2

テキストデータセットで DNN-RNN を試しています。これは単純なダミー データであり、ほとんどのテキスト データでコードを使用できると思います。ただし、トレーニング済みのモデルを読み込んで再トレーニングしようとすると、エラーが発生します。私が間違っているかどうか教えてください。

def convert_docs(documents,no_class=2,MAX_DOCUMENT_LENGTH=200):
    '''Takes list of docs and associated clas list as input.
    Prepares it for the tflearn library. documents should be a list of strings and 
    clas should be a numbered list of classes encoded into 0,1,2 etc.
    no_classes is the number of classes that are going to be used in the model
    this is defaulted to 2'''

    if MAX_DOCUMENT_LENGTH is None:
        list_docs = []
        for x in documents:
            list_docs.append(x.split())

        MAX_DOCUMENT_LENGTH = max(len(l) for l in list_docs) 
        print(MAX_DOCUMENT_LENGTH)
    else:
        MAX_DOCUMENT_LENGTH=MAX_DOCUMENT_LENGTH

    vocab_processor = VocabularyProcessor(MAX_DOCUMENT_LENGTH,min_frequency=5,vocabulary=None)
    data = np.array(list(vocab_processor.fit_transform(documents)))
    n_words = len(vocab_processor.vocabulary_)

戻りデータ、vocab_processor、n_words、MAX_DOCUMENT_LENGTH

これは、テキスト ドキュメントのリストを必要な形式に変換するためのものです。

 def model_RNN(MAX_DOCUMENT_LENGTH,n_words):
        net = input_data(shape=[None, MAX_DOCUMENT_LENGTH])
        net = embedding(net, input_dim=n_words, output_dim=128)
        net = bidirectional_rnn(net, BasicLSTMCell(128), BasicLSTMCell(128))
        net = dropout(net, 0.5)
        net = fully_connected(net, 2, activation='softmax')
        net = regression(net, optimizer='adam', loss='categorical_crossentropy')
        model = tflearn.DNN(net, clip_gradients=0., tensorboard_verbose=2)
        return model

ここで RNN モデルを初期化します

def classify_DNN(data,clas,model):
    from sklearn.cross_validation import StratifiedKFold
    folds = 10 #number of folds for the cv 
    skf = StratifiedKFold(n_folds=folds,y=clas)
    fold = 1
    cms = np.array([[0,0],[0,0]])
    accs = []
    aucs=[]
    for train_index, test_index in skf:
        X_train, X_test = data[train_index], data[test_index]
        y_train, y_test = clas[train_index], clas[test_index]
        trainy= to_categorical(y_train, nb_classes=2)
        model.fit(X_train, trainy, n_epoch = 10, shuffle=True)
        prediction = model.predict(X_test)
        pred=np.argmax(prediction,axis=1)
        acc = accuracy_score(pred, y_test)
        cm = confusion_matrix(y_test,pred)
        fpr, tpr, thresholds = metrics.roc_curve(y_test, pred)
        print('Test Accuracy for fold {} : {}'.format(fold,round((acc*100),2)))
        au = metrics.auc(fpr, tpr)
        #au=roc_auc_score(testY, pred)
        print('AUC for fold {} : {}'.format(fold,round((au*100),2)))
        fold +=1
        cms += cm
        accs.append(acc)
        aucs.append(au)
    #print('CV test accuracy: {}\n{}'.format(round((np.mean(accs)*100),2),cms))
    #print('\nCV AUC: {}'.format(round(np.mean(aucs)*100),2))
    print('\nCV accuracy: %.3f +/- %.3f' % (round((np.mean(accs)*100),2),round((np.std(accs)*100),2)))
    print('\nCV ROC AUC: %.3f +/- %.3f' % (round((np.mean(aucs)*100),2),round((np.std(aucs)*100),2)))
    return model, round(np.mean(accs)*100,2), round(np.mean(aucs)*100,2)

これはモデルをトレーニングするためのものです..これが最善の方法ではないことはわかっていますが、実験でした..

def pred_user_dnn(user_transformed, clf, y=None):
    '''
    Used for predicting the class of the user string given the transformed user input and the pretrained classifier
    Arguments:
        user_transformed= the transformed doc using the one used on the training data.. Must have same dimension as the training data
        clf= classifier pre trained on the training data of the one returned from cros_val()
        y= the training labels
    returns:
        string- Yes if the predicted label is 0
        No is the predicted label is 1
    '''
    usr_p = clf.predict(user_transformed)
    usr_p= np.argmax(usr_p,1)
    print('\nUser class'+str(usr_p))
    for x in usr_p:
        if x==0:
            print("Case recovery eligibility is: Yes")
            return 'Yes'
        elif x==1:
            print("Case recovery eligibility is: No")
            return 'No'

この関数は新しい文字列を予測します

tf.reset_default_graph()    
data,vocab_processor, n_words, MAX_DOCUMENT_LENGTH = convert_docs(documents,no_class=2,MAX_DOCUMENT_LENGTH=200)
model = model_RNN(MAX_DOCUMENT_LENGTH,n_words)
clf, acc, roc_auc =classify_DNN(data,clas,model)
final_name = 'LSTM'.lower()+'_'+now+'.clf'
clf.save(os.path.join(trained,final_name))

これは、トレーニング済みのモデルを保存するためのものです

tf.reset_default_graph()
model_name=model_name.lower()
data,vocab_processor, n_words, MAX_DOCUMENT_LENGTH = convert_docs(documents,no_class=2,MAX_DOCUMENT_LENGTH=200)
model = model_RNN(MAX_DOCUMENT_LENGTH,n_words)
path_clf= #path where the model is saved
model.load(os.path.join(trained,path_clf))
user_transformed = np.array(list(vocab_processor.transform(clean_user_list)))
#using it for prediction
user_transformed =pad_sequences(sequences=user_transformed,maxlen=MAX_DOCUMENT_LENGTH, value=0.)
result = pred_user_dnn(user_transformed, model)

