We Keep Coding

PyTorch Custom LSTM architecture not learning

I am building a model to classify news (AG news dataset). The vocab size ~33k with custom embedding layer. I have run this for 20 epochs but the loss and accuracy (1.3 and 26% respec.) is almost constant even at the end of 20th epoch. Can someone please help me with this? Also, am I feeding the correct input to the fc layer? I am using CrossEntropyLoss as the loss function.
Here is my model class:
class NewsClassifier(nn.Module):
def __init__(self, vocab_weights = None, rnn_type = 'LSTM', vocab_size = len(vocab.vocab), n_classes = 4, embed_size = 300, rnn_units = 512, \
n_layers = 2, bi_dir = True, rnn_drop = 0.0, padding_index = vocab['<unk>']):
super().__init__()
self.rnn_units = rnn_units
self.n_classes = n_classes
self.rnn_type = rnn_type
if vocab_weights:
self.embedding = nn.Embedding.from_pretrained(torch.as_tensor(vocab_weights))
else:
self.embedding = nn.Embedding(vocab_size, embed_size, padding_idx = padding_index)
if rnn_type == 'LSTM':
self.rnn = nn.LSTM(embed_size, rnn_units, num_layers = n_layers, bidirectional = bi_dir, dropout = rnn_drop)
elif rnn_type == 'GRU':
self.rnn = nn.GRU(embed_size, rnn_units, num_layers = n_layers, bidirectional = bi_dir, dropout = rnn_drop)
else:
raise NotImplementError
self.fc = nn.Linear(2 * rnn_units if bi_dir else rnn_units, self.n_classes)
def forward(self, data, lens):
x_embed = self.embedding(data) # (padded_lens, batch_size, embed_dim)
x_packed = pack_padded_sequence(x_embed, lens.cpu(), enforce_sorted = False) #packing sequences and passing to RNN unit
if self.rnn_type == 'LSTM':
output_packed, (hidden,cell) = self.rnn(x_packed) #output is packed and cannot be fed to linear layers
else:
output_packed, hidden = self.rnn(x_packed) #For GRU there is only hidden state
#Though n number of layers are stacked the output is always 1
output_padded, _ = pad_packed_sequence(output_packed) #output is padded to be fed to linear layer (padded_lens, batch size, hidden_units)
#Picking only the last output --> equivalent to reutrn_sequences = False in Keras
out_reduced = torch.cat((output_padded[-1, :, : self.rnn_units], output_padded[-1, :, self.rnn_units :]), 1)
return self.fc(out_reduced)
model = NewsClassifier()
print(f'The total number of trainable parameters are : {sum(p.numel() for p in model.parameters() if p.requires_grad)}')
My training function is:
def train(model, iterator = trainDataloader, optimizer = optimizer, loss_fn = criterion):
e_loss = e_acc = i = 0
model.train()
for inputs, leng, labels in iterator:
inputs, leng, labels = inputs.to(device), leng.to(device), labels.to(device)
optimizer.zero_grad()
preds = model(inputs, leng).squeeze(1)
loss = loss_fn(preds, labels.long())
acc = accuracy(preds, labels)
loss.backward()
optimizer.step()
e_loss += loss.item()
e_acc += acc.item()
i += 1
return e_loss/i, e_acc/i
def predict(model, iterator = testDataloader, loss_fn = criterion):
e_loss = e_acc = i = 0
model.eval()
with torch.no_grad():
for inputs, leng, labels in iterator:
inputs, leng, labels = inputs.to(device), leng.to(device), labels.to(device)
preds = model(inputs, leng).squeeze(1)
loss = loss_fn(preds, labels.long())
acc = accuracy(preds, labels)
e_loss += loss.item()
e_acc += acc.item()
i += 1
return e_loss/i, e_acc/i
N_EPOCHS = 20
best_valid_loss = float('inf')
for epoch in range(N_EPOCHS):
start_time = time.time()
train_loss, train_acc = train(model)
valid_loss, valid_acc = predict(model)
end_time = time.time()
epoch_mins, epoch_secs = epoch_time(start_time, end_time)
if valid_loss < best_valid_loss:
best_valid_loss = valid_loss
torch.save(model.state_dict(), 'tut1-model.pt')
print(f'Epoch: {epoch+1:02} / {N_EPOCHS} | Epoch Time: {epoch_mins}m {epoch_secs}s')
print(f'\tTrain Loss: {train_loss:.3f} | Train Acc: {train_acc*100:.2f}%')
print(f'\t Val. Loss: {valid_loss:.3f} | Val. Acc: {valid_acc*100:.2f}%')

