semantic-segmentation-pytorch
semantic-segmentation-pytorch copied to clipboard
Preparation of the dataset
Hello, I decreased the number of classes to 11 and retaining the network on my dataset. But ended with the ERROR- "RuntimeError: cuDNN error: CUDNN_STATUS_NOT_INITIALIZED". I think this is because of the annotated images(coloured) that I created. Can you tell me the procedure to create my own dataset properly. I'm only retraining the last conv layers of the decoder network.
I'm getting this error for my dataset.
samples: 11
1 Epoch = 5000 iters
Traceback (most recent call last):
File "train.py", line 347, in
The annotated images format are grayscale .png files
Hi I tried training with 1 class. Converted the label images to .png files with 1 channel. the pixel values are 0 for background and 1 for class-of-interest. However training is not happening. The loss is just coming as 0 and accuracy as 100. The output of any trained model is showing completely segmented as 'class-of-interest'. Any suggestions on whats going wrong? Thank you.
Are there any other changes to be made other than in config file?
In our setup, label 0 is ignored during training. So if you have two classes, please set the labels as 1 and 2. @nanditam1
Hey I am unable to understand how to subset the classes as I cannot understand the accurate label to class association. I also want to only use a subset of classes.
As you can see in image, after using encoding function provided I am getting two different class numbers for the class of person. It is not corrosponding to colours and numbers given in https://docs.google.com/spreadsheets/d/1se8YEtb2detS7OuPE86fXGyD269pMycAWe2mtKUj2W8/edit?usp=sharing.
@hangzhaomit Hello, when i use custom dataset with 5 class,getting this error: RuntimeError: cuda runtime error (710) : device-side assert triggered at /pytorch/aten/src/THC/generic/THCTensorMath.cu:226 You mentioned earlier that you can change labes to fix bugs. i want chang the labes, which file can change labes?
In our setup, label 0 is ignored during training. So if you have two classes, please set the labels as 1 and 2. @nanditam1
Hello, where do I change the labels for training? The objectInfo150 and such txt filesare not being read during training. So, where exactly is the labels list?
Hi I tried training with 1 class. Converted the label images to .png files with 1 channel. the pixel values are 0 for background and 1 for class-of-interest. However training is not happening. The loss is just coming as 0 and accuracy as 100. The output of any trained model is showing completely segmented as 'class-of-interest'. Any suggestions on whats going wrong? Thank you.
Are there any other changes to be made other than in config file?
I change the num_class to 2 and the loss is normal, but the inference effect is pool