I'm running the following using the huggingface implementation:
t1 = "My example sentence is really great."
tokenizer = TransfoXLTokenizer.from_pretrained('transfo-xl-wt103')
model = TransfoXLLMHeadModel.from_pretrained("transfo-xl-wt103")
encoded_input = tokenizer(t1, return_tensors='pt', add_space_before_punct_symbol=True)
output = model(**encoded_input)
tmp = output[0].detach().numpy()
print(tmp.shape)
>>> (1, 7, 267735)
With the goal of getting output embeddings that I'll use downstream.
The last dimension is /substantially/ larger than I expected, and it looks like it is the size of the entire vocab_size rather than a reduction based on the ECL from the paper (which potentially I am misinterpreting).
What argument would I provide the model to reduce this layer size to a smaller dimensional space, something more like the basic BERT at 400 or 768 and still obtain good performance based on the pretrained embeddings?
That's because you used ...LMHeadModel, which predicts the next token. You can use TransfoXLModel.from_pretrained("transfo-xl-wt103") instead, then output[0] is the last hidden state which has the shape (batch_size, sequence_length, hidden_size).
Related
Is there a way to get the topic distribution of an unseen document using a pretrained LDA model without using the LDA_Model[unseenDoc] syntax? I am trying to implement my LDA model into a web application, and if there was a way to use matrix multiplication to get a similar result then I could use the model in javascript.
For example, I tried the following:
import numpy as np
import gensim
from gensim.corpora import Dictionary
from gensim import models
import nltk
from nltk.stem import WordNetLemmatizer, SnowballStemmer
nltk.download('wordnet')
def Preprocesser(text_list):
smallestWordSize = 3
processedList = []
for token in gensim.utils.simple_preprocess(text_list):
if token not in gensim.parsing.preprocessing.STOPWORDS and len(token) > smallestWordSize:
processedList.append(StemmAndLemmatize(token))
return processedList
lda_model = models.LdaModel.load('LDAModel\GoldModel') #Load pretrained LDA model
dictionary = Dictionary.load("ModelTrain\ManDict") #Load dictionary model was trained on
#Sample Unseen Doc to Analyze
doc = "I am going to write a string about how I can't get my task executor \
to travel properly. I am trying to use the \
AGV navigator, but it doesn't seem to be working network. I have been trying\
to use the AGV Process flow but that isn't working either speed\
trailer offset I am now going to change this so I can see how fast it runs"
termTopicMatrix = lda_model.get_topics() #Get Term-topic Matrix from pretrained LDA model
cleanDoc = Preprocesser(doc) #Tokenize, lemmatize, clean and stem words
bowDoc = dictionary.doc2bow(cleanDoc) #Create bow using dictionary
dictSize = len(termTopicMatrix[0]) #Get length of terms in dictionary
fullDict = np.zeros(dictSize) #Initialize array which is length of dictionary size
First = [first[0] for first in bowDoc] #Get index of terms in bag of words
Second = [second[1] for second in bowDoc] #Get frequency of term in bag of words
fullDict[First] = Second #Add word frequency to full dictionary
print('Matrix Multiplication: \n', np.dot(termTopicMatrix,fullDict))
print('Conventional Syntax: \n', lda_model[bowDoc])
Output:
Matrix Multiplication:
[0.0283254 0.01574513 0.03669142 0.01671816 0.03742738 0.01989461
0.01558603 0.0370233 0.04648389 0.02887623 0.00776652 0.02147539
0.10045133 0.01084273 0.01229849 0.00743788 0.03747379 0.00345913
0.03086953 0.00628912 0.29406082 0.10656977 0.00618827 0.00406316
0.08775404 0.00785408 0.02722744 0.09957815 0.01669402 0.00744392
0.31177135 0.03063149 0.07211428 0.01192056 0.03228589]
Conventional Syntax:
[(0, 0.070313625), (2, 0.056414187), (18, 0.2016589), (20, 0.46500313), (24, 0.1589748)]
In the pretrained model there are 35 topics and 1155 words.
In the "Conventional Syntax" output, the first element of each tuple is the index of the topic and the second element is the probability of the topic. In the "Matrix Multiplication" version, the probability is the index and the value is the probability. Clearly the two don't match up.
For example, the lda_model[unseenDoc] shows that topic 0 has a 0.07 probability, but the matrix multiplication method says that topic has a 0.028 probability. Am I missing a step here?
