leonardoaraujosantos / changenet Goto Github PK

References

• Pytorch Issue Message
• Pytorch Discussion
• Pytorch Discussion 2

hi, nice work, but where can i download the dataset

Hello @leonardoaraujosantos !

We found some interest in your GitHub repository "ChangeNet", but we think something is missing there. We couldn't find the directory "ChangeDataset" and the files "train.txt" and "val.txt" (or any code that creates them).

We would like to get your help with this issue.

By the way, if you already have the trained model and are willing to share it with us, we will be thankful!

Hello, I think your work is quite amazing and I'm very interested in your job, but when I tested your code on VL_CMU_CD, I got a bad result. Could you please share your file lists of this dataset? Thanks a lot!

Use AX Library

References

• https://ax.dev/docs/bayesopt

Hi @leonardoaraujosantos , seems like you did a great work.
I would like to ask if you can share the model (best_model.pkl), so I'll be able to run it.
Thanks.

I have downloaded the VL-CMU-CD dataset, however, the dataset folder contains all bi-temporal .png images and GTs. Then,
how to generate the 'change_dataset_train.pkl' and 'change_dataset_train.pkl' using the downloaded VL-CMU-CD dataset? thus I can run the Train.py in this project.

I want to train chang net with 3 classes, so i set num_classes to 4 (value of 4 class is 0, 1, 2, 3) and fix:

line 38 - utils_train.py to labels = sample['label'].squeeze(0).type(torch.LongTensor).to(device)
but it raise error:

RuntimeErrorTraceback (most recent call last)
in
1 num_epochs = 5
2 best_model, _ = utils_train.train_model(change_net, dataloaders_dict,
----> 3 criterion, optimizer, sc_plt, writer, device, num_epochs=num_epochs)
4 torch.save(best_model.state_dict(), 'best_model.pkl')

~/AFS/changenet/utils_train.py in train_model(model, dataloaders, criterion, optimizer, sc_plt, writer, device, num_epochs)
63 # backward + optimize only if in training phase
64 if phase == 'train':
---> 65 loss.backward()
66 optimizer.step()
67

/usr/local/lib/python3.6/dist-packages/torch/tensor.py in backward(self, gradient, retain_graph, create_graph)
105 products. Defaults to False.
106 """
--> 107 torch.autograd.backward(self, gradient, retain_graph, create_graph)
108
109 def register_hook(self, hook):

/usr/local/lib/python3.6/dist-packages/torch/autograd/init.py in backward(tensors, grad_tensors, retain_graph, create_graph, grad_variables)
91 Variable._execution_engine.run_backward(
92 tensors, grad_tensors, retain_graph, create_graph,
---> 93 allow_unreachable=True) # allow_unreachable flag
94
95

RuntimeError: cuDNN error: CUDNN_STATUS_ALLOC_FAILED

Please help me to train with 3 classes. Thanks!

I can't understand about this part of the article. Would you please tell me the 'force the network to work in constrained space' means?

Hi, @leonardoaraujosantos

I have tried running your code and stuck into the issue with RunTimeError:

Epoch 0/49

Traceback (most recent call last):
File "train_changenet.py", line 90, in
best_model, _ = utils_train.train_model(change_net, dataloaders_dict, criterion, optimizer, sc_plt, None, device, num_epochs=num_epochs)
File "/home/files/ChangeNet/utils_train.py", line 34, in train_model
for sample in dataloaders[phase]:
File "/opt/conda/lib/python3.6/site-packages/torch/utils/data/dataloader.py", line 345, in next
data = self._next_data()
File "/opt/conda/lib/python3.6/site-packages/torch/utils/data/dataloader.py", line 856, in _next_data
return self._process_data(data)
File "/opt/conda/lib/python3.6/site-packages/torch/utils/data/dataloader.py", line 881, in _process_data
data.reraise()
File "/opt/conda/lib/python3.6/site-packages/torch/_utils.py", line 395, in reraise
raise self.exc_type(msg)
RuntimeError: Caught RuntimeError in DataLoader worker process 0.
Original Traceback (most recent call last):
File "/opt/conda/lib/python3.6/site-packages/torch/utils/data/_utils/worker.py", line 178, in _worker_loop
data = fetcher.fetch(index)
File "/opt/conda/lib/python3.6/site-packages/torch/utils/data/_utils/fetch.py", line 47, in fetch
return self.collate_fn(data)
File "/opt/conda/lib/python3.6/site-packages/torch/utils/data/_utils/collate.py", line 74, in default_collate
return {key: default_collate([d[key] for d in batch]) for key in elem}
File "/opt/conda/lib/python3.6/site-packages/torch/utils/data/_utils/collate.py", line 74, in
return {key: default_collate([d[key] for d in batch]) for key in elem}
File "/opt/conda/lib/python3.6/site-packages/torch/utils/data/_utils/collate.py", line 55, in default_collate
return torch.stack(batch, 0, out=out)
RuntimeError: stack expects each tensor to be equal size, but got [3, 224, 224] at entry 0 and [4, 224, 224] at entry 9

It seems that then generating the dataset, there is a problem with the tensor dimension.
Did you have this issue?

Hi.
From where can I download the data?
Also, can you upload a sample of the file you used as the input?