Comments (7)
You need to make changes only in loadCamvid.lua
. What is the value of #classes
after this line?
from enet-training.
It seems that no matter which dataset I use, the decoder part is as follow, which is only one layer of convolution with 13 filters. Do you have any idea where to fix?
th> model = torch.load('model-4.net')
th> model
nn.ConcatTable {
input
|-> (1): cudnn.SpatialConvolution(3 -> 13, 3x3, 2,2, 1,1)
-> (2): nn.SpatialMaxPooling(2x2, 2,2)
... -> output
}
from enet-training.
Yes, the #classes is fine.
from enet-training.
As a sanity check consider looking at the models you're loading, and if they are pointing to the correct directories.
Since the dimensions are not hard-coded in the model/train/test files, this might be due to the pre-loaded model you're using.
from enet-training.
On closer inspection, I did find this in the encoder file pointing to a hard-coded dimension. This might fix your problem.
from enet-training.
See if you have the same issue as #3
from enet-training.
Thank you ishann and codeAC29, you were right, I was looking at wrong model. It works perfectly now!
from enet-training.
Related Issues (20)
- What is the learning rate decay and preprocessing you used in your training? HOT 13
- Consider hosting the pretrained model on Github HOT 1
- model-cityscapes.net released HOT 1
- what is the test time per image on cpu HOT 1
- implementation different from paper? HOT 1
- Do you freeze weights of encoder while training the whole model HOT 1
- encoder weights HOT 5
- "assertion failed!" When trying to run demo.lua
- In frameimage.lua:17: module 'fastimage' not found: HOT 2
- Not able to reproduce the fps on tx2 HOT 3
- Confused about the camVid dataset used to train encoder HOT 5
- Is the error the same as the loss HOT 1
- lua/5.2/nn/JoinTable.lua:38: bad argument #1 to 'copy' (sizes do not match at /home/user/torch/extra/cutorch/lib/THC/THCTensorCopy.cu:31) HOT 1
- add one more class to pre-trained model
- Which encoder weights should I use as CNNEncoder?
- Cityscapes Test Result HOT 1
- Assertion `t >= 0 && t < n_classes` failed, HOT 1
- Training ENet using own Dataset
- there is no mask when i try the visualization
- input and target should be of same size
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 enet-training.