pytorch-semantic-segmentation
pytorch-semantic-segmentation copied to clipboard
zijundeng
PyTorch for Semantic Segmentation
Hello, author!About the SEGNET's upper sampling method has a little confusion, why use the transposition convolution, which does not record the index of the pooling? Hope receive your reply！
Hello, author!About the SEGNET's upper sampling method has a little confusion, why use the transposition convolution, which does not record the index of the pooling? Hope receive your reply！
hello author, i installed tensorboardX, but your code imports summary writer from tensorboard, gives error. how can i solve this. if i use from tensorboard import SummaryWriter ImportError: cannot import...
When I try to run the train.py, it reports an error like this: - Can't pickle local object 'main..' is there anyone know why? And how can I reslove it?
Thanks for awesome code!How could I predict photos in a dir not to type all photos name I want to predict
I training FCN32 with the my onw datatset. However, i realized that the loss is empty and lead to the error above. The detailed error: C:/cb/pytorch_1000000000000/work/aten/src/THCUNN/SpatialClassNLLCriterion.cu:106: block: [3,0,0], thread: [293,0,0]...
I found some strange settings: `score_pool4 = self.score_pool4(0.01 * pool4)` `score_pool3 = self.score_pool3(0.0001 * pool3)` but in my experiments, the model without 0.01 and 0.0001 performs better than the original...
In the fcn32, the output has been cropped. Why are we ignoring the first 19 pixels? Is there any reason for this cropping scheme?
