Classes Number maybe not reasonable
Closed this issue · 12 comments
Hello, Writers, Firstly thanks for your share.
I find that Cityscapes Datasets includes 34 classes, thus the segmentation code write for only 20 classes, do you transform the label values to 20 classes before training?
Please use Cityscapes code to convert the labels
ok...
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?
How long did you train? Make sure your labels are correct
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.
Is your dataset balanced?
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
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.
ok，thanks for your idea.
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?
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'))
that's right, thank you