I am trying to create a text classifier as the one found here:
https://pytorch.org/tutorials/beginner/text_sentiment_ngrams_tutorial.html
When I run the code I encounter the following:
line 3014, in cross_entropy
return torch._C._nn.cross_entropy_loss(input, target, weight, _Reduction.get_enum(reduction), ignore_index, label_smoothing)
IndexError: Target -1 is out of bounds.
I have made sure that the number of outputs match across training, valid and test sets. The code is as follows:
import torch
import pandas as pd
import sklearn
from sklearn.model_selection import train_test_split
df = pd.read_csv("cleaned_train.csv", sep="|")
df_test = pd.read_csv("cleaned_test3.csv", sep="|")
# Splitting training set into train set and test set
target_train, input_valid, y_train, input_valid = train_test_split(df['label'].tolist(),
df['content'].tolist(),
test_size=0.2,
random_state=42)
# making the data fit to the pipeline
train_iter = list(zip(target_train, y_train))
valid_dat = list(zip(input_valid, input_valid))
test_dat = list(zip(df_test['label'].tolist(), df_test['content'].tolist()))
from torchtext.data.utils import get_tokenizer
from torchtext.vocab import build_vocab_from_iterator
tokenizer = get_tokenizer('basic_english')
def yield_tokens(data_iter):
for _, text in data_iter:
yield tokenizer(text)
vocab = build_vocab_from_iterator(yield_tokens(train_iter), specials=["<unk>"])
vocab.set_default_index(vocab["<unk>"])
text_pipeline = lambda x: vocab(tokenizer(x))
label_pipeline = lambda x: int(x) - 1
from torch.utils.data import DataLoader
device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
def collate_batch(batch):
label_list, text_list, offsets = [], [], [0]
for (_label, _text) in batch:
label_list.append(label_pipeline(_label))
processed_text = torch.tensor(text_pipeline(_text), dtype=torch.int64)
text_list.append(processed_text)
offsets.append(processed_text.size(0))
label_list = torch.tensor(label_list, dtype=torch.int64)
offsets = torch.tensor(offsets[:-1]).cumsum(dim=0)
text_list = torch.cat(text_list)
return label_list.to(device), text_list.to(device), offsets.to(device)
train_iter = list(zip(target_train, y_train))
dataloader = DataLoader(train_iter, batch_size=8, shuffle=False, collate_fn=collate_batch)
from torch import nn
import torch.nn.functional as F
class TextClassificationModel(nn.Module):
def __init__(self, vocab_size, embed_dim, num_class):
super(TextClassificationModel, self).__init__()
self.embedding = nn.EmbeddingBag(vocab_size, embed_dim, sparse=True)
self.fc1 = nn.Linear(embed_dim, 256)
self.fc2 = nn.Linear(256, 128)
self.fc3 = nn.Linear(128, num_class)
self.init_weights()
def init_weights(self):
initrange = 0.5
self.embedding.weight.data.uniform_(-initrange, initrange)
self.fc1.weight.data.uniform_(-initrange, initrange)
self.fc1.bias.data.zero_()
self.fc2.weight.data.uniform_(-initrange, initrange)
self.fc2.bias.data.zero_()
self.fc3.weight.data.uniform_(-initrange, initrange)
self.fc3.bias.data.zero_()
def forward(self, text, offsets):
embedded = self.embedding(text, offsets)
x = F.relu(self.fc1(embedded))
x = F.relu(self.fc2(x))
x = self.fc3(x)
return x
train_iter = list(zip(target_train, y_train))
num_class = len(set([label for (label, text) in train_iter]))
vocab_size = len(vocab)
emsize = 128
model = TextClassificationModel(vocab_size, emsize, num_class).to(device)
import time
def train(dataloader):
model.train()
total_acc, total_count = 0, 0
log_interval = 500
start_time = time.time()
for idx, (label, text, offsets) in enumerate(dataloader):
optimizer.zero_grad()
predicted_label = model(text, offsets)
loss = criterion(predicted_label, label)
loss.backward()
torch.nn.utils.clip_grad_norm_(model.parameters(), 0.1)
optimizer.step()
total_acc += (predicted_label.argmax(1) == label).sum().item()
total_count += label.size(0)
if idx % log_interval == 0 and idx > 0:
elapsed = time.time() - start_time
print('| epoch {:3d} | {:5d}/{:5d} batches '
'| accuracy {:8.3f}'.format(epoch, idx, len(dataloader),
total_acc/total_count))
total_acc, total_count = 0, 0
start_time = time.time()
def evaluate(dataloader):
model.eval()
total_acc, total_count = 0, 0
with torch.no_grad():
for idx, (label, text, offsets) in enumerate(dataloader):
predicted_label = model(text, offsets)
loss = criterion(predicted_label, label)
total_acc += (predicted_label.argmax(1) == label).sum().item()
total_count += label.size(0)
return total_acc/total_count
from torch.utils.data.dataset import random_split
from torchtext.data.functional import to_map_style_dataset
# Hyperparameters
EPOCHS = 15
LR = 0.1 # learning rate
BATCH_SIZE = 16 # batch size for training
criterion = torch.nn.CrossEntropyLoss()
optimizer = torch.optim.SGD(model.parameters(), lr=LR)
scheduler = torch.optim.lr_scheduler.StepLR(optimizer, 1.0, gamma=0.1)
total_accu = None
train_iter2 = train_iter
test_iter = test_dat
valid_iter = valid_dat
train_dataloader = DataLoader(train_iter2, batch_size=BATCH_SIZE,
shuffle=True, collate_fn=collate_batch)
valid_dataloader = DataLoader(valid_iter, batch_size=BATCH_SIZE,
shuffle=True, collate_fn=collate_batch)
test_dataloader = DataLoader(test_iter, batch_size=BATCH_SIZE,
shuffle=True, collate_fn=collate_batch)
for epoch in range(1, EPOCHS + 1):
epoch_start_time = time.time()
train(train_dataloader)
accu_val = evaluate(valid_dataloader)
if total_accu is not None and total_accu > accu_val:
scheduler.step()
else:
total_accu = accu_val
print('-' * 59)
print('| end of epoch {:3d} | time: {:5.2f}s | '
'valid accuracy {:8.3f} '.format(epoch,
time.time() - epoch_start_time,
accu_val))
print('-' * 59)