Bi directional LSTM Regularization how to increase accuracy

This is my model:
class BiLSTM(nn.Module):
def __init__(self):
super(BiLSTM, self).__init__()
self.hidden_size = 128
drp = 0.2
n_classes = len(le.classes_)
self.embedding = nn.Embedding(max_features, embed_size)
self.embedding.weight = nn.Parameter(torch.tensor(embedding_matrix, dtype=torch.float32))
self.embedding.weight.requires_grad = False
self.lstm = nn.LSTM(embed_size, self.hidden_size, bidirectional=True, batch_first=True)
self.linear = nn.Linear(self.hidden_size*4 , 128)
self.relu = nn.ReLU()
self.dropout = nn.Dropout(drp)
self.out = nn.Linear(128, n_classes)
def forward(self, x):
#rint(x.size())
h_embedding = self.embedding(x)
_embedding = torch.squeeze(torch.unsqueeze(h_embedding, 0))
h_lstm, _ = self.lstm(h_embedding)
avg_pool = torch.mean(h_lstm, 1)
max_pool, _ = torch.max(h_lstm, 1)
conc = torch.cat(( avg_pool, max_pool), 1)
conc = self.relu(self.linear(conc))
conc = self.dropout(conc)
out = self.out(conc)
return out
n_epochs = 87
model = BiLSTM()
loss_fn = nn.CrossEntropyLoss(reduction='mean',)
optimizer = torch.optim.Adam(filter(lambda p: p.requires_grad, model.parameters()), lr=0.002)
model.cuda()
# Load train and test in CUDA Memory
x_train = torch.tensor(train_X, dtype=torch.long).cuda()
y_train = torch.tensor(train_y, dtype=torch.long).cuda()
x_cv = torch.tensor(test_X, dtype=torch.long).cuda()
y_cv = torch.tensor(test_y, dtype=torch.long).cuda()
# Create Torch datasets
train = torch.utils.data.TensorDataset(x_train, y_train)
valid = torch.utils.data.TensorDataset(x_cv, y_cv)
# Create Data Loaders
train_loader = torch.utils.data.DataLoader(train, batch_size=batch_size, shuffle=True)
valid_loader = torch.utils.data.DataLoader(valid, batch_size=batch_size, shuffle=True)
train_loss = []
valid_loss = []
for epoch in range(n_epochs):
start_time = time.time()
# Set model to train configuration
model.train()
avg_loss = 0.
for i, (x_batch, y_batch) in enumerate(train_loader):
# Predict/Forward Pass
y_pred = model(x_batch)
# Compute loss
loss = loss_fn(y_pred, y_batch)
optimizer.zero_grad()
loss.backward()
optimizer.step()
avg_loss += loss.item() / len(train_loader)
#acc =n-avg_loss
# Set model to validation configuration
model.eval()
avg_val_loss = 0.
val_preds = np.zeros((len(x_cv),len(le.classes_)))
for i, (x_batch, y_batch) in enumerate(valid_loader):
y_pred = model(x_batch).detach()
avg_val_loss += loss_fn(y_pred, y_batch).item() / len(valid_loader)
#val_accuracy = n- avg_val_loss
# keep/store predictions
val_preds[i * batch_size:(i+1) * batch_size] =F.softmax(y_pred).cpu().numpy()
val_preds=val_preds*5000
# Check Accuracy
val_accuracy = sum(val_preds.argmax(axis=1)==test_y)/len(test_y)
train_loss.append(avg_loss)
valid_loss.append(avg_val_loss)
elapsed_time = time.time() - start_time
print('Epoch {}/{} \t Train_loss={:.4f} \t val_loss={:.4f} \t val_acc={:.4f} \t time={:.2f}s'.format(
epoch + 1, n_epochs , avg_loss, avg_val_loss, val_accuracy, elapsed_time))
This is the output I am receiving.I have used the BiLSTM model. I tried changing the loss techniques and dropout value but it didn't work. The issue is I guess the model is overfitting how can I increase the accuracy this is the output I am receiving.I have used the BiLSTM model. I tried changing the loss techniques and dropout value but it didn't work. The issue is I guess the model is overfitting how can I increase the accuracy
This is the output I am receiving.I have used the BiLSTM model. I tried changing the loss techniques and dropout value but it didn't work. The issue is I guess the model is overfitting how can I increase the accuracy, The size of the dataset is 3000
[1]: https://i.stack.imgur.com/NbK92.png [output looks like this][1]
[1]: https://i.stack.imgur.com/ll12J.png [Data Looks Like this][1]

