Related
I would like to print the output vector/tensor in BERT an wasn't sure how to do it. I've been using the following example to walk myself through it:
https://colab.research.google.com/drive/1pTuQhug6Dhl9XalKB0zUGf4FIdYFlpcX
Its a simple classification problem, but I want to be able to get the output vector before we classify the training examples. Can someone point to where in the code I can do this and how?
Do you want the weights to the output layer or the logits? I think you want the logits, it is more work but better in the long run to subclass so you can play with it yourself. Here part of subclass I did where I wanted dropout and more control. I'll just include it here where you can access all the parts of the model
class MyBert(BertPreTrainedModel):
def __init__(self, config, dropout_prob):
super().__init__(config)
self.num_labels = 2
self.bert = BertModel(config)
self.dropout = torch.nn.Dropout(dropout_prob)
self.classifier = torch.nn.Linear(config.hidden_size, self.num_labels)
self.init_weights()
def forward(self,
input_ids=None,
attention_mask=None,
token_type_ids=None,
position_ids=None,
head_mask=None,
inputs_embeds=None,
labels=None,):
outputs = self.bert(
input_ids,
attention_mask=attention_mask,
token_type_ids=token_type_ids,
position_ids=position_ids,
head_mask=head_mask,
inputs_embeds=inputs_embeds,
)
pooled_output = outputs[1]
pooled_output = self.dropout(pooled_output)
logits = self.classifier(pooled_output)
outputs = (logits,) + outputs[2:] # add hidden states and attention if they are here
if labels is not None:
loss_fct = torch.nn.CrossEntropyLoss()
loss = loss_fct(logits.view(-1, self.num_labels), labels.view(-1))
outputs = (loss,) + outputs
return outputs # (loss), logits, (hidden_states), (attentions)
I’m trying to train a Transformer Seq2Seq model using nn.Transformer class. I believe I am implementing it wrong, since when I train it, it seems to fit too fast, and during inference it repeats itself often. This seems like a masking issue in the decoder, and when I remove the target mask, the training performance is the same. This leads me to believe I am doing the target masking wrong. Here is my model code:
class TransformerModel(nn.Module):
def __init__(self,
vocab_size, input_dim, heads, feedforward_dim, encoder_layers, decoder_layers,
sos_token, eos_token, pad_token, max_len=200, dropout=0.5,
device=(torch.device("cuda") if torch.cuda.is_available() else torch.device("cpu"))):
super(TransformerModel, self).__init__()
self.target_mask = None
self.embedding = nn.Embedding(vocab_size, input_dim, padding_idx=pad_token)
self.pos_embedding = nn.Embedding(max_len, input_dim, padding_idx=pad_token)
self.transformer = nn.Transformer(
d_model=input_dim, nhead=heads, num_encoder_layers=encoder_layers,
num_decoder_layers=decoder_layers, dim_feedforward=feedforward_dim,
dropout=dropout)
self.out = nn.Sequential(
nn.Linear(input_dim, feedforward_dim),
nn.ReLU(),
nn.Linear(feedforward_dim, vocab_size))
self.device = device
self.max_len = max_len
self.sos_token = sos_token
self.eos_token = eos_token
# Initialize all weights to be uniformly distributed between -initrange and initrange
def init_weights(self):
initrange = 0.1
self.encoder.weight.data.uniform_(-initrange, initrange)
self.decoder.bias.data.zero_()
self.decoder.weight.data.uniform_(-initrange, initrange)
# Generate mask covering the top right triangle of a matrix
def generate_square_subsequent_mask(self, size):
mask = (torch.triu(torch.ones(size, size)) == 1).transpose(0, 1)
mask = mask.float().masked_fill(mask == 0, float('-inf')).masked_fill(mask == 1, float(0.0))
return mask
def forward(self, src, tgt):
# src: (Max source seq len, batch size, 1)
# tgt: (Max target seq len, batch size, 1)
# Embed source and target with normal and positional embeddings
embedded_src = (self.embedding(src) +
self.pos_embedding(
torch.arange(0, src.shape[1]).to(self.device).unsqueeze(0).repeat(src.shape[0], 1)))
# Generate target mask
target_mask = self.generate_square_subsequent_mask(size=tgt.shape[0]).to(self.device)
embedded_tgt = (self.embedding(tgt) +
self.pos_embedding(
torch.arange(0, tgt.shape[1]).to(self.device).unsqueeze(0).repeat(tgt.shape[0], 1)))
# Feed through model
outputs = self.transformer(src=embedded_src, tgt=embedded_tgt, tgt_mask=target_mask)
outputs = F.log_softmax(self.out(outputs), dim=-1)
return outputs
For those having the same problem, my issue was that I wasn't properly adding the SOS token to the target I was feeding the model, and the EOS token to the target I was using in the loss function.
