dict has no attribute word_vec

[senjutisen7]

trafficstars

Hi

When I try to load the glove vectors,while training the LSTM, I get the following error:

AttributeError: 'dict' object has no attribute 'word_vec'

This happens when I try to train the LSTM with the following code :

def get_init_embedding(reverse_dict, embedding_size): print("Loading GLove vectors..") with open("C:/Users/sensen/OneDrive - HERE Global B.V-/Desktop/NLP/glove.6B.300d_pickle", 'rb') as handle: word_vectors = pickle.load(handle)

word_vec_list = list()

#loop through all the words in reverse dict

used_words = 0
for _,word in sorted(reverse_dict.items()):
    try:
        word_vec = word_vectors.word_vec(word)
used_words += 1
    except KeyError:
        word_vec = np.zeros([embedding_size], dtype=np.float32)
        
    word_vec_list.append(word_vec)
    

word_vec_list[2] = np.random.normal(0, 1, embedding_size)
word_vec_list[3] = np.random.normal(0, 1, embedding_size)

return np.array(word_vec_list)

Building model architecture class Model(object): def init(self, reversed_dict, article_max_len, summary_max_len, args, forward_only=False): self.vocabulary_size = len(reversed_dict) self.embedding_size = args.embedding_size self.num_hidden = args.num_hidden self.num_layers = args.num_layers self.learning_rate = args.learning_rate self.beam_width = args.beam_width if not forward_only:#forward_only=In training phase, keep_prob is used for defining drop out % self.keep_prob = args.keep_prob else: self.keep_prob = 1.0 self.cell = tf.nn.rnn_cell.BasicLSTMCell #initializing an LSTM cell with tf.variable_scope("decoder/projection"):#projection layer used in decoder in both training and testing.Projection layer is used for converting indices of individual words to continous weight vector self.projection_layer = tf.layers.Dense(self.vocabulary_size, use_bias=False) #Defining batch size self.batch_size = tf.placeholder(tf.int32, (), name="batch_size") self.X = tf.placeholder(tf.int32, [None, article_max_len]) #Defining X again for subsequent steps self.X_len = tf.placeholder(tf.int32, [None])#Defining X as length of articles. Its a place holder cause length of articles will become input that will be called in runtime env self.decoder_input = tf.placeholder(tf.int32, [None, summary_max_len])#Starting to define decoder self.decoder_len = tf.placeholder(tf.int32, [None])#Defining a decoder lenght self.decoder_target = tf.placeholder(tf.int32, [None, summary_max_len]) #Defining a decoder target self.global_step = tf.Variable(0, trainable=False)

    #EMBEDDING LAYER
    
    with tf.name_scope("embedding"):
        if not forward_only and args.glove:#if in training phase and if glove is used
            init_embeddings = tf.constant(get_init_embedding(reversed_dict, self.embedding_size), dtype=tf.float32)#Constant function because word embedding wont change as part of dict.Get_Init_embedding is a function that returns the vector for each word in our dict
        else:
            init_embeddings = tf.random_uniform([self.vocabulary_size, self.embedding_size], -1.0, 1.0)#if embedding is in testing phase, no constant dict is available. initializing a random variable
        self.embeddings = tf.get_variable("embeddings", initializer=init_embeddings)
        self.encoder_emb_inp = tf.transpose(tf.nn.embedding_lookup(self.embeddings, self.X), perm=[1, 0, 2]) #encoder input
        self.decoder_emb_inp = tf.transpose(tf.nn.embedding_lookup(self.embeddings, self.decoder_input), perm=[1, 0, 2]) #decoder input

    with tf.name_scope("encoder"):
        fw_cells = [self.cell(self.num_hidden) for _ in range(self.num_layers)]
        bw_cells = [self.cell(self.num_hidden) for _ in range(self.num_layers)]
        fw_cells = [rnn.DropoutWrapper(cell) for cell in fw_cells]
        bw_cells = [rnn.DropoutWrapper(cell) for cell in bw_cells]