You can review the full source code used by LDAModel's get_document_topics() method in your installation, or online at:
https://github.com/RaRe-Technologies/gensim/blob/e75f6c8e8d1dee0786b1b2cd5ef60da2e290f489/gensim/models/ldamodel.py#L1283
(It also makes use of the inference() method in the same file.)
It's doing a lot more scaling/normalization/clipping than your code, which is likely the cause of the discrepancy. But you should be able to examine, line-by-line, where your process & its differ to get the steps to match up.
It also shouldn't be hard to use the gensim code's steps as guidance for creating parallel Javascript code that, given the right parts of the model's state, can reproduce its results.
My question is how I should interpret my situation?
I trained a Doc2Vec model following this tutorial https://blog.griddynamics.com/customer2vec-representation-learning-and-automl-for-customer-analytics-and-personalization/.
For some reason, doc_model.docvecs.doctags returns {}. But doc_model.docvecs.vectors_docs seems to return a proper value.
Why the doc2vec object doesn't return any doctags but vectors_docs?
Thank you for any comments and answers in advance.
This is the code I used to train a Doc2Vec model.
from gensim.models.doc2vec import LabeledSentence, TaggedDocument, Doc2Vec
import timeit
import gensim
embeddings_dim = 200 # dimensionality of user representation
filename = f'models/customer2vec.{embeddings_dim}d.model'
if TRAIN_USER_MODEL:
class TaggedDocumentIterator(object):
def __init__(self, df):
self.df = df
def __iter__(self):
for row in self.df.itertuples():
yield TaggedDocument(words=dict(row._asdict())['all_orders'].split(),tags=[dict(row._asdict())['user_id']])
it = TaggedDocumentIterator(combined_orders_by_user_id)
doc_model = gensim.models.Doc2Vec(vector_size=embeddings_dim,
window=5,
min_count=10,
workers=mp.cpu_count()-1,
alpha=0.055,
min_alpha=0.055,
epochs=20) # use fixed learning rate
train_corpus = list(it)
doc_model.build_vocab(train_corpus)
for epoch in tqdm(range(10)):
doc_model.alpha -= 0.005 # decrease the learning rate
doc_model.min_alpha = doc_model.alpha # fix the learning rate, no decay
doc_model.train(train_corpus, total_examples=doc_model.corpus_count, epochs=doc_model.iter)
print('Iteration:', epoch)
doc_model.save(filename)
print(f'Model saved to [{filename}]')
else:
doc_model = Doc2Vec.load(filename)
print(f'Model loaded from [{filename}]')
doc_model.docvecs.vectors_docs returns
If all of the tags you supply are plain Python ints, those ints are used as the direct-indexes into the vectors-array.
This saves the overhead of maintaining a mapping from arbitrary tags to indexes.
But, it may also cause an over-allocation of the vectors array, to be large enough for the largest int tag you provided, even if other lower ints are never used. (That is: if you provided a single document, with a tags=[1000000], it will allocate an array sufficient for tags 0 to 1000000, even if most of those never appear in your training data.)
If you want model.docvecs.doctags to collect a list of all your tags, use string tags rather than plain ints.
Separately: don't call train() multiple times in your own loop, or manage the alpha learning-rate in your own code, unless you have an overwhelmingly good reason to do so. It's inefficient & error-prone. (Your code, for example, is actually performing 200 training-epochs, and if you were to increase the loop count without carefully adjusting your alpha increment, you could wind up with nonsensical negative alpha values – a very common error in code following this bad practice. Call .train() once with your desired number of epochs. Set the alpha and min_alpha at reasonable starting and nearly-zero values – probably just the defaults unless you're sure your change is helping – and then leave them alone.
I am new to ML and TensorFlow. I am trying to build a CNN to categorize a good image against corrupted images, similar to rock paper scissor tutorials in tensor flow, except for only two categories.
