I recently implemented a name generating RNN "from scratch" which was doing ok but far from perfect. So I thought about trying my luck with pytorch's LSTM class to see if it makes a difference. Indeed it does and the outpus looks way better for the first 7 ~ 8 characters. But then the networks gets caught in a loop and outputs things like "laulaulaulau" or "rourourourou" (it is supposed the generate french names).
Is it a often occuring problem ? If so do you know a way to fix it ? I'm concern about the fact the network doesn't produce EOS tokens...
This is an issue which has already been asked here Why does my keras LSTM model get stuck in an infinite loop?
but not really answered hence my post.
here is the model :
class pytorchLSTM(nn.Module):
def __init__(self,input_size,hidden_size):
super(pytorchLSTM,self).__init__()
self.input_size = input_size
self.hidden_size = hidden_size
self.lstm = nn.LSTM(input_size, hidden_size)
self.output_layer = nn.Linear(hidden_size,input_size)
self.tanh = nn.Tanh()
self.softmax = nn.LogSoftmax(dim = 2)
def forward(self, input, hidden)
out, hidden = self.lstm(input,hidden)
out = self.tanh(out)
out = self.output_layer(out)
out = self.softmax(out)
return out, hidden
The input and target are two sequences of one-hot encoded vectors respectively with a start of sequence and end of sequence vector at the start and the end. They represent the characters inside of a name taken from the name list (database).
I use a and token on each name from the database. here are the function I use
def inputTensor(line):
#tensor starts with <start of sequence> token.
tensor = torch.zeros(len(line)+1, 1, n_letters)
tensor[0][0][n_letters - 2] = 1
for li in range(len(line)):
letter = line[li]
tensor[li+1][0][all_letters.find(letter)] = 1
return tensor
# LongTensor of second letter to end (EOS) for target
def targetTensor(line):
letter_indexes = [all_letters.find(line[li]) for li in range(len(line))]
letter_indexes.append(n_letters - 1) # EOS
return torch.LongTensor(letter_indexes)
training loop :
def train_lstm(model):
start = time.time()
criterion = nn.NLLLoss()
optimizer = torch.optim.Adam(model.parameters())
n_iters = 20000
print_every = 1000
plot_every = 500
all_losses = []
total_loss = 0
for iter in range(1,n_iters+1):
line = randomChoice(category_line)
input_line_tensor = inputTensor(line)
target_line_tensor = targetTensor(line).unsqueeze(-1)
optimizer.zero_grad()
loss = 0
output, hidden = model(input_line_tensor)
for i in range(input_line_tensor.size(0)):
l = criterion(output[i], target_line_tensor[i])
loss += l
loss.backward()
optimizer.step()
the sampling function :
def sample():
max_length = 20
input = torch.zeros(1,1,n_letters)
input[0][0][n_letters - 2] = 1
output_name = ""
hidden = (torch.zeros(2,1,lstm.hidden_size),torch.zeros(2,1,lstm.hidden_size))
for i in range(max_length):
output, hidden = lstm(input)
output = output[-1][:][:]
l = torch.multinomial(torch.exp(output[0]),num_samples = 1).item()
if l == n_letters - 1:
break
else:
letter = all_letters[l]
output_name += letter
input = inputTensor(letter)
return output_name
The typical sampled output looks something like that :
Laurayeerauerararauo
Leayealouododauodouo
Courouauurourourodau
Do you know how I can improve that ?
I found the explanation :
When using instances of the LSTM class as part of a RNN, the default input dimensions are (seq_length,batch_dim,input_size). To be able to interpret the output of the lstm as a probability (over the set of inputs) I needed to pass it to a Linear layer before the Softmax call, which is where the problem happens : Linear instances expects the input to be in the format (batch_dim,seq_length,input_size).
To fix this, one needs to pass batch_first = True as an argument to the LSTM upon creation, and then feed the RNN with an input of the form (batch_dim, seq_length, input_size).