        encoder_outputs, encoder_state_fw, encoder_state_bw = tf.contrib.rnn.stack_bidirectional_dynamic_rnn(
            fw_cells, bw_cells, self.encoder_emb_inp,
            sequence_length=self.X_len, time_major=True, dtype=tf.float32)
        self.encoder_output = tf.concat(encoder_outputs, 2)
        encoder_state_c = tf.concat((encoder_state_fw[0].c, encoder_state_bw[0].c), 1)
        encoder_state_h = tf.concat((encoder_state_fw[0].h, encoder_state_bw[0].h), 1)
        self.encoder_state = rnn.LSTMStateTuple(c=encoder_state_c, h=encoder_state_h)

    with tf.name_scope("decoder"), tf.variable_scope("decoder") as decoder_scope:
        decoder_cell = self.cell(self.num_hidden * 2)

        if not forward_only:
            attention_states = tf.transpose(self.encoder_output, [1, 0, 2])
            attention_mechanism = tf.contrib.seq2seq.BahdanauAttention(
                self.num_hidden * 2, attention_states, memory_sequence_length=self.X_len, normalize=True)
            decoder_cell = tf.contrib.seq2seq.AttentionWrapper(decoder_cell, attention_mechanism,
                                                               attention_layer_size=self.num_hidden * 2)
            initial_state = decoder_cell.zero_state(dtype=tf.float32, batch_size=self.batch_size)
            initial_state = initial_state.clone(cell_state=self.encoder_state)
            helper = tf.contrib.seq2seq.TrainingHelper(self.decoder_emb_inp, self.decoder_len, time_major=True)
            decoder = tf.contrib.seq2seq.BasicDecoder(decoder_cell, helper, initial_state)
            outputs, _, _ = tf.contrib.seq2seq.dynamic_decode(decoder, output_time_major=True, scope=decoder_scope)
            self.decoder_output = outputs.rnn_output
            self.logits = tf.transpose(
                self.projection_layer(self.decoder_output), perm=[1, 0, 2])
            self.logits_reshape = tf.concat(
                [self.logits, tf.zeros([self.batch_size, summary_max_len - tf.shape(self.logits)[1], self.vocabulary_size])], axis=1)
        else:
            tiled_encoder_output = tf.contrib.seq2seq.tile_batch(
                tf.transpose(self.encoder_output, perm=[1, 0, 2]), multiplier=self.beam_width)
            tiled_encoder_final_state = tf.contrib.seq2seq.tile_batch(self.encoder_state, multiplier=self.beam_width)
            tiled_seq_len = tf.contrib.seq2seq.tile_batch(self.X_len, multiplier=self.beam_width)
            attention_mechanism = tf.contrib.seq2seq.BahdanauAttention(
                self.num_hidden * 2, tiled_encoder_output, memory_sequence_length=tiled_seq_len, normalize=True)
            decoder_cell = tf.contrib.seq2seq.AttentionWrapper(decoder_cell, attention_mechanism,
                                                               attention_layer_size=self.num_hidden * 2)
            initial_state = decoder_cell.zero_state(dtype=tf.float32, batch_size=self.batch_size * self.beam_width)
            initial_state = initial_state.clone(cell_state=tiled_encoder_final_state)
            decoder = tf.contrib.seq2seq.BeamSearchDecoder(
                cell=decoder_cell,
                embedding=self.embeddings,
                start_tokens=tf.fill([self.batch_size], tf.constant(2)),
                end_token=tf.constant(3),
                initial_state=initial_state,
                beam_width=self.beam_width,
                output_layer=self.projection_layer
            )
            outputs, _, _ = tf.contrib.seq2seq.dynamic_decode(
                decoder, output_time_major=True, maximum_iterations=summary_max_len, scope=decoder_scope)
            self.prediction = tf.transpose(outputs.predicted_ids, perm=[1, 2, 0])

    with tf.name_scope("loss"):
        if not forward_only:
            crossent = tf.nn.sparse_softmax_cross_entropy_with_logits(
                logits=self.logits_reshape, labels=self.decoder_target)
            weights = tf.sequence_mask(self.decoder_len, summary_max_len, dtype=tf.float32)
            self.loss = tf.reduce_sum(crossent * weights / tf.to_float(self.batch_size))

            params = tf.trainable_variables()
            gradients = tf.gradients(self.loss, params)
            clipped_gradients, _ = tf.clip_by_global_norm(gradients, 5.0)
            optimizer = tf.train.AdamOptimizer(self.learning_rate)
            self.update = optimizer.apply_gradients(zip(clipped_gradients, params), global_step=self.global_step)