The Colab Notebook
Model Architecture
train_generator = training_datagen.flow_from_directory(
TRAINING_DIR,
target_size=(150,150),
class_mode='categorical'
)
validation_generator = validation_datagen.flow_from_directory(
VALIDATION_DIR,
target_size=(150,150),
class_mode='categorical'
)
model = tf.keras.models.Sequential([
# Note the input shape is the desired size of the image 150x150 with 3 bytes color
# This is the first convolution
tf.keras.layers.Conv2D(64, (3,3), activation='relu', input_shape=(150, 150, 3)),
tf.keras.layers.MaxPooling2D(2, 2),
# The second convolution
tf.keras.layers.Conv2D(64, (3,3), activation='relu'),
tf.keras.layers.MaxPooling2D(2,2),
# The third convolution
tf.keras.layers.Conv2D(128, (3,3), activation='relu'),
tf.keras.layers.MaxPooling2D(2,2),
# The fourth convolution
tf.keras.layers.Conv2D(128, (3,3), activation='relu'),
tf.keras.layers.MaxPooling2D(2,2),
# Flatten the results to feed into a DNN
tf.keras.layers.Flatten(),
tf.keras.layers.Dropout(0.5),
# 512 neuron hidden layer
tf.keras.layers.Dense(512, activation='relu'),
tf.keras.layers.Dense(2, activation='softmax')
])
model.summary()
model.compile(loss = 'categorical_crossentropy', optimizer='rmsprop', metrics=['accuracy'])
history = model.fit_generator(train_generator, epochs=25, validation_data = validation_generator, verbose = 1)
model.save("rps.h5")
Only Change I made was turning input shape to (150,150,1) to (150,150,3) and changed last layers output to 2 neurons from 3. The training gave me consistently accuracy of 90 above for data set of 600 images in each class. But when I am making a prediction using code in the tutorial, it gives me highly wrong values even for data in the data set.
PREDICTION
Original code in TensorFlow tutorial
for file in onlyfiles:
path = fn
img = image.load_img(path, target_size=(150, 150,3)) # changed target_size to (150, 150,3)) from (150,150 )
x = image.img_to_array(img)
x = np.expand_dims(x, axis=0)
images = np.vstack([x])
classes = model.predict(images, batch_size=10)
print(fn)
print(classes)
I changed target_size to (150, 150,3)) from (150,150) in my belief that since my input is a 3 channel image,
Result
It gives very wrong values [0,1][0,1] for even images in which are in dataset
But when I changed the code to this
for file in onlyfiles:
path = fn
img = image.load_img(path, target_size=(150, 150,3))
x = image.img_to_array(img)
x = np.expand_dims(x, axis=0)
x /= 255.
classes = model.predict(images, batch_size=10)
print(fn)
print(classes)
In this case values come like
[[9.9999774e-01 2.2242968e-06]]
[[9.9999785e-01 2.1864464e-06]]
[[9.9999785e-01 2.1641024e-06]]
one or two errors are there but it is very much correct
So my question even though the last activation is softmax, why it is now coming in decimal values, is there any logical mistake in the way I am making predictions.? I tried binary also, but couldn't find much difference.
Please note -
When you are changing output classes from 2 to 3, you are asking the model to categorise into 3 classes. This would contradict your problem statement which separates good and corrupted ones i.e 2 output classes (a binary problem). I think it can be reversed from 3 to 2 if I have understood the question correctly.
Second the output you are getting is perfectly correct, the neural network models outputs probabilities instead of absolute class values like 0 or 1. By probability, it tells how likely it belongs to say class 0 or class 1.
Also , as mentioned above by #BBloggsbott - you just have to use np.argmax on the output array which will tell you the probability of belonging to class 1 (Positive class) by default.
Hope this helps.
Thanks.
Softmax returns probability distributions for the vector it gets as input. So, the fact that you are getting decimal values is not a problem. If you want to find the exact class each image belongs to, try using the argmax function on the predictions.
I wanted to see if I can simply set new weights for gensim's Word2Vec without training. I get the 20 News Group data set from scikit-learn (from sklearn.datasets import fetch_20newsgroups) and trained an instance of Word2Vec on it:
model_w2v = models.Word2Vec(sg = 1, size=300)
model_w2v.build_vocab(all_tokens)
model_w2v.train(all_tokens, total_examples=model_w2v.corpus_count, epochs = 30)
Here all_tokens is the tokenized data set.
