python - Tensorflow: ValueError: Cannot feed value of shape (423,) for Tensor 'Placeholder:0', which has shape '(?, 423)'

Question

I'm a newbie to ML and learning TF through this tutorial -

In the following code, I can calculate epoch loss but not accuracy.

import tensorflow as tf
from wordsnlp import create_feature_sets_and_labels
import numpy as np
train_x,train_y,test_x,test_y = create_feature_sets_and_labels('pos.txt','neg.txt')
n_nodes_hl1 = 500


n_classes = 2

batch_size = 100

x = tf.placeholder('float',[None,len(train_x[0])])
y = tf.placeholder('float')

#(input_data*weights) + biases
def neural_network_model(data):
    hidden_1_layer = {'weights': tf.Variable(tf.random_normal([len(train_x[0]),n_nodes_hl1])),
                      'biases': tf.Variable(tf.random_normal([n_nodes_hl1]))}

    return output

def neural_network_model(data):
hidden_1_layer = {'weights': tf.Variable(tf.random_normal([len(train_x[0]),n_nodes_hl1])),
                  'biases': tf.Variable(tf.random_normal([n_nodes_hl1]))}

hidden_2_layer = {'weights': tf.Variable(tf.random_normal([n_nodes_hl1,n_nodes_hl2])),
                  'biases': tf.Variable(tf.random_normal([n_nodes_hl2]))}

hidden_3_layer = {'weights': tf.Variable(tf.random_normal([n_nodes_hl2,n_nodes_hl3])),
                  'biases': tf.Variable(tf.random_normal([n_nodes_hl3]))}

output_layer = {'weights': tf.Variable(tf.random_normal([n_nodes_hl3,n_classes])),
                  'biases': tf.Variable(tf.random_normal([n_classes]))}

l1= tf.add(tf.matmul(data, hidden_1_layer['weights']) , hidden_1_layer['biases'])
l1 = tf.nn.relu(l1)

l2= tf.add(tf.matmul(l1, hidden_2_layer['weights']) , hidden_2_layer['biases'])
l1 = tf.nn.relu(l2)

l3= tf.add(tf.matmul(l2, hidden_2_layer['weights']) , hidden_2_layer['biases'])
l1 = tf.nn.relu(l3)

output = tf.matmul(l3, output_layer['weights']) + output_layer['biases']

return output
def train_neural_network(x):
    prediction = neural_network_model(x)
    cost = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits(logits=prediction,labels=y))
    optimizer = tf.train.AdamOptimizer().minimize(cost)

    hm_epochs = 10

    with tf.Session() as sess:
        sess.run(tf.initialize_all_variables())

        for epoch in range(hm_epochs):
            epoch_loss=0
            i=0
            while i < len(train_x):
                start = i
                end = i + batch_size
                batch_x = np.array(train_x[start:end])
                batch_y = np.array(train_y[start:end])

                _,c = sess.run([optimizer,cost] , feed_dict = {x: batch_x , y : batch_y})
                epoch_loss+= c
                i+= batch_size
            print("Epoch",epoch , 'completed out of ' ,hm_epochs, ' loss: ', epoch_loss )



        correct = tf.equal(tf.argmax(prediction,1), tf.argmax(y,1))
        accuracy = tf.reduce_mean(tf.cast(correct, 'float'))
        print('Accuracy: ', accuracy.eval({x:test_x , y: test_y}))



train_neural_network(x)

The error which i'm getting for this code(I simplified) while i'm calculating accuracy is :

ValueError: Cannot feed value of shape (423,) for Tensor 'Placeholder:0', which has shape '(?, 423)'

Can you please point out what's the problem is? Thanks in advance.

Answer 1

First of all, your code is incomplete, check neural_network_model function.

Anyways the following code works. For now, I have just used one network layer, you can add more layers in your neural_network_model function. Making sure that n_classes and the size of output in neural_network_model function is same.