Some tips to improve the network in the order of importance (and ease of implementing):
1. Training data
If you want your generated samples to look real, you have to give some real data to the network. Find a set of names, split those into letters and transform into indices. This step alone would give way more realistic names.
2. Separate start and end tokens.
I would go with <SON> (Start Of Name) and <EON> (End Of Name). In this configuration neural network can learn combinations of letters leading to <EON> and combinations of letters coming after <SON>. ATM it's trying to fit two different concepts into this one custom token.
3. Unsupervised Pretaining
You may want to give your letters some semantic meaning instead of one-hot encoded vectors, check word2vec for basic approach.
Basically, each letter would be represented by N-dimensional vector (say 50 dimensions) and would be closer in space if the letter occurs more often next to another letter (a closer to k than x).
Simple way to implement that would be taking some text dataset and trying to predict next letter at each timestep. Each letter would be represented by random vector at the beginning, through backpropagation letter representations would be updated to reflect their similarity.
Check pytorch embedding tutorial for more info.
4. Different architecture
You may want to check Andrej Karpathy's idea for generating baby names. It is simply described here.
Essentially, after training, you feed your model with random letters (say 10) and tell it to predict the next letter.
You remove last letter from random seed and put the predicted one in it's place. Iterate until <EON> is outputted.
Related
I have a pytorch model:
model = torch.nn.Sequential(
torch.nn.LSTM(40, 256, 3, batch_first=True),
torch.nn.Linear(256, 256),
torch.nn.ReLU()
)
And for the LSTM layer, I want to retrieve only the last hidden state from the batch to pass through the rest of the layers. Ex:
_, (hidden, _) = lstm(data)
hidden = hidden[-1]
Though, that example only works for a subclassed model. I need to somehow do this on a nn.Sequential() model that way when I save it, it can properly be converted to a tensorflow.js model. The reason I can't make and train this model in tensorflow.js is because I'm trying to implement this repo: Resemblyzer in tensorflow.js while still using the same weights as the pretrained Resemblyzer model which was made in pytorch as a subclassed model. I thought of using the torchvisions.transformations.Lambda() transformation but I would assume that would make it incompatible with tensorflow.js. Is there any way to make this possible while still allowing the model to convert properly?
You could split up your sequential but only doing so in the forward definition of your model on inference. Once defined:
model = nn.Sequential(nn.LSTM(40, 256, 3, batch_first=True),
nn.Linear(256, 256),
nn.ReLU())
You can split it:
>>> lstm, fc = model[0], model[1:]
Then infer in two steps:
>>> out, (hidden, _) = lstm(data)
>>> hidden = hidden[-1]
>>> out = fc(out) # <- or fc(out[-1]) depending on what you want
Though the answer is provided above, I thought of elaborating on the same as PyTorch LSTM documentation is confusing.
In TF, we directly get the last_state as the output. No further action needed.
Let us check the Torch output of LSTM:
There are 2 outputs - a sequence and a tuple. We are interested in the last state so we can ignore the sequence and focus on the tuple. The tuple consists of 2 values - the first is the hidden state of the last cell (of all layers in the LSTM) and the second is the cell state of the last cell (again of all layers in the LSTM). We are interested in the hidden state. So
_, tup = self.bilstm(inp)
We are interested in tup[0]. Let us dig further into this.
The shape of tup[0] is somewhat odd with batch size at the centre. On the left of the batch size is the number of layers in the LSTM (multiply 2 if is biLSTM). On the right is the dimension you have provided while defining the LSTM. You could take the output from the last layer by simply doing a tup[0][-1] which is the answer provided above.
Alternatively if you want to make use of hidden states across layers, you may try something like:
out = tup[0].swapaxes(0,1)
out = out.reshape(*out.shape[:-2], -1)
The first line produces shape of batch_size, num_layers, hidden_size_specified. The second line produces shape of batch_size, num_layers x hidden_size_specified
(For e.g., Let us say, yours is a biLSTM and you have 3 layers and your hiddensize is 100, you could choose to concatenate the output such that you get one vector of 2 x 3 x 100 = 600 dimensions and then run a simple linear layer on top of this to get the output you want.)