Then I created a new instance of Word2Vec without training
model_w2v_new = models.Word2Vec(sg = 1, size=300)
model_w2v_new.build_vocab(all_tokens)
and set the embeddings of the new Word2Vec equal to the first one
model_w2v_new.wv.vectors = model_w2v.wv.vectors
Most of the functions work as expected, e.g.
model_w2v.wv.similarity( w1='religion', w2 = 'religions')
> 0.4796233
model_w2v_new.wv.similarity( w1='religion', w2 = 'religions')
> 0.4796233
and
model_w2v.wv.words_closer_than(w1='religion', w2 = 'judaism')
> ['religions']
model_w2v_new.wv.words_closer_than(w1='religion', w2 = 'judaism')
> ['religions']
and
entities_list = list(model_w2v.wv.vocab.keys()).remove('religion')
model_w2v.wv.most_similar_to_given(entity1='religion',entities_list = entities_list)
> 'religions'
model_w2v_new.wv.most_similar_to_given(entity1='religion',entities_list = entities_list)
> 'religions'
However, most_similar doesn't work:
model_w2v.wv.most_similar(positive=['religion'], topn=3)
[('religions', 0.4796232581138611),
('judaism', 0.4426296651363373),
('theists', 0.43141329288482666)]
model_w2v_new.wv.most_similar(positive=['religion'], topn=3)
>[('roderick', 0.22643062472343445),
> ('nci', 0.21744996309280396),
> ('soviet', 0.20012077689170837)]
What am I missing?
Disclaimer. I posted this question on datascience.stackexchange but got no response, hoping to have a better luck here.
Generally, your approach should work.
It's likely the specific problem you're encountering was caused by an extra probing step you took and is not shown in your code, because you had no reason to think it significant: some sort of most_similar()-like operation on model_w2v_new after its build_vocab() call but before the later, malfunctioning operations.
Traditionally, most_similar() calculations operate on a version of the vectors that has been normalized to unit-length. The 1st time these unit-normed vectors are needed, they're calculated – and then cached inside the model. So, if you then replace the raw vectors with other values, but don't discard those cached values, you'll see results like you're reporting – essentially random, reflecting the randomly-initialized-but-never-trained starting vector values.
If this is what happened, just discarding the cached values should cause the next most_similar() to refresh them properly, and then you should get the results you expect:
model_w2v_new.wv.vectors_norm = None
public BinomialModelPrediction predictBinomial(RowData data) throws PredictException {
double[] preds = this.preamble(ModelCategory.Binomial, data);
BinomialModelPrediction p = new BinomialModelPrediction();
double d = preds[0];
p.labelIndex = (int)d;
String[] domainValues = this.m.getDomainValues(this.m.getResponseIdx());
p.label = domainValues[p.labelIndex];
p.classProbabilities = new double[this.m.getNumResponseClasses()];
System.arraycopy(preds, 1, p.classProbabilities, 0, p.classProbabilities.length);
if(this.m.calibrateClassProbabilities(preds)) {
p.calibratedClassProbabilities = new double[this.m.getNumResponseClasses()];
System.arraycopy(preds, 1, p.calibratedClassProbabilities, 0, p.calibratedClassProbabilities.length);
}
return p;
}
Eg: classProbabilities =[0.82333,0,276666]
labelIndex = 1
label = true
domainValues = [false,true]
what does this labelIndex signifies and does the class probabilities
order is same as the domain value order ,If order is same then it means that here probability of false is 0.82333 and probability of true is 0.27666 but why is this labelIndex showing as 1 and label as true.
Please help me to figure out this issue.
Like Tom commented, the prediction is not "wrong". You can infer from this that the threshold H2O has chosen is less than 0.27666. You probably have imbalanced training data, otherwise H2O would have not picked a low threshold for classifying a predicted value of 0.27666 as a 1. Does your training set include fewer examples of the positive class than the negative class?
If you don't like that threshold for whatever reason, then you can manually create your own. Just make sure you know how to properly evaluate the effect of using different thresholds on the performance of your model, otherwise I'd recommend just using the default threshold.
The name, "classProbabilities" is a misnomer. These are not actual probabilities, they are predicted values, though people often use the terms interchangeably. Binary classification algorithms produce "predicted values" that look like probabilities when they're between 0 and 1, but unless a calibration process is performed, they are not going to represent the probabilities. Calibration is not necessarily a straight-forward process and there are many techniques. Here's some more info about calibration methods for imbalanced data. In H2O, you can perform calibration using Platt scaling using the calibrate_model option. But this is probably not really necessary to what you're trying to do.
The proper way to use the raw output from a binary classification model is to only look at the predicted value for the positive class (you can simply ignore the predicted value for the negative class). Then you choose a threshold which suits your needs, or you can use the default threshold in H2O, which is chosen to maximize the F1 score. Some other software will use a hardcoded threshold of 0.5, but that will be a terrible choice if you don't have an even number of positive and negative examples in your training data. If you have only a few positive examples in your training data, then the best threshold will be something much lower than 0.5.