pytorch 1.0 error

[yr18]

Hello,

I have updated my pytorch to the latest 1.0 version but still use python 3.6
when I run the code I got the following tracebacks , I wonder if I can run the code with the latest pytorch 1.0? Thank you so much for your time and help!

Traceback (most recent call last):
File "C:\Users\Administrator\Desktop\pytorch-drl4vrp-master\trainer.py", line 390, in
train_vrp(args)
File "C:\Users\Administrator\Desktop\pytorch-drl4vrp-master\trainer.py", line 348, in train_vrp
train(actor, critic, **kwargs)
File "C:\Users\Administrator\Desktop\pytorch-drl4vrp-master\trainer.py", line 164, in train
tour_indices, tour_logp = actor(static, dynamic, x0)
File "C:\Users\Administrator\AppData\Local\Programs\Python\Python36\lib\site-packages\torch\nn\modules\module.py", line 489, in call
result = self.forward(*input, **kwargs)
File "C:\Users\Administrator\Desktop\pytorch-drl4vrp-master\model.py", line 192, in forward
dynamic_hidden = self.dynamic_encoder(dynamic)
File "C:\Users\Administrator\AppData\Local\Programs\Python\Python36\lib\site-packages\torch\nn\modules\module.py", line 489, in call
result = self.forward(*input, **kwargs)
File "C:\Users\Administrator\Desktop\pytorch-drl4vrp-master\model.py", line 17, in forward
output = self.conv(input)
File "C:\Users\Administrator\AppData\Local\Programs\Python\Python36\lib\site-packages\torch\nn\modules\module.py", line 489, in call
result = self.forward(*input, **kwargs)
File "C:\Users\Administrator\AppData\Local\Programs\Python\Python36\lib\site-packages\torch\nn\modules\conv.py", line 187, in forward
self.padding, self.dilation, self.groups)
RuntimeError: Expected object of scalar type Double but got scalar type Float for argument #2 'weight'

[nabilbenmerad]

So were you able to resolve this ? I'm getting a similar DataType error:

Traceback (most recent call last):
File "trainer.py", line 390, in
train_vrp(args)
File "trainer.py", line 348, in train_vrp
train(actor, critic, **kwargs)
File "trainer.py", line 164, in train
tour_indices, tour_logp = actor(static, dynamic, x0)
File "/home/nabimaru/.local/lib/python3.6/site-packages/torch/nn/modules/module.py", line 489, in call
result = self.forward(*input, **kwargs)
File "/home/nabimaru/Workspace/DCbrain/GraphRL/VRP/pytorch-drl4vrp-master/model.py", line 192, in forward
dynamic_hidden = self.dynamic_encoder(dynamic)
File "/home/nabimaru/.local/lib/python3.6/site-packages/torch/nn/modules/module.py", line 489, in call
result = self.forward(*input, **kwargs)
File "/home/nabimaru/Workspace/DCbrain/GraphRL/VRP/pytorch-drl4vrp-master/model.py", line 17, in forward
output = self.conv(input)
File "/home/nabimaru/.local/lib/python3.6/site-packages/torch/nn/modules/module.py", line 489, in call
result = self.forward(*input, **kwargs)
File "/home/nabimaru/.local/lib/python3.6/site-packages/torch/nn/modules/conv.py", line 187, in forward
self.padding, self.dilation, self.groups)
RuntimeError: Input type (torch.cuda.DoubleTensor) and weight type (torch.cuda.FloatTensor) should be the same

Thank you in advance.

[mveres01]

It should be enough to modify a small snippet in tasks/vrp.py

        # All states will have their own intrinsic demand in [1, max_demand),
        # then scaled by the maximum load. E.g. if load=10 and max_demand=30,
        # demands will be scaled to the range (0, 3)
        demands = torch.randint(1, max_demand + 1, dynamic_shape)
        demands = demands.type(torch.FloatTensor) / max_load

        demands[:, 0, 0] = 0  # depot starts with a demand of 0
        self.dynamic = torch.cat((loads, demands), dim=1)