There is another way to get the output of the LSTM. We discussed that the first output of an LSTM is a sequence:
sequence, tup = self.bilstm(inp)
This sequence is the output of the LAST hidden layer of the LSTM. It is a sequence because it contains hidden states of EVERY cell in this layer. So its length will be the input sequence length that you have provided. We could choose to take the hidden state of the last element in the sequence by doing a:
#shape of sequence is: batch_size, seq_size, dim
sequence = sequence.swapaxes(0,1)
#shape of sequence is: seq_size, batch_size, dim
sequence = sequence[-1]
#shape of sequence is: batch_size, dim (ie last seq is taken)
Needless to say this will be the same value we got by taking the last layer from tup[0]. Well, not quite! If the LSTM is a biLSTM, then using the sequence approach returns is 2 x hidden_size dim output (which is correct) wheras using the tup[0][-1] approach will give us only hidden_size dim even for a biLSTM. OP's LSTM is a non-biLSTM so both answers hold true.
I'm using Torchtext for some NLP tasks, specifically using the built-in embeddings.
I want to be able to do a inverse vector search: Generate a noisy vector, find the vector that is closest to it, then get back the word that is "closest" to the noisy vector.
From the torchtext docs, here's how to attach embeddings to a built-in dataset:
from torchtext.vocab import GloVe
from torchtext import data
embedding = GloVe(name='6B', dim=100)
# Set up fields
TEXT = data.Field(lower=True, include_lengths=True, batch_first=True)
LABEL = data.Field(sequential=False, is_target=True)
# make splits for data
train, test = datasets.IMDB.splits(TEXT, LABEL)
# build the vocabulary
TEXT.build_vocab(train, vectors=embedding, max_size=100000)
LABEL.build_vocab(train)
# Get an example vector
embedding.get_vecs_by_tokens("germany")
Then we can build the annoy index:
from annoy import AnnoyIndex
num_trees = 50
ann_index = AnnoyIndex(embedding_dims, 'angular')
# Iterate through each vector in the embedding and add it to the index
for vector_num, vector in enumerate(TEXT.vocab.vectors):
ann_index.add_item(vector_num, vector) # Here's the catch: will vector_num correspond to torchtext.vocab.Vocab.itos?
ann_index.build(num_trees)
Then say I want to retrieve a word using a noisy vector:
# Get an existing vector
original_vec = embedding.get_vecs_by_tokens("germany")
# Add some noise to it
noise = generate_noise_vector(ndims=100)
noisy_vector = original_vec + noise
# Get the vector closest to the noisy vector
closest_item_idx = ann_index.get_nns_by_vector(noisy_vector, 1)[0]
# Get word from noisy item
noisy_word = TEXT.vocab.itos[closest_item_idx]
My question comes in for the last two lines above: The ann_index was built using enumerate over the embedding object, which is a Torch tensor.
The [vocab][2] object has its own itos list that given an index returns a word.
My question is this: Can I be certain that the order in which words appear in the itos list, is the same as the order in TEXT.vocab.vectors? How can I map one index to the other?
Can I be certain that the order in which words appear in the itos list, is the same as the order in TEXT.vocab.vectors?
Yes.
The Field class will always instantiate a Vocab object (source), and since you are passing the pre-trained vectors to TEXT.build_vocab, the Vocab constructor will call the load_vectors function.
if vectors is not None:
self.load_vectors(vectors, unk_init=unk_init, cache=vectors_cache)
In the load_vectors, the vectors are filled by enumerating the words in the itos.
for i, token in enumerate(self.itos):
start_dim = 0
for v in vectors:
end_dim = start_dim + v.dim
self.vectors[i][start_dim:end_dim] = v[token.strip()]
start_dim = end_dim
assert(start_dim == tot_dim)
Therefore, you can be certain that itos and vectors will have the same order.
