Sequential Model incompatible with layer - machine-learning

Question

I've recently updated my project to include more intents for my NLU chatbot. I retrained the model. However, when I make an input into the program I receive an error message saying
File "C:\Users\jiann\ChatBot - Copy\chatbot.py", line 39, in predict_clas
s
res = model.predict(np.array([bow]))[0]
File "c:\users\jiann\appdata\local\programs\python\python39\lib\site-pack
ages\keras\utils\traceback_utils.py", line 67, in error_handler
raise e.with_traceback(filtered_tb) from None
File "c:\users\jiann\appdata\local\programs\python\python39\lib\site-pack
ages\tensorflow\python\framework\func_graph.py", line 1147, in autograph_ha
ndler
raise e.ag_error_metadata.to_exception(e)
ValueError: in user code:
File "c:\users\jiann\appdata\local\programs\python\python39\lib\site-pa
ckages\keras\engine\training.py", line 1801, in predict_function *
return step_function(self, iterator)
File "c:\users\jiann\appdata\local\programs\python\python39\lib\site-pa
ckages\keras\engine\training.py", line 1790, in step_function **
outputs = model.distribute_strategy.run(run_step, args=(data,))
File "c:\users\jiann\appdata\local\programs\python\python39\lib\site-pa
ckages\keras\engine\training.py", line 1783, in run_step **
outputs = model.predict_step(data)
File "c:\users\jiann\appdata\local\programs\python\python39\lib\site-pa
ckages\keras\engine\training.py", line 1751, in predict_step
return self(x, training=False)
File "c:\users\jiann\appdata\local\programs\python\python39\lib\site-pa
ckages\keras\utils\traceback_utils.py", line 67, in error_handler
raise e.with_traceback(filtered_tb) from None
ckages\keras\engine\input_spec.py", line 264, in assert_input_compatibilityckages\keras\engine\input_spec.py", line 264, in assert_input_compatibilityckage
raise ValueError(f'Input {input_index} of layer "{layer_name}" is ' raise ValueError(f'Input {input_index} of layer "{layer_name}" is '
ValueError: Input 0 of layer "sequential" is incompatible with the laye
r: expected shape=(None, 9), found shape=(None, 40)
This error only pops up when I include more than one Intent. Below I've include the relevant code for the Sequential model and the Intents:
Intents.json:
{"intents": [
{"tag": "greeting",
"patterns": ["Hi", "How are you", "Is anyone there?", "Hello", "Good day", "Whats up", "Hey", "greetings"],
"responses": ["Hello!", "Good to see you again!", "Hi there, how can I help?"],
"context_set": ""
},
{"tag": "goodbye",
"patterns": ["cya", "See you later", "Goodbye", "I am Leaving", "Have a Good day", "bye", "cao", "see ya"],
"responses": ["Sad to see you go :(", "Talk to you later", "Goodbye!"],
"context_set": ""
},
{"tag": "stocks",
"patterns": ["what stocks do I own?", "how are my shares?", "what companies am I investing in?", "what am I doing in the markets?"],
"responses": ["You own the following shares: ABBV, AAPL, FB, NVDA and an ETF of the S&P 500 Index!"],
"context_set": ""
}
]
}
training.py:
import random
import json
import pickle
import numpy as np
import nltk
from keras.layers import Dense, Dropout
from keras.models import Sequential
from keras.optimizer_v2.gradient_descent import SGD
nltk.download('punkt')
nltk.download('wordnet')
nltk.download('omw-1.4')
# Lemmatizer uses stem of a word instead of conjugate (performance purposes)
from nltk.stem import WordNetLemmatizer
from tensorflow import keras
# from tensorflow.keras.models import Sequential
# from tensorflow.keras.layers i
# mport Dense, Activation, Dropout
# from tensorflow.keras.optimizers import SGD
lemmatizer = WordNetLemmatizer()
# Reading json file, pass to load function, get json object dictionary
intents = json.loads(open('intents.json').read())
words = []
classes = []
documents = []
# Characters that you won't pay attention to
ignore_letters = ['?', '!', '.', ',']
# Splits each pattern entry into individual words
for intent in intents['intents']:
for pattern in intent['patterns']:
word_list = nltk.word_tokenize(pattern)
