Comments (12)
Please use Cityscapes code to convert the labels
from espnetv2.
ok...
from espnetv2.
I now use s=0.5, and 9 classes, total 44000 images,The sky and building result is very good, but the person classes result is so terrible that cannot recognize sometimes, Could you give me some advice?
from espnetv2.
How long did you train? Make sure your labels are correct
from espnetv2.
About less than 1 hour a epoch, I trained 50 epoches, Label is checked repeatly.
I find when s=1.5, person is recognized in first few epoch, but s = 0.5, it is occured in about 20-30 epoch and other classes perform worse than person not be found.
Now, It is a little embarrassed that when other classes performs nice, people cannot be splited;
when people could, other classes looks not very satisfying...
the mIou is 40% level.
from espnetv2.
Is your dataset balanced?
from espnetv2.
the number of person is fewer, and I think the aera of the sky and building is much more bigger than person, but I 'm confused how to solve it, If you add extra augmentation to person images, other classes are also become more
from espnetv2.
You can compute class-wise weights and pass it to loss function.
Let us assume that you have 2 classes whose area distribution in the dataset is 1000 and 50. Obviously, class 1 has more area and network will be biased towards this class. You can take inverse of these areas now to compute class-wise weights. Now you will have a weight vector with 0.001 and 0.02 as values. When you pass this vector to loss function, class with low pixel area is panelized more.
from espnetv2.
ok,thanks for your idea.
from espnetv2.
Hi, I find there are pretrained models for segmentation, but got state_dict key errors when load.
Unexpected key(s) in state_dict: "module.net.level1.conv.weight", "module.net.level1.bn.weight", "module.net.level1.bn.bias" ......"module.level5.4.bn.weight", "module.level5.4.act.weight"
Missing key(s) in state_dict: "module.level1.conv.weight", "module.level1.bn.running_var", "module.level1.bn.running_mean", "module.level1.bn.bias"......"module.project_l2.act.weight", "module.project_l1.1.conv.weight"
Is there something wrong?
from espnetv2.
You need to first wrap the model inside the DataParallel wrapper and then load the weights, something like this:
model = net.EESPNet_Seg(20, s=1.0)
model = nn.DataParallel(model)
model.load_state_dict(torch.load('../pretrained/espnet.pth'))
from espnetv2.
that's right, thank you
from espnetv2.
Related Issues (20)
- About cyclic learning rate HOT 1
- Downsampling HOT 1
- Training issues (from pretrained weights) HOT 1
- a strange question
- a strange question
- A strange problem encountered during training
- A strange problem encountered during training HOT 15
- About Power consumption HOT 9
- Turning ESPNet into c++ cudastream problem HOT 2
- train.txt create HOT 2
- compared with ShuffleNet V2 HOT 3
- train/eval for another dataset HOT 1
- Question about predict on espnetv2 HOT 3
- Espnet .pth with another scale factor HOT 1
- You have following values as class labels: [ 0 1 2 4 5 6 7 8 10 11 13 255] Some problem with labels. Please check image file: ./city/gtFine/train/cologne/cologne_000000_000019_gtFine_labelTrainIds.png Exiting!! HOT 2
- Network parameters of segmentation model in the paper HOT 5
- Have you used ImageNet pretrained weight to train epsnetv2 for segmentation? HOT 1
- Can anyone upload a pretrained model? HOT 1
- The tool to calculate FLOPs
- Can this model be used for regression tasks?
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 espnetv2.