/datasets/DF2K/DF2K_HR/DF2K_HR/000001_s0015.png', remaining retry times: 1 2022-10-16 04:24:44,006 WARNING: File client error: [Errno 2] No such file or directory: '/content/Real-ESRGAN/datasets/DF2K/DF2K_HR/DF2K_HR/000001_s008.png', remaining retry times: 1 2022-10-16 04:24:44,007 WARNING: File client error: [Errno 2] No such file or directory: '/content/Real-ESRGAN/datasets/DF2K/DF2K_HR/DF2K_multiscale/000001_s0012T0.png', remaining retry times: 1 2022-10-16 04:24:44,015 WARNING: File client error: [Errno 2] No such file or directory: '/content/Real-ESRGAN/datasets/DF2K/DF2K_HR/DF2K_multiscale/000001_s0012T0.png', remaining retry times: 1 2022-10-16 04:24:44,706 WARNING: File client error: [Errno 2] No such file or directory: '/content/Real-ESRGAN/datasets/DF2K/DF2K_HR/DF2K_multiscale/000001_s0017T3.png', remaining retry times: 0 2022-10-16 04:24:44,708 WARNING: File client error: [Errno 2] No such file or directory: '/content/Real-ESRGAN/datasets/DF2K/DF2K_HR/DF2K_multiscale/000001_s004T2.png', remaining retry times: 0 2022-10-16 04:24:44,710 WARNING: File client error: [Errno 2] No such file or directory: '/content/Real-ESRGAN/datasets/DF2K/DF2K_HR/DF2K_HR/000001_s002.png', remaining retry times: 0 2022-10-16 04:24:44,710 WARNING: File client error: [Errno 2] No such file or directory: '/content/Real-ESRGAN/datasets/DF2K/DF2K_HR/DF2K_multiscale/000001_s005T1.png', remaining retry times: 0 2022-10-16 04:24:44,712 WARNING: File client error: [Errno 2] No such file or directory: '/content/Real-ESRGAN/datasets/DF2K/DF2K_HR/DF2K_multiscale/000001_s0014T0.png', remaining retry times: 0 2022-10-16 04:24:45,006 WARNING: File client error: [Errno 2] No such file or directory: '/content/Real-ESRGAN/datasets/DF2K/DF2K_HR/DF2K_multiscale/000001_s0017T3.png', remaining retry times: 0 2022-10-16 04:24:45,007 WARNING: File client error: [Errno 2] No such file or directory: '/content/Real-ESRGAN/datasets/DF2K/DF2K_HR/DF2K_multiscale/000001_s004T2.png', remaining retry times: 0 2022-10-16 04:24:45,007 WARNING: File client error: [Errno 2] No such file or directory: '/content/Real-ESRGAN/datasets/DF2K/DF2K_HR/DF2K_HR/000001_s002.png', remaining retry times: 0 2022-10-16 04:24:45,008 WARNING: File client error: [Errno 2] No such file or directory: '/content/Real-ESRGAN/datasets/DF2K/DF2K_HR/DF2K_multiscale/000001_s005T1.png', remaining retry times: 0 2022-10-16 04:24:45,016 WARNING: File client error: [Errno 2] No such file or directory: '/content/Real-ESRGAN/datasets/DF2K/DF2K_HR/DF2K_multiscale/000001_s0014T0.png', remaining retry times: 0 2022-10-16 04:24:46,010 WARNING: File client error: [Errno 2] No such file or directory: '/content/Real-ESRGAN/datasets/DF2K/DF2K_HR/DF2K_multiscale/000001_s0018T2.png', remaining retry times: 2 Traceback (most recent call last): File "realesrgan/train.py", line 11, in train_pipeline(root_path) File "/usr/local/lib/python3.7/dist-packages/basicsr/train.py", line 157, in train_pipeline train_data = prefetcher.next() File "/usr/local/lib/python3.7/dist-packages/basicsr/data/prefetch_dataloader.py", line 76, in next return next(self.loader) File "/usr/local/lib/python3.7/dist-packages/torch/utils/data/dataloader.py", line 681, in next data = self._next_data() File "/usr/local/lib/python3.7/dist-packages/torch/utils/data/dataloader.py", line 1376, in _next_data return self._process_data(data) File "/usr/local/lib/python3.7/dist-packages/torch/utils/data/dataloader.py", line 1402, in _process_data data.reraise() File "/usr/local/lib/python3.7/dist-packages/torch/_utils.py", line 461, in reraise raise exception UnboundLocalError: Caught UnboundLocalError in DataLoader worker process 0. Original Traceback (most recent call last): File "/usr/local/lib/python3.7/dist-packages/torch/utils/data/_utils/worker.py", line 302, in _worker_loop data = fetcher.fetch(index) File "/usr/local/lib/python3.7/dist-packages/torch/utils/data/_utils/fetch.py", line 49, in fetch data = [self.dataset[idx] for idx in possibly_batched_index] File "/usr/local/lib/python3.7/dist-packages/torch/utils/data/_utils/fetch.py", line 49, in data = [self.dataset[idx] for idx in possibly_batched_index] File "/content/Real-ESRGAN/realesrgan/data/realesrgan_dataset.py", line 106, in getitem img_gt = imfrombytes(img_bytes, float32=True) UnboundLocalError: local variable 'img_bytes' referenced before assignment

Lenubolim commented 2 years ago

Maybe there are some errors in your path