Comments (3)
Hi @phexic,
Based on the logs, it seems that your model is diverging, most likely because of the very small batch size.
You can try to increase it by reducing the size of the training patches.
from pynet-pytorch.
Thank you for your prompt reply!
I did try batchsize 24 by using 2 V100(32g), howerver the same problem occured that mse(0.3079) did not change and psnr remained 6.6111. Also, during training epoch 1, mse suddenly increases and training result suddenly turns completely black(about from 700+ batchidx). By print hidden layer gradient,It seems gradient explodes (NAN).
At the same time, I have checked my custom training data, all training pairs's mse below 0.07 which is within the normal range. What do you think might be the cause?
Btw, line 58 in load_data.py
dslr_image = np.float32(misc.imresize(dslr_image, self.scale / 2.0)) / 255.0
Is it not necessary that self.scale / 2.0 because network in paper "Replacing Mobile Camera ISP with a Single Deep Learning Model
" only has 4 downsample layer differs from "Bokeh..".
from pynet-pytorch.
Hi @phexic , did you fix this problem? I got similar results:
Epoch 0, mse: 0.2329, psnr: 6.3279, ms-ssim: 0.5204
Epoch 1, mse: 0.0000, psnr: 54.1944, ms-ssim: 0.9943
Epoch 2, mse: 0.0000, psnr: 54.1944, ms-ssim: 0.9943
Epoch 3, mse: 0.0000, psnr: 54.1944, ms-ssim: 0.9943
Epoch 4, mse: 0.0000, psnr: 54.1944, ms-ssim: 0.9943
Epoch 5, mse: 0.0000, psnr: 54.1944, ms-ssim: 0.9943
Epoch 6, mse: 0.0000, psnr: 54.1944, ms-ssim: 0.9943
from pynet-pytorch.
Related Issues (20)
- Minimal working example produces red tinted images on forward inference HOT 2
- Tensor size mismatch when testing on own png HOT 5
- About the preprocess of the dataset alignment HOT 3
- Problems when unzip the dataset HOT 1
- Is there any result comparsion with the AIM2019 RAW2RGB TOP1(MOS) solution? HOT 1
- can't download model from google drive HOT 2
- Model
- Weight input mismatch HOT 1
- A comparsion with the AIM2020 Image Signal Processing Challenge HOT 2
- How to convert raw images to Visualized RAW Images like yours paper examples HOT 1
- The dataset is different compared with tensorflow version
- Training Bokeh Problem
- Tensorflow vs Pytorch Activation Functions
- extract_bayer_channels HOT 1
- Can not download the Zurich RAW to RGB dataset HOT 2
- Cannot download the pretrain model HOT 2
- data preprocessing code of Zurich RAW to RGB dataset
- How to get visualized image?
- [Request] data preprocessing code for RAW andd RGB alignment
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 pynet-pytorch.