Comments (5)
Oh, well, ok then, I'll try this with my own version of the code.
Thank you.
from trainner.
Uuuuuuuuuhhhhhhh, pardon me?
You lost me.
from trainner.
python3 train.py -opt train_sr.yml export CUDA_VISIBLE_DEVICES=0 23-02-03 00:44:55.135 - INFO: name: 001_sr_template use_tb_logger: True model: sr scale: 4 gpu_ids: [0] use_amp: True use_swa: False use_cem: False use_atg: False datasets:[ train:[ name: DIV2K mode: aligned dataroot_HR: ['../datasets/train/hr1', '../datasets/train/hr2', '../datasets/train/hr3'] dataroot_LR: ['../datasets/train/lr1', '../datasets/train/lr2'] subset_file: None use_shuffle: True znorm: False n_workers: 4 batch_size: 8 virtual_batch_size: 8 preprocess: crop crop_size: 128 image_channels: 3 use_flip: True use_rot: True use_hrrot: False phase: train scale: 4 data_type: img aug_configs:[ lr_downscale_types:[ resize:[ resize_prob:[ down: 1.0 ] resize_range_up: [1, 1.5] resize_range_down: [0.15, 1] down_up_min: 0.5 ] ] ] shuffle_degradations: False lr_downscale: True lr_downscale_types: [773, 777] resize_strat: pre ] val:[ name: val_set14_part mode: aligned dataroot_B: ../datasets/val/hr dataroot_A: ../datasets/val/lr znorm: False lr_downscale: False lr_downscale_types: [773, 777] phase: val scale: 4 data_type: img resize_strat: pre ] ] path:[ root: .. pretrain_model_G: ../experiments/pretrained_models/RRDB_PSNR_x4.pth experiments_root: ../experiments/001_sr_template models: ../experiments/001_sr_template/models training_state: ../experiments/001_sr_template/training_state log: ../experiments/001_sr_template val_images: ../experiments/001_sr_template/val_images ] train:[ optim_G: adam optim_D: adam lr_scheme: MultiStepLR lr_gamma: 0.5 swa_lr: 0.0001 swa_anneal_epochs: 10 swa_anneal_strategy: cos pixel_criterion: l1 pixel_weight: 0.01 feature_criterion: l1 feature_weight: 1 gan_type: vanilla gan_weight: 0.005 manual_seed: 0 niter: 500000.0 val_freq: 5000.0 metrics: psnr,ssim,lpips grad_clip: norm grad_clip_value: 0.1 overwrite_val_imgs: None val_comparison: None lr_steps: [50000, 100000, 200000, 300000] swa_start_iter: 375000 atg_start_iter: 415000 ] logger:[ print_freq: 200 save_checkpoint_freq: 5000.0 overwrite_chkp: False ] is_train: True network_G:[ strict: False type: rrdb_net norm_type: None mode: CNA nf: 64 nb: 23 nr: 3 in_nc: 3 out_nc: 3 gc: 32 convtype: Conv2D act_type: leakyrelu gaussian_noise: True plus: False finalact: None upscale: 4 upsample_mode: upconv ] network_D:[ strict: True type: discriminator_vgg in_nc: 3 base_nf: 64 norm_type: batch mode: CNA act_type: leakyrelu convtype: Conv2D arch: ESRGAN size: 128 ] 23-02-03 00:44:55.421 - INFO: Random seed: 0 Traceback (most recent call last): File "/home/nickdbts2022/Desktop/traiNNer/codes/train.py", line 500, in <module> main() File "/home/nickdbts2022/Desktop/traiNNer/codes/train.py", line 487, in main dataloaders, data_params = get_dataloaders(opt) File "/home/nickdbts2022/Desktop/traiNNer/codes/train.py", line 134, in get_dataloaders dataset = create_dataset(dataset_opt) File "/home/nickdbts2022/Desktop/traiNNer/codes/data/__init__.py", line 79, in create_dataset dataset = D(dataset_opt) File "/home/nickdbts2022/Desktop/traiNNer/codes/data/aligned_dataset.py", line 41, in __init__ self.A_paths, self.B_paths = get_dataroots_paths(self.opt, strict=False, keys_ds=self.keys_ds) File "/home/nickdbts2022/Desktop/traiNNer/codes/data/base_dataset.py", line 235, in get_dataroots_paths paths_A, paths_B = read_dataroots(opt, keys_ds=keys_ds) File "/home/nickdbts2022/Desktop/traiNNer/codes/data/base_dataset.py", line 171, in read_dataroots paths_A = process_img_paths(A_images_paths, opt['data_type']) File "/home/nickdbts2022/Desktop/traiNNer/codes/data/base_dataset.py", line 61, in process_img_paths paths = get_image_paths(data_type, path, max_dataset_size) File "/home/nickdbts2022/Desktop/traiNNer/codes/dataops/common.py", line 82, in get_image_paths paths = sorted(_get_paths_from_images(dataroot, max_dataset_size=max_dataset_size)) File "/home/nickdbts2022/Desktop/traiNNer/codes/dataops/common.py", line 36, in _get_paths_from_images assert os.path.isdir(path), '{:s} is not a valid directory'.format(path) AssertionError: ../datasets/train/lr1 is not a valid directory
from trainner.
I am lost, would someone help please? This is put politely as its the first time I am working with modelling code.
from trainner.
Hello!
These lines:
dataroot_HR: ['../datasets/train/hr1', '../datasets/train/hr2', '../datasets/train/hr3']
dataroot_LR: ['../datasets/train/lr1', '../datasets/train/lr2']
Are only an example, you should put here the paths to your image datasets for training (https://github.com/victorca25/traiNNer#training, https://github.com/victorca25/traiNNer/blob/master/docs/howtotrain.md#normal-single-image-super-resolution-esrgan-srgan-pan-etc-models).
Something similar will happen with:
dataroot_B: ../datasets/val/hr
dataroot_A: ../datasets/val/lr
and:
pretrain_model_G: ../experiments/pretrained_models/RRDB_PSNR_x4.pth
The required files will have to exist in the path for them to be loaded correctly.
from trainner.
Related Issues (20)
- [Feature Request] Curriculum Training for Augmentations
- Pixel Unshuffle is broken HOT 2
- Video dataloader crashes at 1x scale
- Video learning rate too high
- Add lr_crop_size in config HOT 1
- Update requirements.txt with proper versioning for torch
- Feature request/bug fix: Perform scaling and other operations in linear light HOT 3
- `nearest_aligned` is not aligned HOT 2
- so many bugs in your sftgan implementation HOT 6
- How do i even use this HOT 2
- Is there any way to train video super resolution models using this? HOT 4
- lmdb has no valid image file HOT 3
- how to train for real ESRGAN HOT 1
- GPU usage at 0% during training HOT 7
- FutureWarning and UserWarning HOT 5
- "cv2.error: OpenCV(4.7.0) D:\a\opencv-python\opencv-python\opencv\modules\imgproc\src\resize.cpp:4065: error: (-215:Assertion failed) inv_scale_x > 0 in function 'cv::resize'" HOT 1
- ETA is grossly over-estimated. HOT 2
- Pix2Pix 3->1 channel HOT 1
- AttributeError: module 'collections' has no attribute 'Iterable' HOT 1
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from trainner.