For reference:
The target fed to the model should be: [SOS] ....
And the target used for the loss should be: .... [EOS]
I need to visualize the output of Vgg16 model which classify 14 different classes.
I load the trained model and I did replace the classifier layer with the identity() layer but it doesn't categorize the output.
Here is the snippet:
the number of samples here is 1000 images.
epoch = 800
PATH = 'vgg16_epoch{}.pth'.format(epoch)
checkpoint = torch.load(PATH)
model.load_state_dict(checkpoint['model_state_dict'])
optimizer.load_state_dict(checkpoint['optimizer_state_dict'])
epoch = checkpoint['epoch']
class Identity(nn.Module):
def __init__(self):
super(Identity, self).__init__()
def forward(self, x):
return x
model.classifier._modules['6'] = Identity()
model.eval()
logits_list = numpy.empty((0,4096))
targets = []
with torch.no_grad():
for step, (t_image, target, classess, image_path) in enumerate(test_loader):
t_image = t_image.cuda()
target = target.cuda()
target = target.data.cpu().numpy()
targets.append(target)
logits = model(t_image)
print(logits.shape)
logits = logits.data.cpu().numpy()
print(logits.shape)
logits_list = numpy.append(logits_list, logits, axis=0)
print(logits_list.shape)
tsne = TSNE(n_components=2, verbose=1, perplexity=10, n_iter=1000)
tsne_results = tsne.fit_transform(logits_list)
target_ids = range(len(targets))
plt.scatter(tsne_results[:,0],tsne_results[:,1],c = target_ids ,cmap=plt.cm.get_cmap("jet", 14))
plt.colorbar(ticks=range(14))
plt.legend()
plt.show()
here is what this script has been produced: I am not sure why I have all colors for each cluster!
The VGG16 outputs over 25k features to the classifier. I believe it's too much to t-SNE. It's a good idea to include a new nn.Linear layer to reduce this number. So, t-SNE may work better. In addition, I'd recommend you two different ways to get the features from the model:
The best way to get it regardless of the model is by using the register_forward_hook method. You may find a notebook here with an example.
If you don't want to use the register, I'd suggest this one. After loading your model, you may use the following class to extract the features:
class FeatNet (nn.Module):
def __init__(self, vgg):
super(FeatNet, self).__init__()
self.features = nn.Sequential(*list(vgg.children())[:-1]))
def forward(self, img):
return self.features(img)
Now, you just need to call FeatNet(img) to get the features.
To include the feature reducer, as I suggested before, you need to retrain your model doing something like:
class FeatNet (nn.Module):
def __init__(self, vgg):
super(FeatNet, self).__init__()
self.features = nn.Sequential(*list(vgg.children())[:-1]))
self.feat_reducer = nn.Sequential(
nn.Linear(25088, 1024),
nn.BatchNorm1d(1024),
nn.ReLU()
)
self.classifier = nn.Linear(1024, 14)
def forward(self, img):
x = self.features(img)
x_r = self.feat_reducer(x)
return self.classifier(x_r)
Then, you can run your model returning x_r, that is, the reduced features. As I told you, 25k features are too much for t-SNE. Another method to reduce this number is by using PCA instead of nn.Linear. In this case, you send the 25k features to PCA and then train t-SNE using the PCA's output. I prefer using nn.Linear, but you need to test to check which one you get a better result.
I followed this great answer for sequence autoencoder,
LSTM autoencoder always returns the average of the input sequence.
but I met some problem when I try to change the code:
question one:
Your explanation is so professional, but the problem is a little bit different from mine, I attached some code I changed from your example. My input features are 2 dimensional, and my output is same with the input.
for example:
input_x = torch.Tensor([[0.0,0.0], [0.1,0.1], [0.2,0.2], [0.3,0.3], [0.4,0.4]])
output_y = torch.Tensor([[0.0,0.0], [0.1,0.1], [0.2,0.2], [0.3,0.3], [0.4,0.4]])
the input_x and output_y are same, 5-timesteps, 2-dimensional feature.
import torch
import torch.nn as nn
import torch.optim as optim
class LSTM(nn.Module):
def __init__(self, input_dim, latent_dim, num_layers):
super(LSTM, self).__init__()
self.input_dim = input_dim
self.latent_dim = latent_dim
self.num_layers = num_layers
self.encoder = nn.LSTM(self.input_dim, self.latent_dim, self.num_layers)
# I changed here, to 40 dimesion, I think there is some problem
# self.decoder = nn.LSTM(self.latent_dim, self.input_dim, self.num_layers)
self.decoder = nn.LSTM(40, self.input_dim, self.num_layers)
def forward(self, input):
# Encode
_, (last_hidden, _) = self.encoder(input)
# It is way more general that way
encoded = last_hidden.repeat(input.shape)
# Decode
y, _ = self.decoder(encoded)
return torch.squeeze(y)
model = LSTM(input_dim=2, latent_dim=20, num_layers=1)
loss_function = nn.MSELoss()
optimizer = optim.Adam(model.parameters())
y = torch.Tensor([[0.0,0.0], [0.1,0.1], [0.2,0.2], [0.3,0.3], [0.4,0.4]])
x = y.view(len(y), -1, 2) # I changed here
while True:
y_pred = model(x)
optimizer.zero_grad()
loss = loss_function(y_pred, y)
loss.backward()
optimizer.step()
print(y_pred)
The above code can learn very well, can you help review the code and give some instructions.
