Comments (23)
@saeedizadi
Thanks! I have tried to set num_classes to 1 and got zeros everywhere in the output mask. It turned out that I forgot to apply the Sigmoid to the output. Now, I got very good results. Thank you a lot!
from piwise.
when I set num_class=1 and use NLLLoss() loss, I will encounter an error:
RuntimeError: Assertion
cur_target >= 0 && cur_target < n_classes' failed. at /opt/conda/conda-bld/pytorch_1525812548180/work/aten/src/THNN/generic/SpatialClassNLLCriterion.c:111`
@andrewssobral
class UNet(nn.Module):
def __init__(self, n_channels=3, n_classes=1):
super(UNet, self).__init__()
self.down=resnet18()
self.inc = inconv(n_channels, 16)
self.down1 = down(64, 128)
self.down2 = down(128, 256)
self.down3 = down(256, 512)
self.down4 = down(512, 512)'''
self.up1 = up(96, 64,64,drop=0.2)
self.up2 = up(80, 32,64,drop=0.2)
self.up3 = up(48, 16,32,drop=0.1)
self.up4 = up(32, 16,16,drop=0.1)
self.outc = outconv(16, n_classes)
self.reset_params()
criterion=nn.NLLLoss()
for ii,(data,mask,_)in enumerate(trainloader):
#训练模型
data,mask=data.to(device),mask.to(device)
mask=mask.long()
optimizer.zero_grad()
out=myNet(data)#numclass=1
out = F.log_softmax(out, dim=1)
loss=criterion(out,mask)
from piwise.
@saeedizadi maybe has some?
from piwise.
I've modified the models by @bodokaiser for a binary segmentation problems on medical images (using nn.Sigmoid + BCELoss) and hence my pretrained models may not come helpful in general. However, the training is very straight forward on other datasets.
Let me know if you help.
from piwise.
Hi @saeedizadi , can you share what you changed for the binary segmentation? I have set the number of classes = 2 everywhere and used a Sigmoid + BCELoss. However, I got some weird results. How did you modify the output of the net with shape (2xHxW) to match to the mask's shape (1xHxW)?
Thanks!
from piwise.
Hi @ZweeLe
Yes, I wanna share the modifications but I'm a bit out of time these days.
You must change the num_classes to 1 instead of 2. Then, simply change the last layer activation function to nn.Sigmoid() and employ nn.BCELoss() in your code.
Let me know if you need more information.
Saeed
from piwise.
Hi @saeedizadi ,
I am trying to do the same as @ZweeLe (binary segmentation), but I'm lost.
When you talk about:
You must change the num_classes to 1 instead of 2. Then, simply change the last layer activation function to nn.Sigmoid() and employ nn.BCELoss() in your code.
It means:
#NUM_CLASSES = 22
NUM_CLASSES = 1
and
class CrossEntropyLoss2d(nn.Module):
def __init__(self, weight=None):
super().__init__()
#self.loss = nn.NLLLoss2d(weight)
self.loss = nn.BCELoss(weight)
def forward(self, outputs, targets):
#return self.loss(F.log_softmax(outputs), targets)
m = nn.Sigmoid()
return self.loss(m(outputs), targets)
?
from piwise.
Hi @ZweeLe ,
Can you share your modifications for binary segmentation? Thanks
from piwise.
I think you are right that binary segmentation only needs 1 output class / channel with 0 corresponding to first and 1 corresponding to second class.
So something like:
model = Net(1)
criterion = nn.BCEWithLogitsLoss()
outputs = model(inputs)
loss = criterion(outputs, targets)
should work. Further check outputs
and targets
to check if they are compatible with what BCEWithLogitsLoss expects.
from piwise.
Hi @andrewssobral , you just need to follow the above modifications of @bodokaiser. For calculating the loss, the outputs and targets must be 1D arrays:
loss = criterion(outputs.view(-1), targets.view(-1))
To use the nn.BCEWithLogitsLoss() you have to build Pytorch from source. For me I used nn.Sigmoid() and nn.BCELoss() but they are less numerically stable.
For the evaluating code, you will need another post processing code:
outputs = model(inputs)
mask = sigmoid(outputs) * 255
mask[mask < thres] = 0
mask[mask >= thres] = 255
"thres" is the threshold pixel value you set to make a binary mask. You can find out the best value with validation (mine is 120). If you use the default transform then you don't need to multiply with 255.
from piwise.
Thank you @ZweeLe !
When you say:
To use the nn.BCEWithLogitsLoss() you have to build Pytorch from source. For me I used nn.Sigmoid() and nn.BCELoss() but they are less numerically stable.
It means?
class CrossEntropyLoss2d(nn.Module):
def __init__(self, weight=None):
super().__init__()
#self.loss = nn.NLLLoss2d(weight)
#self.loss = nn.BCEWithLogitsLoss(weight)
self.loss = nn.BCELoss(weight)
def forward(self, outputs, targets):
#return self.loss(F.log_softmax(outputs), targets)
#return self.loss(outputs, targets)
return self.loss(nn.Sigmoid(outputs), targets)
from piwise.
@andrewssobral Yes, they are similar. However, the BCELoss only accepts 1D tensors so you have to reshape your tensors or you can define a new BCELoss2d function.
from piwise.
