Comments (3)
I think you should also modify the architecture of the network in RRDBNet_arch.py in order to upscale the necessary amount. Hope it helps
from mmagic.
I am training an SRGAN model with 8x upscaling factor using an LQGT dataset. However the generator only upscales by a 4x factor.
Here is my config
use_tb_logger: True model: srgan distortion: sr scale: 8 gpu_ids: [0, 1, 2, 3] datasets:[ train:[ name: DIV2K mode: LQGT dataroot_LQ: path/to/my/data2.lmdb dataroot_GT: path/to/my/data.lmdb use_shuffle: True n_workers: 6 batch_size: 32 GT_size: 128 use_flip: True use_rot: True color: RGB phase: train scale: 8 data_type: lmdb ] val:[ name: DIV2K mode: LQGT dataroot_LQ: another/path.lmdb dataroot_GT: path/to/data.lmdb phase: val scale: 8 data_type: lmdb ] ] network_G:[ which_model_G: RRDBNet in_nc: 3 out_nc: 3 nf: 64 nb: 16 upscale: 8 scale: 8 ] network_D:[ which_model_D: discriminator_vgg_128 in_nc: 3 nf: 64 ] path:[ pretrain_model_G: network_configs/RRDB_PSNR_x4.pth strict_load: False resume_state: None experiments_root: /home/centos/init-scripts/mmsr-tissue-control/experiment root: /home/centos/init-scripts models: /home/centos/init-scripts/mmsr-tissue-control/experiment/models training_state: /home/centos/init-scripts/mmsr-tissue-control/experiment/training_state log: /home/centos/init-scripts/mmsr-tissue-control/experiment val_images: /home/centos/init-scripts/mmsr-tissue-control/experiment/val_images ] train:[ lr_G: 0.0001 weight_decay_G: 0 beta1_G: 0.9 beta2_G: 0.99 lr_D: 0.0001 weight_decay_D: 0 beta1_D: 0.9 beta2_D: 0.99 lr_scheme: MultiStepLR niter: 400000 warmup_iter: -1 lr_steps: [50000, 100000, 200000, 300000] lr_gamma: 0.5 pixel_criterion: l1 pixel_weight: 0.01 feature_criterion: l1 feature_weight: 1 gan_type: gan gan_weight: 0.005 D_update_ratio: 1 D_init_iters: 0 manual_seed: 10 val_freq: 5000.0 ] logger:[ print_freq: 100 save_checkpoint_freq: 4000.0 ] is_train: True dist: False
I added the following code to LQGT_dataset.py under SRGANModel.optimize_paramters: (starting at L140)
self.fake_H=self.netG(self.var_L) print(self.var_L.shape) print(self.fake_H.shape)
This yields the following output at train time
torch.Size([32, 3, 16, 16]) torch.Size([32, 3, 64, 64])
Is there a fix? Can someone help me shed light on this problem?
Have you dealt with it and what's the size of your hr pictures
from mmagic.
Thanks for using MMSR.
We will upgrade MMSR to MMEditing (in the same repo), which consists of SR, inpainting, matting and generation tasks.
And MMSR will be deprecated and no longer exist.
Your suggestions will be updated in MMEditing.
from mmagic.
Related Issues (20)
- When I run python gradio_PowerPaint.py, it looks for a .bin file in models/unet folder. But the model is a .safetensors file, changing the extension to .bin causes a pickle error. Any workaround?[Bug] HOT 1
- [Feature] PowerPaint training code
- [Bug] Error when running PowerPaint: Entry Not Found for facenet.pth URL HOT 2
- [Bug] Invalid 'input_ids' in position:0 to 75.Expect'[49428,49429,49430,49431,49432,49433,49434,49435,49436,49437] for embedding 'P_obj' but found '[49428,49407]'
- [Feature] Give model different intialization
- [Bug] removal inpainting still include remnants of people HOT 1
- PowerPaint Windows MMCV Error
- PowerPaint Windows MMCV Error?
- [Bug] NSFW Error
- [Bug] no file of configs/animatediff/animatediff.py HOT 2
- [Bug] RealBasic got killed when loading model
- [Docs] The link MMEditing in the README redirects back to the same mmagic page
- [Bug] cyclegan:UnboundLocalError: local variable 'init_info' referenced before assignment HOT 2
- No module named 'diffusers.pipelines.controlnet_xs' HOT 9
- [Feature] The code and documentation are really terrible[Docs] HOT 1
- [Bug] - ImportError: /opt/conda/envs/mmagic/lib/python3.9/site-packages/mmcv/_ext.cpython-39-x86_64-linux-gnu.so: undefined symbol: _ZN3c105ErrorC2ENS_14SourceLocationESs
- [Docs] BasicVSR++ HOT 1
- torch.cuda.OutOfMemoryError: CUDA out of memory.real_basicvsr/basicvsr++运行报错 HOT 2
- [Bug] Can not use `ConcatImageVisualizer` in train step. / 在Train阶段可视化存在bug
- [Feature] Training and Testing Support for Stable Diffusion
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 mmagic.