Блог

Я пытаюсь создать разговорного бота, используя функции ML, и я написал этот код, просматривая учебник на YouTube, но я получаю эту неизвестную ошибку, которая просит меня передать объект в «пользовательские объекты», и я понятия не имею, что делать. Было бы здорово, если бы кто-нибудь мог мне помочь..

Это мой код:

 import random as rd
import json
import pickle
import numpy as np

import nltk
from nltk.stem import WordNetLemmatizer

from tensorflow.keras.models import Sequential
from tensorflow.keras.layers import Dense, Activation, Dropout
from tensorflow.keras.optimizers import SGD

lemmatizer = WordNetLemmatizer()

intents = json.loads(open('train.json').read())

words =[]
classes =[]
documents =[]
ignore_letters = ['!','?','.',',']

for intent in intents['intents']:
    for pattern in intent["patterns"]:
        word_list = nltk.word_tokenize(pattern)
        words.extend(word_list)
        documents.append((word_list,intent['tag']))
        if intent['tag'] not in classes:
            classes.append(intent['tag'])

words = [lemmatizer.lemmatize(word) for word in words if word not in ignore_letters]
words = sorted(set(words))

classes = sorted(set(classes))

pickle.dump(words, open('words.pkl', 'wb'))
pickle.dump(classes, open('classes.pkl','wb'))

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:
        bag.append(1) if word in word_patterns else bag.append(0)

    output_row = list(output_empty)
    output_row[classes.index(document[1])] = 1
    training.append([bag, output_row])

rd.shuffle(training)
training = np.array(training)

train_x = list(training[:,0])
train_y = list(training[:,1])

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, 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=True )
model.save('chatbot_model.h5', hist)
print('done')
 

и когда я запускаю его, он возвращается

 2021-06-03 23:29:11.692757: W tensorflow/stream_executor/platform/default/dso_loader.cc:64] Could not load dynamic library 'cudart64_110.dll'; dlerror: cudart64_110.dll not found
2021-06-03 23:29:11.692947: I tensorflow/stream_executor/cuda/cudart_stub.cc:29] Ignore above cudart dlerror if you do not have a GPU set up on your machine.
c:Speechtotexttraining.py:53: VisibleDeprecationWarning: Creating an ndarray from ragged nested sequences (which is a list-or-tuple of lists-or-tuples-or ndarrays with different lengths or shapes) is deprecated. If you meant to do this, you must specify 'dtype=object' when creating the ndarray
  training = np.array(training)
2021-06-03 23:29:14.418464: W tensorflow/stream_executor/platform/default/dso_loader.cc:64] Could not load dynamic library 'nvcuda.dll'; dlerror: nvcuda.dll not found
2021-06-03 23:29:14.418804: W tensorflow/stream_executor/cuda/cuda_driver.cc:326] failed call to cuInit: UNKNOWN ERROR (303)
2021-06-03 23:29:14.427096: I tensorflow/stream_executor/cuda/cuda_diagnostics.cc:169] retrieving CUDA diagnostic information for host: DESKTOP-LEKVIN8
2021-06-03 23:29:14.427515: I tensorflow/stream_executor/cuda/cuda_diagnostics.cc:176] hostname: DESKTOP-LEKVIN8
2021-06-03 23:29:14.428318: I tensorflow/core/platform/cpu_feature_guard.cc:142] This TensorFlow binary is optimized with oneAPI Deep Neural Network Library (oneDNN) to use the following CPU instructions in performance-critical operations:  AVX AVX2
To enable them in other operations, rebuild TensorFlow with the appropriate compiler flags.
2021-06-03 23:29:14.523825: I tensorflow/compiler/mlir/mlir_graph_optimization_pass.cc:176] None of the MLIR Optimization Passes are enabled (registered 2)
Epoch 1/200
Traceback (most recent call last):
  File "c:Speechtotexttraining.py", line 68, in <module>
    hist=model.fit(np.array(train_x), np.array(train_y), epochs=200, batch_size=5, verbose=True )
  File "C:UsersanishAppDataRoamingPythonPython39site-packagestensorflowpythonkerasenginetraining.py", line 1183, in fit
    tmp_logs = self.train_function(iterator)
  File "C:UsersanishAppDataRoamingPythonPython39site-packagestensorflowpythoneagerdef_function.py", line 889, in __call__
    result = self._call(*args, **kwds)
  File "C:UsersanishAppDataRoamingPythonPython39site-packagestensorflowpythoneagerdef_function.py", line 933, in _call
    self._initialize(args, kwds, add_initializers_to=initializers)
  File "C:UsersanishAppDataRoamingPythonPython39site-packagestensorflowpythoneagerdef_function.py", line 763, in _initialize
    self._stateful_fn._get_concrete_function_internal_garbage_collected(  # pylint: disable=protected-access
  File "C:UsersanishAppDataRoamingPythonPython39site-packagestensorflowpythoneagerfunction.py", line 3050, in _get_concrete_function_internal_garbage_collected
    graph_function, _ = self._maybe_define_function(args, kwargs)
  File "C:UsersanishAppDataRoamingPythonPython39site-packagestensorflowpythoneagerfunction.py", line 3444, in _maybe_define_function
    graph_function = self._create_graph_function(args, kwargs)
  File "C:UsersanishAppDataRoamingPythonPython39site-packagestensorflowpythoneagerfunction.py", line 3279, in _create_graph_function
    func_graph_module.func_graph_from_py_func(
  File "C:UsersanishAppDataRoamingPythonPython39site-packagestensorflowpythonframeworkfunc_graph.py", line 999, in func_graph_from_py_func
    func_outputs = python_func(*func_args, **func_kwargs)
  File "C:UsersanishAppDataRoamingPythonPython39site-packagestensorflowpythoneagerdef_function.py", line 672, in wrapped_fn
    out = weak_wrapped_fn().__wrapped__(*args, **kwds)
  File "C:UsersanishAppDataRoamingPythonPython39site-packagestensorflowpythonframeworkfunc_graph.py", line 986, in wrapper
    raise e.ag_error_metadata.to_exception(e)
ValueError: in user code:

