Hi, when I use your code by your README, I find that the model training is fintuning on your well-trained model. When I choose not to fintuning , and want to retrain the data VOC2012. Some wrongs with the loss. The losses don't converge. I want to konw if anything wrong with your code? emmm, I with you to test your code. Thanks.

It is not a bug. I just want to ask this question to make more clearly understand. Your discriminator network produces a spatial map by using fully convolution layer.

1. Does the spatial map same as the confident map? Or confident map generates by unlabeled data?
2. Does the value of the spatial map (from D network) in range 0 to 1 or just {0,1}?

When I run the evaluation code, I get a mean IoU of 47% as against 68.8% as mentioned. This was done using pretrained model using 1/8 training data. Is there something that I have done wrong or some changes that have to be made to the code before running evaluation? The dataset was VOC2012.

Hi! First, I'd like to thank you for the very helpful repo. During training with the same discriminator as yours, I have met some problems which I can't figure out. 1. The discriminator loss of pred and GT are almost unchanged for most of the time. So I am wondering if this phenomenon is normal. Btw, I haven't added semi data yet.

Hello, I want to ask one question related to the loss_adv_p and loss_D. As the log, the loss_adv_p tends to increase while the loss_D tends to decrease. We expect that loss_D will decrease, it is correct; however, how about the loss_adv_p? I found one interesting thing that is args.lambda_adv_pred, you can set it to 0.5, then the loss_adv_p will decrease but the loss loss_D will increase. They looks opposite side Thanks

iter =        0/   20000, loss_seg = 3.045, loss_adv_p = 0.695, loss_D = 0.693, loss_semi = 0.000

and at 180 iters

iter =      180/   20000, loss_seg = 0.490, loss_adv_p = 1.358, loss_D = 0.572, loss_semi = 0.000

Hello, I am planning to use your data to run your network but it fails. My data is in two categories. One is for the background and the other is set to 0 and 1, respectively. For the single channel label map, use your The network has been trained, but the test result output is all 0. May I ask if I need to adjust some parameters, thank you

Hey , When I try to validate the results , I am getting this error

  output = model(Variable(image, volatile=True).cuda(gpu0))
Traceback (most recent call last):
  File "evaluate_voc.py", line 235, in <module>
    main()
  File "evaluate_voc.py", line 214, in main
    output = model(Variable(image, volatile=True).cuda(gpu0))
  File "/home/ubuntu/.local/lib/python2.7/site-packages/torch/nn/modules/module.py", line 491, in __call__
    result = self.forward(*input, **kwargs)
  File "/home/ubuntu/summer_interns/jose/AdvSemiSeg/model/deeplab.py", line 167, in forward
    x = self.conv1(x)
  File "/home/ubuntu/.local/lib/python2.7/site-packages/torch/nn/modules/module.py", line 491, in __call__
    result = self.forward(*input, **kwargs)
  File "/home/ubuntu/.local/lib/python2.7/site-packages/torch/nn/modules/conv.py", line 301, in forward
    self.padding, self.dilation, self.groups)
RuntimeError: CUDNN_STATUS_MAPPING_ERROR

Thanks for sharing your work. I used evaluate code and I got the error

    import copy_reg
ModuleNotFoundError: No module named 'copy_reg'

I am using python 3.6 from conda install, Ubuntu 16.04. How can I fix it? Thanks

raise RuntimeError('Attempting to deserialize object on a CUDA ' RuntimeError: Attempting to deserialize object on a CUDA device but torch.cuda.is_available() is False. If you are running on a CPU-only machine, please use torch.load with map_location=torch.device('cpu') to map your storages to the CPU.

How can i run it on cpu.Hlep me,please.Thank you!

Hello, first of all, thank you for sharing your work. I have a question in the process of looking at the code.ignore_mask = (y.numpy() == 255) Can you explain this to me? If my label y has a value of 0-9, can it be written like this? I look forward to your reply. Thank you very much.

Excuse me, There are one more questions...hope it not bothing you too much... "The output of D is a probability map with values ranges from 0-1. When the input is unlabeled data, we use the D output map as the indicator for semi-supervised learning."

D_out = interp(model_D(F.softmax(pred))) D_out_sigmoid = F.sigmoid(D_out).data.cpu().numpy().squeeze(axis=1) ##following is used to draw the confindence map in your papar Figure3 for i in range(args.batch_size): plt.imshow(D_out_sigmoid[i], cmap='jet') plt.show() Can I interpret the D_out_sigmoid is the confidence map you mentioned? I use VOC_20000.pth and VOC_20000_D.pth(when use these two model the evaluatation mIOU is 0.709) as the parameters for RESTORE_FROM and RESTORE_FROM_D,and tried to get the figure of confidence map,but it looks not matching so well,it looks weird ,can you explain how you get the confidence map in your paper?