Thank you @ZweeLe
I did your tips, and now the algorithm is running, but the loss becomes negative, please see:
loss: 1.2735891342163086 (epoch: 1, step: 0)
save: segnet-001-0000.pth (epoch: 1, step: 0)
loss: -1.1411563158035278 (epoch: 1, step: 1)
loss: -3.6113040447235107 (epoch: 1, step: 2)
loss: -4.822791635990143 (epoch: 1, step: 3)
loss: -6.884974336624145 (epoch: 1, step: 4)
loss: -7.026113708813985 (epoch: 1, step: 5)
loss: -8.921686070305961 (epoch: 1, step: 6)
loss: -10.695589691400528 (epoch: 1, step: 7)
loss: -11.778627316157023 (epoch: 1, step: 8)
loss: -13.278458523750306 (epoch: 1, step: 9)
loss: -14.816673040390015 (epoch: 1, step: 10)
loss: -16.244035343329113 (epoch: 1, step: 11)
loss: -17.84725154363192 (epoch: 1, step: 12)
loss: -19.353035739489965 (epoch: 1, step: 13)
loss: -21.03988642692566 (epoch: 1, step: 14)
loss: -22.63021345436573 (epoch: 1, step: 15)
loss: -23.58169169986949 (epoch: 1, step: 16)
loss: -25.269151012102764 (epoch: 1, step: 17)
loss: -26.97707804880644 (epoch: 1, step: 18)
loss: -28.725287783145905 (epoch: 1, step: 19)
loss: -29.03264051391965 (epoch: 1, step: 20)
loss: -30.018881505185906 (epoch: 1, step: 21)
loss: -31.15997344514598 (epoch: 1, step: 22)
loss: -32.05112152298292 (epoch: 1, step: 23)
loss: -33.00953503608704 (epoch: 1, step: 24)
loss: -35.36375263104072 (epoch: 1, step: 25)
loss: -36.99868559837341 (epoch: 1, step: 26)
loss: -39.33454824345453 (epoch: 1, step: 27)
loss: -41.40287765141191 (epoch: 1, step: 28)
this is normal?
from piwise.
@andrewssobral That is weird, the loss must be positive and decrease over time. You should check your outputs of the model and the targeted masks before applying BCELoss. All values should be in range of 0~1. Did you apply the transformation to the labels?
from piwise.
Hi @ZweeLe ,
I solved this issue by changing this:
input_transform = Compose([
CenterCrop(256),
ToTensor(),
Normalize([.485, .456, .406], [.229, .224, .225]),
])
target_transform = Compose([
CenterCrop(256),
ToLabel(),
Relabel(255, 21),
])
to this:
input_transform = Compose([
Scale((64,64)),
ToTensor(),
])
target_transform = Compose([
Scale((64,64)),
ToTensor(),
])
Now, the algorithm is learning well, the loss is decreasing and the preliminary results are very good! Thank you! and thanks to @bodokaiser for your advices ;-)
from piwise.
@andrewssobral Yes. The ToLabel() and Relabel() are not necessary for binary segmentation. Can you share your training time? For me, it took nearly 5 secs for an iteration and 0.5s to evaluate an image, which is a bit slow since I have a large dataset.
from piwise.
@ZweeLe as I have only 126 images and I'm using Amazon EC2 with p2x.large instance (NVIDIA K80 with 12Gb of RAM), the training time is very fast (less than 5 minutes). In my laptop with only CPU, it is much more slow, I stopped the training berfore 10 epochs. I think the training will take around (or more than) 30min for the whole dataset.
from piwise.
Can I directly use nn.CrossEntropyLoss() for binary segmentation? Need I set num_class=1 ? And I want use weighed loss. @andrewssobral @duylp @saeedizadi @bodokaiser
from piwise.
You would suggest to use Sigmoid() + BinaryCrossEntropy for Binary Segmentation.
from piwise.
@saeedizadi I don't understand how to set the parameter weight
for :
class torch.nn.BCELoss(weight=None, size_average=None, reduce=None, reduction='elementwise_mean')
from piwise.
@woaichipinngguo You should see the definitions for the parameters. But, for the initial try, just try to use the default values, and see the results, then, you can customise them toward your taste
from piwise.
Hi @woaichipinngguo , you can find here an example of training binary segmentation on pytorch here:
https://github.com/andrewssobral/deep-learning-pytorch/blob/master/segmentation/train_binseg.py
this code was based on bodokaiser/piwise repository. However, in the code I don't make use of weights, and some improvements (e.g. model selection, prediction, etc) are needed, I still working to improve it.
from piwise.
@woaichipinngguo You may have a label index overpassing the limit. Cross-entropy needs at least 2 classes.
from piwise.
Related Issues (20)
- Semantic segmentation for binary masks (2 class: background/foreground object) HOT 9
- SyntaxError: invalid syntax in main.py HOT 2
- Object detection HOT 9
- Syntax Error in main.py HOT 2
- No model named segnet2? HOT 4
- Evaluation error HOT 4
- Out of Memory Issue HOT 2
- No folder named "Labels", Tuple Index out of range, size mismatch. HOT 6
- Is there some question in transform.py? HOT 4
- The result of the semantic segmentation HOT 1
- A question about the size of output imgae HOT 1
- This question is about how to eliminate the white box in the image HOT 1
- Some questions about dataset HOT 4
- About an inexplicable bug HOT 1
- It's different with the standard SegNet HOT 9
- Does the relization of the Segnet in network.py match the paper of segnet? HOT 2
- 用自己的数据集后得到的预测结果全红 HOT 1
- Softmax in the evaluation stage HOT 1
- Blank output maps! HOT 9
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 piwise.