The pytorch training model cannot be created successfully

I would like to do a neural network for regression analysis using optuna based on this site.
I would like to create a model with two 1D data as input and one 1D data as output in batch learning.
x is the training data and y is the teacher data.
class Model(nn.Module):
# コンストラクタ(インスタンス生成時の初期化)
def __init__(self,trial, mid_units1, mid_units2):
super(Model, self).__init__()
self.linear1 = nn.Linear(2, mid_units1)
self.bn1 = nn.BatchNorm1d(mid_units1)
self.linear2 = nn.Linear(mid_units1, mid_units2)
self.bn2 = nn.BatchNorm1d(mid_units2)
self.linear3 = nn.Linear(mid_units2, 1)
self.activation = trial_activation(trial)
def forward(self, x):
x = self.linear1(x)
x = self.bn1(x)
x = self.activation(x)
x = self.linear2(x)
device = "cuda" if torch.cuda.is_available() else "cpu"
EPOCH = 100
x = torch.from_numpy(a[0].astype(np.float32)).to(device)
y = torch.from_numpy(a[1].astype(np.float32)).to(device)
def train_epoch(model, optimizer, criterion):
model.train()
optimizer.zero_grad() # 勾配情報を0に初期化
y_pred = model(x) # 予測
loss = criterion(y_pred.reshape(y.shape), y) # 損失を計算(shapeを揃える)
loss.backward() # 勾配の計算
optimizer.step() # 勾配の更新
return loss.item()
def trial_activation(trial):
activation_names = ['ReLU','logsigmoid']
activation_name = trial.suggest_categorical('activation', activation_names)
if activation_name == activation_names[0]:
activation = F.relu
else:
activation = F.logsigmoid
return activation
def objective(trial):
device = 'cuda' if torch.cuda.is_available() else 'cpu'
# 中間層のユニット数の試行
mid_units1 = int(trial.suggest_discrete_uniform("mid_units1", 1024*2,1024*4, 64*2))
mid_units2 = int(trial.suggest_discrete_uniform("mid_units2", 1024, 1024*2, 64*2))
net = Model(trial, mid_units1, mid_units2).to(device)
criterion = nn.MSELoss()
# 最適化手法の試行
optimizer = trial_optimizer(trial, net)
train_loss = 0
for epoch in range(EPOCH):
train_loss = train_epoch(net, optimizer, criterion, device)
torch.save(net.state_dict(), str(trial.number) + "new1.pth")
return train_loss
strage_name = "a.sql"
study_name = 'a'
study = optuna.create_study(
study_name = study_name,
storage='sqlite:///' + strage_name,
load_if_exists=True,
direction='minimize')
TRIAL_SIZE = 100
study.optimize(objective, n_trials=TRIAL_SIZE)
error message
---> 28 loss = criterion(y_pred.reshape(y.shape), y) # 損失を計算(shapeを揃える)
29 loss.backward() # 勾配の計算
30 optimizer.step() # 勾配の更新
AttributeError: 'NoneType' object has no attribute 'reshape'
Because of the above error, I checked the value of y_pred and found it to be None.
model.train()
optimizer.zero_grad()
I am thinking that these two lines may be wrong, but I don't know how to solve this problem.

With PyTorch, when you call y_pred = model(x) that will call the forward function which is defined in the Model class.
So, y_pred will get the result of the forward function, in your case, it returns nothing, that's why you get a None value. You can change the forward function as below:
def forward(self, x):
x = self.linear1(x)
x = self.bn1(x)
x = self.activation(x)
x = self.linear2(x)
return x

