Target size (torch.Size([32, 9])) must be the same as input size (torch.Size([32, 10]))-CodePudding

I have 10 classes. I have a model such as;

from brevitas.nn import QuantLinear, QuantReLU
import torch.nn as nn

# Setting seeds for reproducibility
torch.manual_seed(0)

model = nn.Sequential(
      QuantLinear(input_size, hidden1, bias=True, weight_bit_width=weight_bit_width),
      nn.BatchNorm1d(hidden1),
      nn.Dropout(0.5),
      QuantReLU(bit_width=act_bit_width),
      QuantLinear(hidden1, hidden2, bias=True, weight_bit_width=weight_bit_width),
      nn.BatchNorm1d(hidden2),
      nn.Dropout(0.5),
      QuantReLU(bit_width=act_bit_width),
      QuantLinear(hidden2, hidden3, bias=True, weight_bit_width=weight_bit_width),
      nn.BatchNorm1d(hidden3),
      nn.Dropout(0.5),
      QuantReLU(bit_width=act_bit_width),
      QuantLinear(hidden3, num_classes, bias=True, weight_bit_width=weight_bit_width)
)

model.to(device)

and I have defined my training phase as:

def train(model, train_loader, optimizer, criterion):
    losses = []
    # ensure model is in training mode
    model.train()    
    
    for i, data in enumerate(train_loader, 0):        
        inputs, target = data['pointcloud'].to(device).float(), data['category'].to(device)
        target = torch.nn.functional.one_hot(target)
        optimizer.zero_grad()   
                
        # forward pass
        output = model(inputs)
        loss = criterion(output, target.float())
        
        # backward pass   run optimizer to update weights
        loss.backward()
        optimizer.step()
        
        # keep track of loss value
        losses.append(loss.data.cpu().numpy()) 
           
    return losses

As I run the training code:

import numpy as np
from sklearn.metrics import accuracy_score
from tqdm import tqdm, trange

# Setting seeds for reproducibility
torch.manual_seed(0)
np.random.seed(0)

running_loss = []
running_test_acc = []
t = trange(num_epochs, desc="Training loss", leave=True)

for epoch in t:
        loss_epoch = train(model, train_loader, optimizer,criterion)
        test_acc = test(model, valid_loader)
        t.set_description("Training loss = %f test accuracy = %f" % (np.mean(loss_epoch), test_acc))
        t.refresh() # to show immediately the update           
        running_loss.append(loss_epoch)
        running_test_acc.append(test_acc)

I get an error as:

Target size (torch.Size([32, 9])) must be the same as input size (torch.Size([32, 10]))

Please help me about what can be possibly the solution. I have added one hot encoding because I have seen some solutions like that before.

CodePudding user response：

The code error is pretty straightforward - the criterion (that you didn't show here in the code) expects both the input and the target arguments to be the same size, but they're not.

The problem is that you're using torch.nn.functional.one_hot(target) without telling it how many classes you need for one-hot encoding; it is then infered as the largest values in target 1 (see: https://pytorch.org/docs/stable/generated/torch.nn.functional.one_hot.html). You should change it to torch.nn.functional.one_hot(target, num_classes=10)