File size: 3,345 Bytes
b9c7def a1cd320 b0e9893 a1cd320 b0e9893 a1cd320 15fd446 a1cd320 82d14d8 a1cd320 15fd446 a1cd320 15fd446 a1cd320 15fd446 a1cd320 b47601b a1cd320 b47601b a1cd320 b47601b a1cd320 b9c7def 0dc1348 b9c7def |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 |
import gradio as gr
from datasets import load_dataset
from tensorflow.keras.preprocessing.text import Tokenizer
from tensorflow.keras.preprocessing.sequence import pad_sequences
import numpy as np
import tensorflow as tf
import random
import spaces
maxlen = 50
def get_sequences(tokenizer, tweets):
sequences = tokenizer.texts_to_sequences(tweets)
padded = pad_sequences(sequences, truncating='post', padding='post', maxlen=maxlen)
return padded
def get_label(idx):
if idx == 0: return 'sadness'
elif idx == 1: return 'joy'
elif idx == 2: return 'love'
elif idx == 3: return 'anger'
elif idx == 4: return 'fear'
else: return 'surprise'
def get_tweet(data):
tweets = [x['text'] for x in data]
labels = [get_label(x['label']) for x in data]
return tweets, labels
def get_train_val_test_sets():
dataset = load_dataset("dair-ai/emotion")
train = dataset['train']
val = dataset['validation']
test = dataset['test']
return train, val, test
train, val, test = get_train_val_test_sets()
tweets, labels = get_tweet(train)
tokenizer = Tokenizer(num_words=10000,oov_token='<UNK>')
tokenizer.fit_on_texts(tweets)
padded_train_seq = get_sequences(tokenizer, tweets)
classes = set(labels)
class_to_index = dict((c,i) for i,c in enumerate(classes))
index_to_class = dict((v,k) for k,v in class_to_index.items())
names_to_ids = lambda labels: np.array([class_to_index.get(x) for x in labels])
train_labels = names_to_ids(labels)
@spaces.GPU(duration=125)
def load_model():
model = tf.keras.models.Sequential([
tf.keras.layers.Embedding(10000, 16, input_length=maxlen),
tf.keras.layers.Bidirectional(tf.keras.layers.LSTM(20, return_sequences=True)),
tf.keras.layers.Bidirectional(tf.keras.layers.LSTM(20)),
tf.keras.layers.Dense(6, activation='softmax')
])
model.compile(
loss='sparse_categorical_crossentropy',
optimizer='adam',
metrics=['accuracy']
)
print(model.summary())
val_tweets, val_labels = get_tweet(val)
val_seq = get_sequences(tokenizer, val_tweets)
val_labels = names_to_ids(val_labels)
h = model.fit(
padded_train_seq, train_labels, validation_data=(val_seq, val_labels),
epochs=8,
callbacks=[
tf.keras.callbacks.EarlyStopping(monitor='val_accuracy', patience=2)
]
)
# test_tweets, test_labels = get_tweet(test)
# test_seq = get_sequences(tokenizer, test_tweets)
# test_labels = names_to_ids(test_labels)
# _ = model.evaluate(test_seq, test_labels)
# i = random.randint(0, len(test_labels) - 1)
# print('Sentence:', test_tweets[i])
# print('Emotion:', index_to_class[test_labels[i]])
# p = model.predict(np.expand_dims(test_seq[i],axis=0))[0]
# pred_class = index_to_class[np.argmax(p).astype('uint8')]
# print('Predicted Emotion:', pred_class)
# preds = (model.predict(test_seq) > 0.5).astype("int32")
# print(preds)
return model
model = load_model()
def predict(tweet):
print("ENTERED", tweet)
seq = get_sequences(tokenizer, [tweet])
print(seq)
p = model.predict(np.expand_dims(seq[0],axis=0))[0]
print(p)
return index_to_class[np.argmax(p).astype('uint8')]
demo = gr.Interface(fn=predict, inputs="text", outputs="text")
demo.launch()
|