I'm using a LSTM for multi class text classification. I tried a lot of solutions to the problem mentioned in the header but I cant get it working. Code :
vocab_size = 5000
embedding_dim = 200
max_length = 200 #try 150 next time
trunc_type = 'post'
padding_type = 'post'
oov_tok = '<OOV>'
my_file = open("C:\\Users\\Ashish\\Desktop\\pr2_data\\train.txt", "r", encoding="utf8")
content = my_file.read()
articles = content.split("\n") #articles is a list of training articles
my_file.close()
my_file = open("C:\\Users\\Ashish\\Desktop\\pr2_data\\train.labels", "r", encoding="utf8")
content = my_file.read()
labels = content.split("\n") #labels is a list of training labels
my_file.close()
train_articles=[]
for i in articles:
article = i
for word in STOPWORDS:
token = ' ' + word + ' '
article = article.replace(token, ' ')
article = article.replace(' ', ' ')
train_articles.append(article)
train_labels=labels
#PREP VALIDATION SET
my_file = open("C:\\Users\\Ashish\\Desktop\\pr2_data\\val.txt", "r", encoding="utf8")
content = my_file.read()
val_articles = content.split("\n")
my_file.close()
validation_articles=[]
for i in val_articles:
article = i
for word in STOPWORDS:
token = ' ' + word + ' '
article = article.replace(token, ' ')
article = article.replace(' ', ' ')
validation_articles.append(article)
my_file = open("C:\\Users\\Ashish\\Desktop\\pr2_data\\val.labels", "r", encoding="utf8")
content = my_file.read()
validation_labels = content.split("\n")
my_file.close()
labels=train_labels+validation_labels
articles=train_articles+validation_articles
####error free till here
#####train_sequences
tokenizer = Tokenizer(num_words = vocab_size, oov_token=oov_tok)
tokenizer.fit_on_texts(train_articles)
word_index = tokenizer.word_index
train_sequences = tokenizer.texts_to_sequences(train_articles)
train_padded = pad_sequences(train_sequences, maxlen=max_length, padding=padding_type, truncating=trunc_type)
validation_sequences = tokenizer.texts_to_sequences(validation_articles)
validation_padded = pad_sequences(validation_sequences, maxlen=max_length, padding=padding_type, truncating=trunc_type)
label_tokenizer = Tokenizer()
label_tokenizer.fit_on_texts(labels)
training_label_seq = np.array(label_tokenizer.texts_to_sequences(train_labels))
validation_label_seq = np.array(label_tokenizer.texts_to_sequences(validation_labels))
model = tf.keras.Sequential([
# Add an Embedding layer expecting input vocab of size 5000, and output embedding dimension of size 64 we set at the top
tf.keras.layers.Embedding(vocab_size, embedding_dim),
tf.keras.layers.Bidirectional(tf.keras.layers.LSTM(embedding_dim)),
# tf.keras.layers.Bidirectional(tf.keras.layers.LSTM(32)),
# use ReLU in place of tanh function since they are very good alternatives of each other.
tf.keras.layers.Dense(embedding_dim, activation='relu'),
# Add a Dense layer with 6 units and softmax activation.
# When we have multiple outputs, softmax convert outputs layers into a probability distribution.
tf.keras.layers.Dense(12, activation='softmax')
])
model.summary()
model.compile(loss='sparse_categorical_crossentropy', optimizer='adam', metrics=['accuracy'])
num_epochs = 10
history = model.fit(train_padded, training_label_seq, epochs=num_epochs, validation_data=(validation_padded, validation_label_seq), verbose=2)
The error is as follows:
File "aa.py", line 97, in <module>
history = model.fit(train_padded, training_label_seq, epochs=num_epochs, validation_data=(validation_padded, validation_label_seq), verbose=2)
File "C:\Users\Ashish\AppData\Local\Programs\Python\Python38\lib\site-packages\tensorflow\python\framework\constant_op.py", line 98, in convert_to_eager_tensor
return ops.EagerTensor(value, ctx.device_name, dtype)
ValueError: Failed to convert a NumPy array to a Tensor (Unsupported object type list).