Python: tqdm progress bar stuck at 0%

I have written the following code to train a bert model on my dataset, I have used from tqdm.notebook import tqdm this import for tqdm and have used it in the loops. But when I run the program the bar stays at 0% even after the entire code has run. How to fix this?
Code
Model
TRANSFORMERS = {
"bert-multi-cased": (BertModel, BertTokenizer, "bert-base-uncased"),
}
class Transformer(nn.Module):
def __init__(self, model, num_classes=1):
"""
Constructor
Arguments:
model {string} -- Transformer to build the model on. Expects "camembert-base".
num_classes {int} -- Number of classes (default: {1})
"""
super().__init__()
self.name = model
model_class, tokenizer_class, pretrained_weights = TRANSFORMERS[model]
bert_config = BertConfig.from_json_file(MODEL_PATHS[model] + 'bert_config.json')
bert_config.output_hidden_states = True
self.transformer = BertModel(bert_config)
self.nb_features = self.transformer.pooler.dense.out_features
self.pooler = nn.Sequential(
nn.Linear(self.nb_features, self.nb_features),
nn.Tanh(),
)
self.logit = nn.Linear(self.nb_features, num_classes)
def forward(self, tokens):
"""
Usual torch forward function
Arguments:
tokens {torch tensor} -- Sentence tokens
Returns:
torch tensor -- Class logits
"""
_, _, hidden_states = self.transformer(
tokens, attention_mask=(tokens > 0).long()
)
hidden_states = hidden_states[-1][:, 0] # Use the representation of the first token of the last layer
ft = self.pooler(hidden_states)
return self.logit(ft)
Training
def fit(model, train_dataset, val_dataset, epochs=1, batch_size=8, warmup_prop=0, lr=5e-4):
train_loader = DataLoader(train_dataset, batch_size=batch_size, shuffle=True)
val_loader = DataLoader(val_dataset, batch_size=batch_size, shuffle=False)
optimizer = AdamW(model.parameters(), lr=lr)
num_warmup_steps = int(warmup_prop * epochs * len(train_loader))
num_training_steps = epochs * len(train_loader)
scheduler = get_linear_schedule_with_warmup(optimizer, num_warmup_steps, num_training_steps)
loss_fct = nn.BCEWithLogitsLoss(reduction='mean').cuda()
for epoch in range(epochs):
model.train()
start_time = time.time()
optimizer.zero_grad()
avg_loss = 0
for step, (x, y_batch) in tqdm(enumerate(train_loader), total=len(train_loader)):
y_pred = model(x.to(device))
loss = loss_fct(y_pred.view(-1).float(), y_batch.float().to(device))
loss.backward()
avg_loss += loss.item() / len(train_loader)
xm.optimizer_step(optimizer, barrier=True)
#optimizer.step()
scheduler.step()
model.zero_grad()
optimizer.zero_grad()
model.eval()
preds = []
truths = []
avg_val_loss = 0.
with torch.no_grad():
for x, y_batch in tqdm(val_loader):
y_pred = model(x.to(device))
loss = loss_fct(y_pred.detach().view(-1).float(), y_batch.float().to(device))
avg_val_loss += loss.item() / len(val_loader)
probs = torch.sigmoid(y_pred).detach().cpu().numpy()
preds += list(probs.flatten())
truths += list(y_batch.numpy().flatten())
score = roc_auc_score(truths, preds)
dt = time.time() - start_time
lr = scheduler.get_last_lr()[0]
print(f'Epoch {epoch + 1}/{epochs} \t lr={lr:.1e} \t t={dt:.0f}s \t loss={avg_loss:.4f} \t val_loss={avg_val_loss:.4f} \t val_auc={score:.4f}')
model = Transformer("bert-multi-cased")
device = torch.device('cuda:2')
model = model.to(device)
epochs = 3
batch_size = 32
warmup_prop = 0.1
lr = 1e-4
train_dataset = JigsawDataset(df_train)
val_dataset = JigsawDataset(df_val)
test_dataset = JigsawDataset(df_test)
fit(model, train_dataset, val_dataset, epochs=epochs, batch_size=batch_size, warmup_prop=warmup_prop, lr=lr)
Output
0%| | 0/6986 [00:00<?, ?it/s]
How to fix this?

The import should be:
from tqdm import tqdm
The error is in the training function, correct this loop:
for x, y_batch in tqdm(val_loader, total = len(val_loader)):

Contrary to Ishan Dutta answer, tqdm.notebook.tqdm (and not tqdm.tqdm) is the correct function to use for both Jupyter Notebook and JupyterLab.
This problem can happen if you don't have ipywidgets installed or if you have installed ipywidgets before installing JupyterLab.
What fixed it for me was reinstalling ipywidgets:
pip3 uninstall ipywidgets --yes
pip3 install --upgrade ipywidgets

How to solve size mismatch error in pytorch?