Training import time start = time.perf_counter() import tensorflow as tf import argparse import pickle import os

class args: pass

args.num_hidden=150 args.num_layers=2 args.beam_width=10 args.glove="store_true" args.embedding_size=300

args.learning_rate=1e-3 args.batch_size=64 args.num_epochs=10 args.keep_prob = 0.8

args.toy=False #"store_true"

args.with_model="store_true"

if not os.path.exists("saved_model"):

os.mkdir("saved_model")

else:

if args.with_model:

old_model_checkpoint_path = open('saved_model/', 'r')

old_model_checkpoint_path = "".join(["saved_model/",old_model_checkpoint_path.read().splitlines()[0].split('"')[1] ])

print("Building dictionary...") word_dict, reverse_dict, article_max_len, summary_max_len = build_dict("train", args.toy) print("Loading training dataset...") train_x, train_y = build_dataset("train", word_dict, article_max_len, summary_max_len, args.toy)

tf.reset_default_graph()

with tf.Session() as sess: model = Model(reverse_dict, article_max_len, summary_max_len, args) sess.run(tf.global_variables_initializer()) saver = tf.train.Saver(tf.global_variables()) if 'old_model_checkpoint_path' in globals(): print("Continuing from previous trained model:" , old_model_checkpoint_path , "...") saver.restore(sess, old_model_checkpoint_path )

batches = batch_iter(train_x, train_y, args.batch_size, args.num_epochs)
num_batches_per_epoch = (len(train_x) - 1) // args.batch_size + 1

print("\nIteration starts.")
print("Number of batches per epoch :", num_batches_per_epoch)
for batch_x, batch_y in batches:
    batch_x_len = list(map(lambda x: len([y for y in x if y != 0]), batch_x))
    batch_decoder_input = list(map(lambda x: [word_dict["<s>"]] + list(x), batch_y))
    batch_decoder_len = list(map(lambda x: len([y for y in x if y != 0]), batch_decoder_input))
    batch_decoder_output = list(map(lambda x: list(x) + [word_dict["</s>"]], batch_y))

    batch_decoder_input = list(
        map(lambda d: d + (summary_max_len - len(d)) * [word_dict["<padding>"]], batch_decoder_input))
    batch_decoder_output = list(
        map(lambda d: d + (summary_max_len - len(d)) * [word_dict["<padding>"]], batch_decoder_output))
    
    train_feed_dict = {
        model.batch_size: len(batch_x),
        model.X: batch_x,
        model.X_len: batch_x_len,
        model.decoder_input: batch_decoder_input,
        model.decoder_len: batch_decoder_len,
        model.decoder_target: batch_decoder_output
    }

    _, step, loss = sess.run([model.update, model.global_step, model.loss], feed_dict=train_feed_dict)

    if step % 1000 == 0:
        print("step {0}: loss = {1}".format(step, loss))

    if step % num_batches_per_epoch == 0:
        hours, rem = divmod(time.perf_counter() - start, 3600)
        minutes, seconds = divmod(rem, 60)
        saver.save(sess, "C:/Users/sensen/OneDrive - HERE Global B.V-/Desktop/NLP/Open source libraries/Text summarization", global_step=step)
        print(" Epoch {0}: Model is saved.".format(step // num_batches_per_epoch),
        "Elapsed: {:0>2}:{:0>2}:{:05.2f}".format(int(hours),int(minutes),seconds) , "\n")

I have converted the downloaded glove txt into pickle using the following code:

import pickle import numpy as np

f = open('C:/Users/sensen/OneDrive - HERE Global B.V-/Desktop/NLP/Open source libraries/Text summarization/glove.6B/glove.6B.300d.txt', 'r', encoding='UTF-8') g = open('glove.6B.300d_pickle', 'wb') word_dict = {} wordvec = [] for idx, line in enumerate(f.readlines()): word_split = line.split(' ') word = word_split[0] word_dict[word] = idx d = word_split[1:] d[-1] = d[-1][:-1] d = [float(e) for e in d] wordvec.append(d)

embedding = np.array(wordvec) pickling = {} pickling = {'embedding' : embedding, 'word_dict': word_dict} pickle.dump(pickling, g) f.close() g.close()

Can you help me solve the error?