    C:UsersanishAppDataRoamingPythonPython39site-packagestensorflowpythonkerasenginetraining.py:855 train_function  *
        return step_function(self, iterator)
    C:UsersanishAppDataRoamingPythonPython39site-packagestensorflowpythonkerasenginetraining.py:845 step_function  **
        outputs = model.distribute_strategy.run(run_step, args=(data,))
    C:UsersanishAppDataRoamingPythonPython39site-packagestensorflowpythondistributedistribute_lib.py:1285 run
        return self._extended.call_for_each_replica(fn, args=args, kwargs=kwargs)
    C:UsersanishAppDataRoamingPythonPython39site-packagestensorflowpythondistributedistribute_lib.py:2833 call_for_each_replica
        return self._call_for_each_replica(fn, args, kwargs)
    C:UsersanishAppDataRoamingPythonPython39site-packagestensorflowpythondistributedistribute_lib.py:3608 _call_for_each_replica
        return fn(*args, **kwargs)
    C:UsersanishAppDataRoamingPythonPython39site-packagestensorflowpythonkerasenginetraining.py:838 run_step  **
        outputs = model.train_step(data)
    C:UsersanishAppDataRoamingPythonPython39site-packagestensorflowpythonkerasenginetraining.py:796 train_step
        loss = self.compiled_loss(
    C:UsersanishAppDataRoamingPythonPython39site-packagestensorflowpythonkerasenginecompile_utils.py:187 __call__
        self.build(y_pred)
    C:UsersanishAppDataRoamingPythonPython39site-packagestensorflowpythonkerasenginecompile_utils.py:136 build
        self._losses = nest.map_structure(self._get_loss_object, self._losses)
    C:UsersanishAppDataRoamingPythonPython39site-packagestensorflowpythonutilnest.py:867 map_structure
        structure[0], [func(*x) for x in entries],
    C:UsersanishAppDataRoamingPythonPython39site-packagestensorflowpythonutilnest.py:867 <listcomp>
        structure[0], [func(*x) for x in entries],
    C:UsersanishAppDataRoamingPythonPython39site-packagestensorflowpythonkerasenginecompile_utils.py:276 _get_loss_object
        loss = losses_mod.get(loss)
    C:UsersanishAppDataRoamingPythonPython39site-packagestensorflowpythonkeraslosses.py:2078 get
        return deserialize(identifier)
    C:UsersanishAppDataRoamingPythonPython39site-packagestensorflowpythonkeraslosses.py:2033 deserialize
        return deserialize_keras_object(
    C:UsersanishAppDataRoamingPythonPython39site-packagestensorflowpythonkerasutilsgeneric_utils.py:698 deserialize_keras_object
        raise ValueError(

    ValueError: Unknown loss function: categorical crossentropy. Please ensure this object is passed to the `custom_objects` argument. See https://www.tensorflow.org/guide/keras/save_and_serialize#registering_the_custom_object for details.
 

Помощь была бы очень признательна..

Похоже, у вас опечатка. Попробуйте использовать этот код (сосредоточьтесь на нижней полосе):

 model.compile(loss='categorical_crossentropy', optimizer=sgd, metrics=['accuracy'])