When I input 2 examples as the input to the model, the model cannot work:
for example, change the code:
y = torch.Tensor([[0.0,0.0], [0.1,0.1], [0.2,0.2], [0.3,0.3], [0.4,0.4]])
to:
y = torch.Tensor([[[0.0,0.0],[0.5,0.5]], [[0.1,0.1], [0.6,0.6]], [[0.2,0.2],[0.7,0.7]], [[0.3,0.3],[0.8,0.8]], [[0.4,0.4],[0.9,0.9]]])
When I compute the loss function, it complain some errors? can anyone help have a look
question two:
my training samples are with different length:
for example:
x1 = [[0.0,0.0], [0.1,0.1], [0.2,0.2], [0.3,0.3], [0.4,0.4]] #with 5 timesteps
x2 = [[0.5,0.5], [0.6,0.6], [0.7,0.7]] #with only 3 timesteps
How can I input these two training sample into the model at the same time for a batch training.
Recurrent N-dimensional autoencoder
First of all, LSTMs work on 1D samples, yours are 2D as it's usually used for words encoded with a single vector.
No worries though, one can flatten this 2D sample to 1D, example for your case would be:
import torch
var = torch.randn(10, 32, 100, 100)
var.reshape((10, 32, -1)) # shape: [10, 32, 100 * 100]
Please notice it's really not general, what if you were to have 3D input? Snippet belows generalizes this notion to any dimension of your samples, provided the preceding dimensions are batch_size and seq_len:
import torch
input_size = 2
var = torch.randn(10, 32, 100, 100, 35)
var.reshape(var.shape[:-input_size] + (-1,)) # shape: [10, 32, 100 * 100 * 35]
Finally, you can employ it inside neural network as follows. Look at forward method especially and constructor arguments:
import torch
class LSTM(nn.Module):
# input_dim has to be size after flattening
# For 20x20 single input it would be 400
def __init__(
self,
input_dimensionality: int,
input_dim: int,
latent_dim: int,
num_layers: int,
):
super(LSTM, self).__init__()
self.input_dimensionality: int = input_dimensionality
self.input_dim: int = input_dim # It is 1d, remember
self.latent_dim: int = latent_dim
self.num_layers: int = num_layers
self.encoder = torch.nn.LSTM(self.input_dim, self.latent_dim, self.num_layers)
# You can have any latent dim you want, just output has to be exact same size as input
# In this case, only encoder and decoder, it has to be input_dim though
self.decoder = torch.nn.LSTM(self.latent_dim, self.input_dim, self.num_layers)
def forward(self, input):
# Save original size first:
original_shape = input.shape
# Flatten 2d (or 3d or however many you specified in constructor)
input = input.reshape(input.shape[: -self.input_dimensionality] + (-1,))
# Rest goes as in my previous answer
_, (last_hidden, _) = self.encoder(input)
encoded = last_hidden.repeat(input.shape)
y, _ = self.decoder(encoded)
# You have to reshape output to what the original was
reshaped_y = y.reshape(original_shape)
return torch.squeeze(reshaped_y)
Remember you have to reshape your output in this case. It should work for any dimensions.
Batching
When it comes to batching and different length of sequences it is a little more complicated.
You have to pad each sequence in batch before pushing it through network. Usually, values with which you pad are zeros, you may configure it inside LSTM though.
You may check this link for an example. You will have to use functions like torch.nn.pack_padded_sequence and others to make it work, you may check this answer.
Oh, since PyTorch 1.1 you don't have to sort your sequences by length in order to pack them. But when it comes to this topic, grab some tutorials, should make things clearer.
Lastly: Please, separate your questions. If you perform the autoencoding with single example, move on to batching and if you have issues there, please post a new question on StackOverflow, thanks.