I am trying to create a logistic model by using CIFAR10 data in PyTorch. After running the model for evaluation I run into an error :
RuntimeError: size mismatch, m1: [750 x 4096], m2: [1024 x 10] at C:\w\1\s\tmp_conda_3.7_100118\conda\conda-bld\pytorch_1579082551706\work\aten\src\TH/generic/THTensorMath.cpp:136
It seems like input_size is creating a problem, I dont know I am new to this. Please let me know what changes should I make in order to overcome this error.
These are the hyperparameters:
batch_size = 100
learning_rate = 0.001
# Other constants
input_size = 4*4*64
num_classes = 10
This is the cell that downloads and splits the dataset into train, validation and test.
transform = torchvision.transforms.Compose(
[torchvision.transforms.ToTensor(),
torchvision.transforms.Normalize((0.5,0.5,0.5), (0.5,0.5,0.5))])
testset = torchvision.datasets.CIFAR10(root='D:\PyTorch\cifar-10-python', train=False,download=False, transform=transform)
trainvalset = torchvision.datasets.CIFAR10(root='D:\PyTorch\cifar-10-python', train=True,download=False, transform=transform)
trainset, valset = torch.utils.data.random_split(trainvalset, [45000, 5000]) # 10% for validation
train_loader = torch.utils.data.DataLoader(trainset, batch_size=50, shuffle=True)
test_loader = torch.utils.data.DataLoader(testset, batch_size=1000, shuffle=False)
val_loader = torch.utils.data.DataLoader(valset, batch_size=1000, shuffle=False)
This is the architecture of my model.
class CifarModel(nn.Module):
def __init__(self):
super().__init__()
self.linear = nn.Linear(input_size, num_classes)
def forward(self, xb):
xb = xb.view(-1, 64*8*8)
#xb = xb.reshape(-1, 784)
print(xb.shape)
out = self.linear(xb)
return out
def training_step(self, batch):
images, labels = batch
out = self(images) # Generate predictions
loss = F.cross_entropy(out, labels) # Calculate loss
return loss
def validation_step(self, batch):
images, labels = batch
out = self(images) # Generate predictions
loss = F.cross_entropy(out, labels) # Calculate loss
acc = accuracy(out, labels) # Calculate accuracy
return {'val_loss': loss.detach(), 'val_acc': acc.detach()}
def validation_epoch_end(self, outputs):
batch_losses = [x['val_loss'] for x in outputs]
epoch_loss = torch.stack(batch_losses).mean() # Combine losses
batch_accs = [x['val_acc'] for x in outputs]
epoch_acc = torch.stack(batch_accs).mean() # Combine accuracies
return {'val_loss': epoch_loss.item(), 'val_acc': epoch_acc.item()}
def epoch_end(self, epoch, result):
print("Epoch [{}], val_loss: {:.4f}, val_acc: {:.4f}".format(epoch, result['val_loss'], result['val_acc']))
model = CifarModel()
def accuracy(outputs, labels):
_, preds = torch.max(outputs, dim=1)
return torch.tensor(torch.sum(preds == labels).item() / len(preds))
def evaluate(model, val_loader):
outputs = [model.validation_step(batch) for batch in val_loader]
return model.validation_epoch_end(outputs)
def fit(epochs, lr, model, train_loader, val_loader, opt_func=torch.optim.SGD):
history = []
optimizer = opt_func(model.parameters(), lr)
for epoch in range(epochs):
# Training Phase
for batch in train_loader:
loss = model.training_step(batch)
loss.backward()
optimizer.step()
optimizer.zero_grad()
# Validation phase
result = evaluate(model, val_loader)
model.epoch_end(epoch, result)
history.append(result)
return history
evaluate(model, val_loader)

Here you are specifying that the number of output classes should be 10:
num_classes = 10
Your forward function does not reflect this:
xb = xb.view(-1, 64*8*8) # you get 750x4096
out = self.linear(xb) # here an input of
# input_size to linear layer = 4*4*64 # 1024
# num_classes = 10
Modify it like this:
xb = xb.view(-1, 64*4*4) # you get 750x1024
out = self.linear(xb) # M1 750x1024 M2 1024x10:
# input_size = 4*4*64 # 1024
# num_classes = 10