TypeError: new(): argument 'size' must be tuple of ints, but found element of type NoneType at pos 2 when using pytorch, using nn.linear

Question

File "C:\Users\J2\Desktop\Pytorchseries\thenn.py", line 50, in net = Net() TypeError: new(): argument 'size' must be tuple of ints, but found element of type NoneType at pos 2

If it helps I was following the sentdex pytorch tutorial. Any help would be appreciated. I am new to machine learning, and I was hoping that this would work. Please help me out!

import numpy as np
import torch
import torch.nn as nn
import torch.nn.functional as F
import matplotlib.pyplot as plt
import tqdm

training_data = np.load('training_data.npy', allow_pickle=True)
print(len(training_data))

X = torch.Tensor([i[0] for i in training_data]).view(-1,50,50)
X = X/255.0
y = torch.Tensor([i[1] for i in training_data])

plt.imshow(X[0], cmap='gray')
print(y[0])

class Net(nn.Module):
    def __init__(self):
        super().__init__() # just run the init of parent class (nn.Module)
        self.conv1 = nn.Conv2d(1, 32, 5) # input is 1 image, 32 output channels, 5x5 kernel / window
        self.conv2 = nn.Conv2d(32, 64, 5) # input is 32, bc the first layer output 32. Then we say the output will be 64 channels, 5x5 kernel / window
        self.conv3 = nn.Conv2d(64, 128, 5)

        x = torch.randn(50,50).view(-1,1,50,50)
        self._to_linear = None
        self.convs(x)

        self.fc1 = nn.Linear(self._to_linear, 512) #flattening.
        self.fc2 = nn.Linear(512, 2) # 512 in, 2 out bc we're doing 2 classes (dog vs cat).
        

    def convs(self, x):
        # max pooling over 2x2
        x = F.max_pool2d(F.relu(self.conv1(x)), (2, 2))
        x = F.max_pool2d(F.relu(self.conv2(x)), (2, 2))
        x = F.max_pool2d(F.relu(self.conv3(x)), (2, 2))

    def forward(self, x):
        x = self.convs(x)
        x = x.view(-1, self._to_linear)  # .view is reshape ... this flattens X before 
        x = F.relu(self.fc1(x))
        x = self.fc2(x) # bc this is our output layer. No activation here.
        return F.softmax(x, dim=1)

        if self._to_linear is None:
            self._to_linear = x[0].shape[0]*x[0].shape[1]*x[0].shape[2]
        return x

net = Net()
print(net)

import torch.optim as optim

optimizer = optim.Adam(net.parameters(), lr=0.001)
loss_function = nn.MSELoss()

X = torch.Tensor([i[0] for i in training_data]).view(-1,50,50)
X = X/255.0
y = torch.Tensor([i[1] for i in training_data])

VAL_PCT = 0.1  # lets reserve 10% of our data for validation
val_size = int(len(X)*VAL_PCT)
print(val_size)

train_X = X[:-val_size]
train_y = y[:-val_size]

test_X = X[-val_size:]
test_y = y[-val_size:]

print(len(train_X), len(test_X))

BATCH_SIZE = 100
EPOCHS = 1

for epoch in range(EPOCHS):
    for i in tqdm(range(0, len(train_X), BATCH_SIZE)): # from 0, to the len of x, stepping BATCH_SIZE at a time. [:50] ..for now just to dev
        #print(f"{i}:{i+BATCH_SIZE}")
        batch_X = train_X[i:i+BATCH_SIZE].view(-1, 1, 50, 50)
        batch_y = train_y[i:i+BATCH_SIZE]

        net.zero_grad()

        outputs = net(batch_X)
        loss = loss_function(outputs, batch_y)
        loss.backward()
        optimizer.step()    # Does the update

    print(f"Epoch: {epoch}. Loss: {loss}")

correct = 0
total = 0
with torch.no_grad():
    for i in tqdm(range(len(test_X))):
        real_class = torch.argmax(test_y[i])
        net_out = net(test_X[i].view(-1, 1, 50, 50))[0]  # returns a list, 
        predicted_class = torch.argmax(net_out)

        if predicted_class == real_class:
            correct += 1
        total += 1
print("Accuracy: ", round(correct/total, 3))

Answer 1

The issue is with self._to_linear. You use it in __init__ as:

self._to_linear = None    

self.convs(x)
self.fc1 = nn.Linear(self._to_linear, 512) #flattening.

The call to nn.Linear has it as a parameter. This parameter should equal the number of input features in the linear layer, and cannot be None, since the value will determine the shape of the layer (number of weights and biases). How to fix this depends on what you're trying to achieve.