For now run the below code, and then later update neural_network_model function.

import tensorflow as tf
import numpy as np
import random
import nltk
from nltk.tokenize import word_tokenize
import numpy as np
import random
import pickle
from collections import Counter
from nltk.stem import WordNetLemmatizer

lemmatizer = WordNetLemmatizer()
hm_lines = 100000

def create_lexicon(pos,neg):
    lexicon = []
    with open(pos,'r') as f:
        contents = f.readlines()
        for l in contents[:hm_lines]:
            all_words = word_tokenize(l)
            lexicon += list(all_words)

    with open(neg,'r') as f:
        contents = f.readlines()
        for l in contents[:hm_lines]:
            all_words = word_tokenize(l)
            lexicon += list(all_words)

    lexicon = [lemmatizer.lemmatize(i) for i in lexicon]
    w_counts = Counter(lexicon)
    l2 = []
    for w in w_counts:
        #print(w_counts[w])
        if 1000 > w_counts[w] > 50:
            l2.append(w)
    print(len(l2))
    return l2


def sample_handling(sample,lexicon,classification):
    featureset = []
    with open(sample,'r') as f:
        contents = f.readlines()
        for l in contents[:hm_lines]:
            current_words = word_tokenize(l.lower())
            current_words = [lemmatizer.lemmatize(i) for i in current_words]
            features = np.zeros(len(lexicon))
            for word in current_words:
                if word.lower() in lexicon:
                    index_value = lexicon.index(word.lower())
                    features[index_value] += 1
            features = list(features)
            featureset.append([features,classification])
    return featureset

def create_feature_sets_and_labels(pos,neg,test_size = 0.1):
    lexicon = create_lexicon(pos,neg)
    features = []
    features += sample_handling('pos.txt',lexicon,[1,0])
    features += sample_handling('neg.txt',lexicon,[0,1])
    random.shuffle(features)
    features = np.array(features)

    testing_size = int(test_size*len(features))

    train_x = list(features[:,0][:-testing_size])
    train_y = list(features[:,1][:-testing_size])
    test_x = list(features[:,0][-testing_size:])
    test_y = list(features[:,1][-testing_size:])

    return train_x,train_y,test_x,test_y

train_x,train_y,test_x,test_y = create_feature_sets_and_labels('pos.txt','neg.txt')
n_nodes_hl1 = 2


n_classes = 2

batch_size = 100

x = tf.placeholder('float',[None,len(train_x[0])])
y = tf.placeholder('float')

#(input_data*weights) + biases
def neural_network_model(data):
    hidden_1_layer = {'weights': tf.Variable(tf.random_normal([len(train_x[0]),n_nodes_hl1])),
                      'biases': tf.Variable(tf.random_normal([n_nodes_hl1]))}
    output = tf.matmul(data,hidden_1_layer['weights']) + hidden_1_layer['biases']
    return output




def train_neural_network(x):
    prediction = neural_network_model(x)
    cost = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits(logits=prediction,labels=y))
    optimizer = tf.train.AdamOptimizer().minimize(cost)

    hm_epochs = 1

    with tf.Session() as sess:
        sess.run(tf.initialize_all_variables())

        for epoch in range(hm_epochs):
            epoch_loss=0
            i=0
            while i < len(train_x):
                start = i
                end = i + batch_size
                batch_x = np.array(train_x[start:end])
                batch_y = np.array(train_y[start:end])

                _,c = sess.run([optimizer,cost] , feed_dict = {x: batch_x , y : batch_y})
                epoch_loss+= c
                i+= batch_size
            print("Epoch",epoch , 'completed out of ' ,hm_epochs, ' loss: ', epoch_loss )



        correct = tf.equal(tf.argmax(prediction,1), tf.argmax(y,1))
        accuracy = tf.reduce_mean(tf.cast(correct, 'float'))
        print('Accuracy: ', accuracy.eval({x:test_x , y: test_y}))

train_neural_network(x)

Note: The code has flaws at other levels, but that is not the point of this question, I took the missing functions from the place you pointed

Edit 2:

I guess I should not be encouraging you with your silly mistakes, this is last time I am fixing things. You have again just messed up in the same function. You must first go through your code completely before posting it to stack-overflow, so that you are sure you are asking the correct problem you encountering, and not a side silly mistake.

import tensorflow as tf
import numpy as np
import random
import nltk
from nltk.tokenize import word_tokenize
import numpy as np
import random
import pickle
from collections import Counter
from nltk.stem import WordNetLemmatizer

lemmatizer = WordNetLemmatizer()
hm_lines = 100000

def create_lexicon(pos,neg):
    lexicon = []
    with open(pos,'r') as f:
        contents = f.readlines()
        for l in contents[:hm_lines]:
            all_words = word_tokenize(l)
            lexicon += list(all_words)

    with open(neg,'r') as f:
        contents = f.readlines()
        for l in contents[:hm_lines]:
            all_words = word_tokenize(l)
            lexicon += list(all_words)

