Comments (1)
I'm probably a little late to the party, but let me answer this for the future wanderers. When you modify the network by adding/removing a layer or doing anything that modifies the architecture of the network, you are inherently changing the whole model itself.
Simply put, you made a new network. The state dict you're using is for the original model, and hence does not include the parameter entries for your layers. If you wish to test your modified network you will have to train it from scratch (which I wont suggest) or you can use transfer learning (which might save you a lot of time by converging to a lower loss quicker).
You may have to write your own script that initializes the weights of the original layers from the original state dict while using some other parameters initialization method (Glorot, He, Xavier initialization are some of them. Also see this) for the newer layers that you added.
Hope that helps.
from dbpn-pytorch.
Related Issues (20)
- What's class D_DownBlock(torch.nn.Module) mean?What's num_stages mean?
- The question about train. HOT 3
- I inserted some layers into dbpn.py,and it can be trained successfully.But failed to test.
- How to use correctly
- Question in main.py HOT 1
- normalization for DBPNITER
- cannot download zip file in any way
- I trained and eval got black images HOT 3
- what is the size of input ?
- Can't get the same results as in the article with pretrained model. HOT 2
- About training on GAN HOT 1
- Is it appropriate that the last convolutional layer of DBPN has no activation function?
- Training on other datasets HOT 1
- Did you initialize all models with zero 'a'?
- what's real critertion in main.py?
- Questions about the setting of network when denoising.
- Doubt about the patch_size parameter
- Discriminator pretrained model missing
- no valid convolution algorithms available in CuDNN
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 dbpn-pytorch.