Hi, sir. I have a quenstion about loss semi. In training process, my loss_semi is initialy about 0.4 but after long training it significantly decreases. Now in range [0.000 0.006]. Is everything ok or I compile wrong ?

Hello everyone, Recently, I have managed to run the code correctly on Pascal VOC dataset, but when I tried to run the code on my own custom dataset or CityScape dataset, I am unable to run and faced debugging issues. Since I am working on python3.6, I made the following changes in the source code:

• substitute Enumerate.next() by Enumerate.next()
• substitute xrange by range

Also, I change the tensor type from gpu to cpu, e.g. images = Variable(images).cuda(args.gpu) to images = Variable(images).cpu(). As I searched on the internet, I noticed there might be some issue with the number of class. But then I guessed that I have correctly chosen the number of classes, as 30 classes in cityscapes case; or I changed the number of class to 31, but even then facing the same error. BTW, I'm running the code on GoogleColab, and it worked successfully for Pascal VOC dataset. The Error report is as below,

/usr/local/lib/python3.7/dist-packages/torch/optim/sgd.py:105: UserWarning: optimizer contains a parameter group with duplicate parameters; in future, this will cause an error; see github.com/pytorch/pytorch/issues/40967 for more information super(SGD, self).init(params, defaults) train.py:379: UserWarning: Implicit dimension choice for softmax has been deprecated. Change the call to include dim=X as an argument. D_out = interp(model_D(F.softmax(pred))) /usr/local/lib/python3.7/dist-packages/torch/nn/functional.py:1960: UserWarning: nn.functional.sigmoid is deprecated. Use torch.sigmoid instead. warnings.warn("nn.functional.sigmoid is deprecated. Use torch.sigmoid instead.") train.py:382: DeprecationWarning: np.bool is a deprecated alias for the builtin bool. To silence this warning, use bool by itself. Doing this will not modify any behavior and is safe. If you specifically wanted the numpy scalar type, use np.bool_ here. Deprecated in NumPy 1.20; for more details and guidance: https://numpy.org/devdocs/release/1.20.0-notes.html#deprecations ignore_mask_remain = np.zeros(D_out_sigmoid.shape).astype(np.bool) /usr/local/lib/python3.7/dist-packages/torch/nn/_reduction.py:42: UserWarning: size_average and reduce args will be deprecated, please use reduction='mean' instead. warnings.warn(warning.format(ret)) pred_train = 88 label_train = 88 Traceback (most recent call last): File "train.py", line 524, in main() File "train.py", line 435, in main loss_seg = loss_calc(pred, labels) File "train.py", line 178, in loss_calc return criterion(pred, label) File "/usr/local/lib/python3.7/dist-packages/torch/nn/modules/module.py", line 1130, in _call_impl return forward_call(*input, **kwargs) File "/content/drive/MyDrive/Tasweer_Research/Adversarial_Learning_Semi_supervised/AdvSemiSeg/utils/loss.py", line 49, in forward loss = F.cross_entropy(predict, target, weight=weight, size_average=self.size_average) File "/usr/local/lib/python3.7/dist-packages/torch/nn/functional.py", line 3014, in cross_entropy return torch._C._nn.cross_entropy_loss(input, target, weight, _Reduction.get_enum(reduction), ignore_index, label_smoothing) IndexError: Target 119 is out of bounds.

The DeepLab implementation seems to have a long-lasting unobserved issue in Classifier_Module: in line 116 the out variable is returned in the first iteration of the loop. So it only sums up the output of the first and second atrous convolutions in ASPP module (not all 4 of them). The source of this problem probably is a bug in the original implementation which was fixed later.

Unfortunately many other researchers have been used this implementation (or the original implementation before its bug being fixed). So whoever reads this issue better be cautious about the DeepLabv2 pytorch implementation used in other repositories too.

Thank you for sharing your implementation. I would like to fix the ASPP part. This change makes Classifier_Module to use all of the four dilated convolutions properly.

In speedinghzl/Pytorch-Deeplab, which this repository is based on, the ASPP code was fixed in the same way. https://github.com/speedinghzl/Pytorch-Deeplab/commit/cf1d48afe9c611c90f8cabba014697bb0aac5284#diff-246517e88085928a3e2b3e706e7ba4c7d7803f0e7d2e5fd59e5a414abe048cab

I am sorry if I may be mistaken.

why all my losses in experiment are NaN? I used the same code, parameters and dataset. like this "iter = 19998/20000, loss_seg = nan, loss_adv_p = nan, loss_D = nan, loss_semi = nan, loss_semi_adv = nan semi ratio: 1.0000"