我是一个机器学习新手，正在通过这个教程学习TensorFlow –
在下面的代码中，我可以计算epoch损失，但无法计算准确率。
import tensorflow as tffrom wordsnlp import create_feature_sets_and_labelsimport numpy as nptrain_x,train_y,test_x,test_y = create_feature_sets_and_labels('pos.txt','neg.txt')n_nodes_hl1 = 500n_classes = 2batch_size = 100x = tf.placeholder('float',[None,len(train_x[0])])y = tf.placeholder('float')#(input_data*weights) + biasesdef 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 outputdef 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 outputdef 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)当我计算准确率时，代码（我已简化）出现了以下错误：
ValueError: 无法为形状为(423,)的张量’Placeholder:0’提供值，该张量形状为'(?, 423)’
您能指出问题出在哪里吗？提前感谢您。
回答：
首先，您的代码不完整，请检查neural_network_model函数。
无论如何，下面的代码可以运行。目前我只使用了一个网络层，您可以在neural_network_model函数中添加更多层。确保n_classes和neural_network_model函数中output的大小相同。
现在先运行下面的代码，然后再更新neural_network_model函数。
import tensorflow as tfimport numpy as npimport randomimport nltkfrom nltk.tokenize import word_tokenizeimport numpy as npimport randomimport picklefrom collections import Counterfrom nltk.stem import WordNetLemmatizerlemmatizer = WordNetLemmatizer()hm_lines = 100000def 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 l2def 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 featuresetdef 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_ytrain_x,train_y,test_x,test_y = create_feature_sets_and_labels('pos.txt','neg.txt')n_nodes_hl1 = 2n_classes = 2batch_size = 100x = tf.placeholder('float',[None,len(train_x[0])])y = tf.placeholder('float')#(input_data*weights) + biasesdef 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 outputdef 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)注意：代码在其他层面上存在缺陷，但这不是本问题的重点，我从您指出的位置获取了缺失的函数
编辑2：
我想我不应该鼓励你犯这些愚蠢的错误，这是我最后一次修复这些问题。你又一次在同一个函数中搞砸了。你在发布到Stack Overflow之前，必须完全检查你的代码，这样你才能确定你提出的问题是正确的，而不是因为一些愚蠢的小错误。