Suppose I need to build a network that takes two inputs:
A patient's information, represented as an array of features
Selected treatment, represented as one-hot encoded array
Now how do I build a network that outputs a 2D probability matrix A where A[i,j] represents the probability the patient will end up at state j under treatment i. Let's say there are n possible states, and under any treatment, the total probability of all n states sums up to 1.
I wanted to do this because I was motivated by a similar network, where the inputs are the same as above, but the output is a 1d array representing the expected lifetime after treatment i is delivered. And such network is built as follows:
def default_dense(feature_shape, n_treatment):
feature_input = keras.layers.Input(feature_shape)
treatment_input = keras.layers.Input((n_treatments,))
hidden_1 = keras.layers.Dense(16, activation = 'relu')(feature_input)
hidden_2 = keras.layers.Dense(16, activation = 'relu')(hidden_1)
output = keras.layers.Dense(n_treatments)(hidden_2)
output_on_action = keras.layers.multiply([output, treatment_input])
model = keras.models.Model([feature_input, treatment_input], output_on_action)
model.compile(optimizer=tf.optimizers.Adam(0.001),loss='mse')
return model
And the training is simply
model.fit(x = [features, encoded_treatments], y = encoded_treatments * lifetime[:, np.newaxis], verbose = 0)
This is super handy because when predicting, I can use np.ones() as the encoded_treatments, and the network gives expected lifetimes under all treatments, thus choosing the best one is one-step. Certainly I can create multiple networks, each for a treatment, but it would be much less efficient.
Now the questions is, can I do the same to probability output?
I have figured it out myself. The trick is to use RepeatVector() and Permute() layers to generate a matrix mask for treatments.
The output is an element-wise Multiply() of the mask and a Softmax() of same size.
This release of PyTorch seems provide the PackedSequence for variable lengths of input for recurrent neural network. However, I found it's a bit hard to use it correctly.
Using pad_packed_sequence to recover an output of a RNN layer which were fed by pack_padded_sequence, we got a T x B x N tensor outputs where T is the max time steps, B is the batch size and N is the hidden size. I found that for short sequences in the batch, the subsequent output will be all zeros.
Here are my questions.
For a single output task where the one would need the last output of all the sequences, simple outputs[-1] will give a wrong result since this tensor contains lots of zeros for short sequences. One will need to construct indices by sequence lengths to fetch the individual last output for all the sequences. Is there more simple way to do that?
For a multiple output task (e.g. seq2seq), usually one will add a linear layer N x O and reshape the batch outputs T x B x O into TB x O and compute the cross entropy loss with the true targets TB (usually integers in language model). In this situation, do these zeros in batch output matters?
Question 1 - Last Timestep
This is the code that i use to get the output of the last timestep. I don't know if there is a simpler solution. If it is, i'd like to know it. I followed this discussion and grabbed the relative code snippet for my last_timestep method. This is my forward.
class BaselineRNN(nn.Module):
def __init__(self, **kwargs):
...
def last_timestep(self, unpacked, lengths):
# Index of the last output for each sequence.
idx = (lengths - 1).view(-1, 1).expand(unpacked.size(0),
unpacked.size(2)).unsqueeze(1)
return unpacked.gather(1, idx).squeeze()
def forward(self, x, lengths):
embs = self.embedding(x)
# pack the batch
packed = pack_padded_sequence(embs, list(lengths.data),
batch_first=True)
out_packed, (h, c) = self.rnn(packed)
out_unpacked, _ = pad_packed_sequence(out_packed, batch_first=True)
# get the outputs from the last *non-masked* timestep for each sentence
last_outputs = self.last_timestep(out_unpacked, lengths)
# project to the classes using a linear layer
logits = self.linear(last_outputs)
return logits
Question 2 - Masked Cross Entropy Loss
Yes, by default the zero padded timesteps (targets) matter. However, it is very easy to mask them. You have two options, depending on the version of PyTorch that you use.