    lexicon = [lemmatizer.lemmatize(i) for i in lexicon]
    w_counts = Counter(lexicon)
    l2 = []
    for w in w_counts:
        #print(w_counts[w])
        if 1000 > w_counts[w] > 50:
            l2.append(w)
    print(len(l2))
    return l2


def sample_handling(sample,lexicon,classification):
    featureset = []
    with open(sample,'r') as f:
        contents = f.readlines()
        for l in contents[:hm_lines]:
            current_words = word_tokenize(l.lower())
            current_words = [lemmatizer.lemmatize(i) for i in current_words]
            features = np.zeros(len(lexicon))
            for word in current_words:
                if word.lower() in lexicon:
                    index_value = lexicon.index(word.lower())
                    features[index_value] += 1
            features = list(features)
            featureset.append([features,classification])
    return featureset

def create_feature_sets_and_labels(pos,neg,test_size = 0.1):
    lexicon = create_lexicon(pos,neg)
    features = []
    features += sample_handling('pos.txt',lexicon,[1,0])
    features += sample_handling('neg.txt',lexicon,[0,1])
    random.shuffle(features)
    features = np.array(features)

    testing_size = int(test_size*len(features))

    train_x = list(features[:,0][:-testing_size])
    train_y = list(features[:,1][:-testing_size])
    test_x = list(features[:,0][-testing_size:])
    test_y = list(features[:,1][-testing_size:])

    return train_x,train_y,test_x,test_y

train_x,train_y,test_x,test_y = create_feature_sets_and_labels('pos.txt','neg.txt')
n_nodes_hl1 = 2


n_classes = 2

batch_size = 100

x = tf.placeholder('float',[None,len(train_x[0])])
y = tf.placeholder('float')

import tensorflow as tf

import numpy as np
train_x,train_y,test_x,test_y = create_feature_sets_and_labels('pos.txt','neg.txt')
n_nodes_hl1 = 4
n_nodes_hl2 = 3
n_nodes_hl3 = 2

n_classes = 2

batch_size = 100

x = tf.placeholder('float',[None,len(train_x[0])])
y = tf.placeholder('float')

def neural_network_model(data):
    hidden_1_layer = {'weights': tf.Variable(tf.random_normal([len(train_x[0]),n_nodes_hl1])),
                      'biases': tf.Variable(tf.random_normal([n_nodes_hl1]))}

    hidden_2_layer = {'weights': tf.Variable(tf.random_normal([n_nodes_hl1,n_nodes_hl2])),
                      'biases': tf.Variable(tf.random_normal([n_nodes_hl2]))}

    hidden_3_layer = {'weights': tf.Variable(tf.random_normal([n_nodes_hl2,n_nodes_hl3])),
                      'biases': tf.Variable(tf.random_normal([n_nodes_hl3]))}

    output_layer = {'weights': tf.Variable(tf.random_normal([n_nodes_hl3,n_classes])),
                      'biases': tf.Variable(tf.random_normal([n_classes]))}

    l1= tf.add(tf.matmul(data, hidden_1_layer['weights']) , hidden_1_layer['biases'])
    l1 = tf.nn.relu(l1)

    l2= tf.add(tf.matmul(l1, hidden_2_layer['weights']) , hidden_2_layer['biases'])
    l2 = tf.nn.relu(l2)

    l3= tf.add(tf.matmul(l2, hidden_3_layer['weights']) , hidden_3_layer['biases'])
    l3 = tf.nn.relu(l3)

    output = tf.matmul(l3, output_layer['weights']) + output_layer['biases']
    return output

def train_neural_network(x):
    prediction = neural_network_model(x)
    cost = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits(logits=prediction,labels=y))
    optimizer = tf.train.AdamOptimizer().minimize(cost)

    hm_epochs = 10

    with tf.Session() as sess:
        sess.run(tf.initialize_all_variables())

        for epoch in range(hm_epochs):
            epoch_loss=0
            i=0
            while i < len(train_x):
                start = i
                end = i + batch_size
                batch_x = np.array(train_x[start:end])
                batch_y = np.array(train_y[start:end])

                _,c = sess.run([optimizer,cost] , feed_dict = {x: batch_x , y : batch_y})
                epoch_loss+= c
                i+= batch_size
            print("Epoch",epoch , 'completed out of ' ,hm_epochs, ' loss: ', epoch_loss )



        correct = tf.equal(tf.argmax(prediction,1), tf.argmax(y,1))
        accuracy = tf.reduce_mean(tf.cast(correct, 'float'))
        print('Accuracy: ', accuracy.eval({x:test_x , y: test_y}))



train_neural_network(x)