words.extend(word_list)
#Wordlist belongs to specific tag
documents.append((word_list, intent['tag']))
if intent['tag'] not in classes:
classes.append(intent['tag'])
print(documents)
#lemmatizes word inf word list if it is not ignored
words = [lemmatizer.lemmatize(word) for word in words if word not in ignore_letters]
#Set Eliminates duplicate words
words = sorted(set(words))
classes = sorted(set(classes))
#Save the words in file
pickle.dump(words,open('words.pkl','wb'))
#Save classes in file
pickle.dump(classes,open('classes.pkl','wb'))
#CREATING THE TRAINING DATA
#Set individual word values to 0 or 1 depending on whether it occurs
training = []
output_empty = [0] * len(classes)
for document in documents:
bag = []
word_patterns = document[0]
word_patterns = [lemmatizer.lemmatize(word.lower()) for word in word_patterns]
for word in words:#checks to see if word is in pattern
bag.append(1) if word in word_patterns else bag.append(0)
output_row = list(output_empty)
#want to know class at index 1, want to know index,
# add class to oupt_row to 1
output_row[classes.index(document[1])] = 1
training.append([bag, output_row])
#shuffle the data
random.shuffle(training)
#turn into numpy array
training = np.array(training)
#split into x and y values, Features & Labels
train_x =list(training[:,0])
train_y = list(training[:,1])
#Start building Neural Network Model
model = Sequential()
model.add(Dense(128, input_shape=(len(train_x[0]),), activation='relu'))
model.add(Dropout(0.5))
model.add(Dense(64, activation='relu'))
model.add(Dropout(0.5))
model.add(Dense(len(train_y[0]),activation='softmax'))
sgd = SGD(lr=0.01, decay=1e-6, momentum=0.9, nesterov=True)
model.compile(loss='categorical_crossentropy', optimizer=sgd, metrics=['accuracy'])
hist = model.fit(np.array(train_x), np.array(train_y), epochs=200, batch_size=5, verbose=1)
model.save('chatbotmodel.h5',hist)
print('done')
chatbot.py:
import random
import pickle
import numpy as np
import nltk
import os
os.environ['TF_CPP_MIN_LOG_LEVEL'] = '2'
from nltk.stem import WordNetLemmatizer
from keras.models import load_model
lemmatizer = WordNetLemmatizer()
words = pickle.load(open('words.pkl', 'rb'))
classes = pickle.load(open('classes.pkl', 'rb'))
model = load_model('chatbot_model.model')
print(classes)
def clean_up_sentence(sentence):
sentence_words = nltk.word_tokenize(sentence)
sentence_words = [lemmatizer.lemmatize(word) for word in sentence_words]
return sentence_words
def bag_of_words(sentence):
sentence_words = clean_up_sentence(sentence)
bag = [0] * len(words)
for w in sentence_words:
for i, word in enumerate(words):
if word == w:
bag[i] = 1
return np.array(bag)
def predict_class(sentence):
bow = bag_of_words(sentence)
res = model.predict(np.array([bow]))[0]
# allows for certain uncertainty.
# If Uncertainty is too high it won't allow to be taken into account
ERROR_THRESHOLD = 0.25
results = [[i, r] for i, r in enumerate(res) if r > ERROR_THRESHOLD]
results.sort(key=lambda x: x[1], reverse=True)
return_list = []
for r in results:
return_list.append({'intent': classes[r[0]], 'probability': str(r[1])})
return return_list
def get_response(intents_list, intents_json):
tag = intents_list[0]['intent']
list_of_intents = intents_json['intents']
for i in list_of_intents:
if i['tag'] == tag:
result = random.choice(i['responses'])
break
return result
print("Go! Bot is running!")
If I had to take a guess, it would be something wrong with the shape. I'm just not sure how to fix this.

Answer 1

There seems to be a mismatch between the input_shape of your model and the training sample(s) you are providing. I believe the issue stems from these two lines:
model.add(Dense(128, input_shape=(len(train_x[0]),), activation='relu'))
and,
res = model.predict(np.array([bow]))[0]
Depending on what value is returned by len(train_x[0]), calling model.predict() on np.array[bow] may not work if np.array[bow] does not match the input shape specified. Check out this answer for an in-depth explanation of how the various Keras inputs work.