CODEWITHSUNDEEP
tensorflowkeras
deadshot
deadshot

Reputation: 9061

ValueError: Input 0 is incompatible with layer conv1d_1: expected ndim=3, found ndim=2

When I try to give Elmo embedding layer output to conv1d layer input it giving the error

ValueError: Input 0 is incompatible with layer conv1d_1: expected ndim=3, found ndim=2

I want to add a convolution layer from the output of the Elmo embedding layer

import tensorflow as tf
import tensorflow_hub as hub
import keras.backend as K
from keras import Model
from keras.layers import Input, Lambda, Conv1D, Flatten, Dense
from keras.utils import to_categorical
from sklearn.preprocessing import LabelEncoder
import pandas as pd
from sklearn.model_selection import train_test_split

df = pd.read_csv("/home/raju/Desktop/spam.csv", encoding='latin-1')
X = df['v2']
Y = df['v1']

le = LabelEncoder()
le.fit(Y)

Y = le.transform(Y)
Y = to_categorical(Y)

X_train, X_test, y_train, y_test = train_test_split(X, Y, test_size=0.25)

elmo = hub.Module('/home/raju/models/elmo')


def embeddings(x):
    return elmo(tf.squeeze(tf.cast(x, dtype=tf.string)), signature='default', as_dict=True)['default']


input_layer = Input(shape=(1,), dtype=tf.string)
embed_layer = Lambda(embeddings, output_shape=(1024,))(input_layer) 
conv_layer = Conv1D(4, 2, activation='relu')(embed_layer)
fcc_layer = Flatten()(conv_layer)
output_layer = Dense(2, activation='softmax')(fcc_layer)

model = Model(inputs=[input_layer], outputs=output_layer)

Upvotes: 1

Views: 1767

Answers (1)

sdcbr
sdcbr

Reputation: 7129

A Conv1D layer expects input of the shape (batch, steps, channels). The channels dimension is missing in your case, and you need to include it even if it is equal to 1. So the output shape of your elmo module should be (1024, 1) (this does not include the batch size). You can add a dimension to the output of the elmo module with tf.expand_dims(x, axis=-1).

Upvotes: 2

Related Questions