CODEWITHSUNDEEP
pythoncsvneural-networkpycharmpytorch
christianri
christianri

Reputation: 45

Pytorch: [TypeError: __init__() takes 1 positional argument but 2 were given]

I searched StackOverflow and visited other websites for help, but I can´t find a solution to my problem. I will leave the whole code to make it understandable for you. It´s about 110 lines, written with PyTorch.

Each time, I will compile and calculate a prediction, this error-code will show up:

Traceback (most recent call last):
File "/Users/MacBookPro/Dropbox/01 GST h_da Privat/BA/06_KNN/PyTorchV1/BesucherV5.py", line 108, in <module>
result = Network(test_exp).data[0][0].item()
TypeError: __init__() takes 1 positional argument but 2 were given

I know, other users had this too, but none of their solutions helped me out. I guess the mistake is either in my class "Network" or in variable "result". I hope that someone of you had this problem and know how to fix it or can help me in a different way.

Short information about the Dataset:

My Dataset has 10 columns and gets splitted into two sets. X and Y. X has 9 columns, Y just one. These are then used to train the network.

Thank you in advance!

Kind regards Christian Richter

My Code:

import torch
import torch.nn as nn
import torch.nn.functional as F
from torch.autograd import Variable
import torch.optim as optim
import pandas as pd


### Dataset ###

dataset = pd.read_csv('./data/train_data_csv.csv')

x_temp = dataset.iloc[:, :-1].values

print(x_temp)
print()
print(x_temp.size)
print()

y_temp = dataset.iloc[:, 9:].values

print(y_temp)
print()
print(y_temp.size)
print()

x_train_tensor = torch.FloatTensor(x_temp)
y_train_tensor = torch.FloatTensor(y_temp)


### Network Architecture ###

class Network(nn.Module):
    def __init__(self):
        super(Network, self).__init__()
        self.linear1 = nn.Linear(9, 9)  #10 Input-Neurons, 10 Output-Neurons, Linearer Layer
        self.linear2 = nn.Linear(9, 1)


    def forward(self, x):
        pax_predict = F.relu(self.linear1(x))
        pax_predict = self.linear2(x)
        return pax_predict

    def num_flat_features(self, pax_predict):
        size = pax_predict.size()[1:]
        num = 1
        for i in size:
            num *= i
        return num


network = Network()
print(network)

criterion = nn.MSELoss()
target = Variable(y_train_tensor)
optimizer = torch.optim.SGD(network.parameters(), lr=0.0001)

### Training

for epoch in range(200):
    input = Variable(x_train_tensor)
    y_pred = network(input)

    loss = criterion(y_pred, target)

    optimizer.zero_grad()

    loss.backward()
    optimizer.step()

test_exp = torch.Tensor([[40116]])

result = Network(test_exp).data[0][0].item()

print('Result is: ', result)

Upvotes: 1

Views: 15999

Answers (2)

Erfan Khalaji
Erfan Khalaji

Reputation: 63

I was getting the same error, and then I realized that I missed parenthesis when passing ToTensor() transform.

Wrong:

trainData = ImageFolder('data/in/train/', transform=ToTensor)

Right:

trainData = ImageFolder('data/in/train/', transform=ToTensor())

In general, if a function name is used but then the prototype is not as expected, it is likely to face such errors.

Upvotes: 4

Berriel
Berriel

Reputation: 13601

The problem is quite simple and is in this line, I suppose:

result = Network(test_exp).data[0][0].item()

Here you should use network (the object) instead of Network (the class). As you defined, Network takes only 1 argument (i.e., self), but you are passing 2: self and test_exp.

Perhaps if you had chosen another name for your object (e.g., net), you'd have spotted this error more easily. Take that into consideration :)

And please, always post the full traceback.

Upvotes: 4

Related Questions