My code is as below:
class Mymodel(nn.Module):
def __init__(self, input_size, hidden_size, output_size, num_layers, batch_size):
super(Discriminator, self).__init__()
self.input_size = input_size
self.hidden_size = hidden_size
self.output_size = output_size
self.num_layers = num_layers
self.batch_size = batch_size
self.lstm = nn.LSTM(input_size, hidden_size)
self.proj = nn.Linear(hidden_size, output_size)
self.hidden = self.init_hidden()
def init_hidden(self):
return (Variable(torch.zeros(self.num_layers, self.batch_size, self.hidden_size)),
Variable(torch.zeros(self.num_layers, self.batch_size, self.hidden_size)))
def forward(self, x):
lstm_out, self.hidden = self.lstm(x, self.hidden)
output = self.proj(lstm_out)
result = F.sigmoid(output)
return result
I want to use LSTM to classify a sentence to good (1) or bad (0). Using this code, I get the result which is time_step * batch_size * 1 but not 0 or 1. How to edit the code in order to get the classification result?
Theory:
Recall that an LSTM outputs a vector for every input in the series. You are using sentences, which are a series of words (probably converted to indices and then embedded as vectors). This code from the LSTM PyTorch tutorial makes clear exactly what I mean (***emphasis mine):
lstm = nn.LSTM(3, 3) # Input dim is 3, output dim is 3
inputs = [autograd.Variable(torch.randn((1, 3)))
for _ in range(5)] # make a sequence of length 5
# initialize the hidden state.
hidden = (autograd.Variable(torch.randn(1, 1, 3)),
autograd.Variable(torch.randn((1, 1, 3))))
for i in inputs:
# Step through the sequence one element at a time.
# after each step, hidden contains the hidden state.
out, hidden = lstm(i.view(1, 1, -1), hidden)
# alternatively, we can do the entire sequence all at once.
# the first value returned by LSTM is all of the hidden states throughout
# the sequence. the second is just the most recent hidden state
# *** (compare the last slice of "out" with "hidden" below, they are the same)
# The reason for this is that:
# "out" will give you access to all hidden states in the sequence
# "hidden" will allow you to continue the sequence and backpropagate,
# by passing it as an argument to the lstm at a later time
# Add the extra 2nd dimension
inputs = torch.cat(inputs).view(len(inputs), 1, -1)
hidden = (autograd.Variable(torch.randn(1, 1, 3)), autograd.Variable(
torch.randn((1, 1, 3)))) # clean out hidden state
out, hidden = lstm(inputs, hidden)
print(out)
print(hidden)
One more time: compare the last slice of "out" with "hidden" below, they are the same. Why? Well...
If you're familiar with LSTM's, I'd recommend the PyTorch LSTM docs at this point. Under the output section, notice h_t is output at every t.
Now if you aren't used to LSTM-style equations, take a look at Chris Olah's LSTM blog post. Scroll down to the diagram of the unrolled network:
As you feed your sentence in word-by-word (x_i-by-x_i+1), you get an output from each timestep. You want to interpret the entire sentence to classify it. So you must wait until the LSTM has seen all the words. That is, you need to take h_t where t is the number of words in your sentence.
Code:
Here's a coding reference. I'm not going to copy-paste the entire thing, just the relevant parts. The magic happens at self.hidden2label(lstm_out[-1])
class LSTMClassifier(nn.Module):
def __init__(self, embedding_dim, hidden_dim, vocab_size, label_size, batch_size):
...
self.word_embeddings = nn.Embedding(vocab_size, embedding_dim)
self.lstm = nn.LSTM(embedding_dim, hidden_dim)
self.hidden2label = nn.Linear(hidden_dim, label_size)
self.hidden = self.init_hidden()
def init_hidden(self):
return (autograd.Variable(torch.zeros(1, self.batch_size, self.hidden_dim)),
autograd.Variable(torch.zeros(1, self.batch_size, self.hidden_dim)))
def forward(self, sentence):
embeds = self.word_embeddings(sentence)
x = embeds.view(len(sentence), self.batch_size , -1)
lstm_out, self.hidden = self.lstm(x, self.hidden)
y = self.hidden2label(lstm_out[-1])
log_probs = F.log_softmax(y)
return log_probs
The main problem you need to figure out is the in which dim place you should put your batch size when you prepare your data. As far as I know, if you didn't set it in your nn.LSTM() init function, it will automatically assume that the second dim is your batch size, which is quite different compared to other DNN framework. Maybe you can try:
self.lstm = nn.LSTM(input_size, hidden_size, num_layers, batch_first=True)
like this to ask your model to treat your first dim as the batch dim.
As a last layer you have to have a linear layer for however many classes you want i.e 10 if you are doing digit classification as in MNIST . For your case since you are doing a yes/no (1/0) classification you have two lablels/ classes so you linear layer has two classes. I suggest adding a linear layer as
nn.Linear ( feature_size_from_previous_layer , 2)
and then train the model using a cross-entropy loss.
criterion = nn.CrossEntropyLoss()
optimizer = optim.SGD(net.parameters(), lr=0.001, momentum=0.9)