PyTorch 0.2.0: Now pytorch supports masking directly in the CrossEntropyLoss, with the ignore_index argument. For example, in language modeling or seq2seq, where i add zero padding, i mask the zero padded words (target) simply like this:
loss_function = nn.CrossEntropyLoss(ignore_index=0)
PyTorch 0.1.12 and older: In the older versions of PyTorch, masking was not supported, so you had to implement your own workaround. I solution that i used, was masked_cross_entropy.py, by jihunchoi. You may be also interested in this discussion.
A few days ago, I found this method which uses indexing to accomplish the same task with a one-liner.
I have my dataset batch first ([batch size, sequence length, features]), so for me:
unpacked_out = unpacked_out[np.arange(unpacked_out.shape[0]), lengths - 1, :]
where unpacked_out is the output of torch.nn.utils.rnn.pad_packed_sequence.
I have compared it with the method described here, which looks similar to the last_timestep() method Christos Baziotis is using above (also recommended here), and the results are the same in my case.
I want to make use of Theano's logistic regression classifier, but I would like to make an apples-to-apples comparison with previous studies I've done to see how deep learning stacks up. I recognize this is probably a fairly simple task if I was more proficient in Theano, but this is what I have so far. From the tutorials on the website, I have the following code:
def errors(self, y):
# check if y has same dimension of y_pred
if y.ndim != self.y_pred.ndim:
raise TypeError(
'y should have the same shape as self.y_pred',
('y', y.type, 'y_pred', self.y_pred.type)
)
# check if y is of the correct datatype
if y.dtype.startswith('int'):
# the T.neq operator returns a vector of 0s and 1s, where 1
# represents a mistake in prediction
return T.mean(T.neq(self.y_pred, y))
I'm pretty sure this is where I need to add the functionality, but I'm not certain how to go about it. What I need is either access to y_pred and y for each and every run (to update my confusion matrix in python) or to have the C++ code handle the confusion matrix and return it at some point along the way. I don't think I can do the former, and I'm unsure how to do the latter. I've done some messing around with an update function along the lines of:
def confuMat(self, y):
x=T.vector('x')
classes = T.scalar('n_classes')
onehot = T.eq(x.dimshuffle(0,'x'),T.arange(classes).dimshuffle('x',0))
oneHot = theano.function([x,classes],onehot)
yMat = T.matrix('y')
yPredMat = T.matrix('y_pred')
confMat = T.dot(yMat.T,yPredMat)
confusionMatrix = theano.function(inputs=[yMat,yPredMat],outputs=confMat)
def confusion_matrix(x,y,n_class):
return confusionMatrix(oneHot(x,n_class),oneHot(y,n_class))
t = np.asarray(confusion_matrix(y,self.y_pred,self.n_out))
print (t)
But I'm not completely clear on how to get this to interface with the function in question and give me a numpy array I can work with.
I'm quite new to Theano, so hopefully this is an easy fix for one of you. I'd like to use this classifer as my output layer in a number of configurations, so I could use the confusion matrix with other architectures.
I suggest using a brute force sort of a way. You need an output for a prediction first. Create a function for it.
prediction = theano.function(
inputs = [index],
outputs = MLPlayers.predicts,
givens={
x: test_set_x[index * batch_size: (index + 1) * batch_size]})
In your test loop, gather the predictions...
labels = labels + test_set_y.eval().tolist()
for mini_batch in xrange(n_test_batches):
wrong = wrong + int(test_model(mini_batch))
predictions = predictions + prediction(mini_batch).tolist()
Now create confusion matrix this way:
correct = 0
confusion = numpy.zeros((outs,outs), dtype = int)
for index in xrange(len(predictions)):
if labels[index] is predictions[index]:
correct = correct + 1
confusion[int(predictions[index]),int(labels[index])] = confusion[int(predictions[index]),int(labels[index])] + 1
You can find this kind of an implementation in this repository.