I am trying to implement a neural net in PyTorch but it doesn’t seem to work. The problem seems to be in the training loop. I’ve spend several hours into this but can’t get it right. Please help, thanks.
I haven’t added the data preprocessing parts.
# importing libraries import pandas as pd import numpy as np import torch import torch.nn as nn from torch.utils.data import Dataset from torch.utils.data import DataLoader import torch.nn.functional as F
# get x function (dataset related stuff) def Getx(idx): sample = samples[idx] vector = Calculating_bottom(sample) vector = torch.as_tensor(vector, dtype = torch.float64) return vector # get y function (dataset related stuff) def Gety(idx): y = np.array(train.iloc[idx, 4], dtype = np.float64) y = torch.as_tensor(y, dtype = torch.float64) return y
# dataset class mydataset(Dataset): def __init__(self): super().__init__() def __getitem__(self, index): x = Getx(index) y = Gety(index) return x, y def __len__(self): return len(train) dataset = mydataset()
# sample dataset value print(dataset.__getitem__(0))
(tensor([ 5., 5., 8., 14.], dtype=torch.float64), tensor(-0.3403, dtype=torch.float64))
# data-loader dataloader = DataLoader(dataset, batch_size = 1, shuffle = True)
# nn architecture class Net(nn.Module): def __init__(self): super().__init__() self.fc1 = nn.Linear(4, 4) self.fc2 = nn.Linear(4, 2) self.fc3 = nn.Linear(2, 1) def forward(self, x): x = x.float() x = F.relu(self.fc1(x)) x = F.relu(self.fc2(x)) x = self.fc3(x) return x model = Net()
# device device = torch.device('cuda') if torch.cuda.is_available() else torch.device('cpu') model.to(device)
# hyper-parameters criterion = nn.MSELoss() optimizer = torch.optim.SGD(model.parameters(), lr=0.001)
# training loop for epoch in range(5): for batch in dataloader: # unpacking x, y = batch x.to(device) y.to(device) # reset gradients optimizer.zero_grad() # forward propagation through the network out = model(x) # calculate the loss loss = criterion(out, y) # backpropagation loss.backward() # update the parameters optimizer.step()
Error:
/opt/conda/lib/python3.7/site-packages/torch/nn/modules/loss.py:446: UserWarning: Using a target size (torch.Size([1])) that is different to the input size (torch.Size([1, 1])). This will likely lead to incorrect results due to broadcasting. Please ensure they have the same size. return F.mse_loss(input, target, reduction=self.reduction) --------------------------------------------------------------------------- RuntimeError Traceback (most recent call last) <ipython-input-18-3f68fcee9ff3> in <module> 20 21 # backpropagation ---> 22 loss.backward() 23 24 # update the parameters /opt/conda/lib/python3.7/site-packages/torch/tensor.py in backward(self, gradient, retain_graph, create_graph) 219 retain_graph=retain_graph, 220 create_graph=create_graph) --> 221 torch.autograd.backward(self, gradient, retain_graph, create_graph) 222 223 def register_hook(self, hook): /opt/conda/lib/python3.7/site-packages/torch/autograd/__init__.py in backward(tensors, grad_tensors, retain_graph, create_graph, grad_variables) 130 Variable._execution_engine.run_backward( 131 tensors, grad_tensors_, retain_graph, create_graph, --> 132 allow_unreachable=True) # allow_unreachable flag 133 134 RuntimeError: Found dtype Double but expected Float
Advertisement
Answer
You need the data type of the data to match the data type of the model.
Either convert the model to double (recommended for simple nets with no serious performance problems such as yours)
# nn architecture class Net(nn.Module): def __init__(self): super().__init__() self.fc1 = nn.Linear(4, 4) self.fc2 = nn.Linear(4, 2) self.fc3 = nn.Linear(2, 1) self.double()
or convert the data to float.
class mydataset(Dataset): def __init__(self): super().__init__() def __getitem__(self, index): x = Getx(index) y = Gety(index) return x.float(), y.float()