ここで、保存されたモデルを読み込んでいますが、このエラーが発生しています。

model.load(os.path.join(trained,path_clf))
Traceback (most recent call last):

  File "<ipython-input-28-d4cf3784bb15>", line 1, in <module>
    model.load(os.path.join(trained,path_clf))

  File "C:\Users\kkothari\AppData\Local\Continuum\Anaconda3\lib\site-packages\tflearn\models\dnn.py", line 260, in load
    self.trainer.restore(model_file, weights_only, **optargs)

  File "C:\Users\kkothari\AppData\Local\Continuum\Anaconda3\lib\site-packages\tflearn\helpers\trainer.py", line 449, in restore
    self.restorer.restore(self.session, model_file)

  File "C:\Users\kkothari\AppData\Local\Continuum\Anaconda3\lib\site-packages\tensorflow\python\training\saver.py", line 1388, in restore
    {self.saver_def.filename_tensor_name: save_path})

  File "C:\Users\kkothari\AppData\Local\Continuum\Anaconda3\lib\site-packages\tensorflow\python\client\session.py", line 766, in run
    run_metadata_ptr)

  File "C:\Users\kkothari\AppData\Local\Continuum\Anaconda3\lib\site-packages\tensorflow\python\client\session.py", line 964, in _run
    feed_dict_string, options, run_metadata)

  File "C:\Users\kkothari\AppData\Local\Continuum\Anaconda3\lib\site-packages\tensorflow\python\client\session.py", line 1014, in _do_run
    target_list, options, run_metadata)

  File "C:\Users\kkothari\AppData\Local\Continuum\Anaconda3\lib\site-packages\tensorflow\python\client\session.py", line 1034, in _do_call
    raise type(e)(node_def, op, message)

NotFoundError: Key val_loss_2 not found in checkpoint
     [[Node: save_5/RestoreV2_122 = RestoreV2[dtypes=[DT_FLOAT], _device="/job:localhost/replica:0/task:0/cpu:0"](_recv_save_5/Const_0, save_5/RestoreV2_122/tensor_names, save_5/RestoreV2_122/shape_and_slices)]]

Caused by op 'save_5/RestoreV2_122', defined at:
  File "C:\Users\kkothari\AppData\Local\Continuum\Anaconda3\lib\site-packages\spyder\utils\ipython\start_kernel.py", line 223, in <module>
    main()
  File "C:\Users\kkothari\AppData\Local\Continuum\Anaconda3\lib\site-packages\spyder\utils\ipython\start_kernel.py", line 219, in main
    kernel.start()
  File "C:\Users\kkothari\AppData\Local\Continuum\Anaconda3\lib\site-packages\ipykernel\kernelapp.py", line 474, in start
    ioloop.IOLoop.instance().start()
  File "C:\Users\kkothari\AppData\Local\Continuum\Anaconda3\lib\site-packages\zmq\eventloop\ioloop.py", line 162, in start
    super(ZMQIOLoop, self).start()
  File "C:\Users\kkothari\AppData\Local\Continuum\Anaconda3\lib\site-packages\tornado\ioloop.py", line 887, in start
    handler_func(fd_obj, events)
  File "C:\Users\kkothari\AppData\Local\Continuum\Anaconda3\lib\site-packages\tornado\stack_context.py", line 275, in null_wrapper
    return fn(*args, **kwargs)
  File "C:\Users\kkothari\AppData\Local\Continuum\Anaconda3\lib\site-packages\zmq\eventloop\zmqstream.py", line 440, in _handle_events
    self._handle_recv()
  File "C:\Users\kkothari\AppData\Local\Continuum\Anaconda3\lib\site-packages\zmq\eventloop\zmqstream.py", line 472, in _handle_recv
    self._run_callback(callback, msg)
  File "C:\Users\kkothari\AppData\Local\Continuum\Anaconda3\lib\site-packages\zmq\eventloop\zmqstream.py", line 414, in _run_callback
    callback(*args, **kwargs)
  File "C:\Users\kkothari\AppData\Local\Continuum\Anaconda3\lib\site-packages\tornado\stack_context.py", line 275, in null_wrapper
    return fn(*args, **kwargs)
  File "C:\Users\kkothari\AppData\Local\Continuum\Anaconda3\lib\site-packages\ipykernel\kernelbase.py", line 276, in dispatcher
    return self.dispatch_shell(stream, msg)
  File "C:\Users\kkothari\AppData\Local\Continuum\Anaconda3\lib\site-packages\ipykernel\kernelbase.py", line 228, in dispatch_shell
    handler(stream, idents, msg)
  File "C:\Users\kkothari\AppData\Local\Continuum\Anaconda3\lib\site-packages\ipykernel\kernelbase.py", line 390, in execute_request
    user_expressions, allow_stdin)
  File "C:\Users\kkothari\AppData\Local\Continuum\Anaconda3\lib\site-packages\ipykernel\ipkernel.py", line 196, in do_execute
    res = shell.run_cell(code, store_history=store_history, silent=silent)
  File "C:\Users\kkothari\AppData\Local\Continuum\Anaconda3\lib\site-packages\ipykernel\zmqshell.py", line 501, in run_cell
    return super(ZMQInteractiveShell, self).run_cell(*args, **kwargs)
  File "C:\Users\kkothari\AppData\Local\Continuum\Anaconda3\lib\site-packages\IPython\core\interactiveshell.py", line 2717, in run_cell
    interactivity=interactivity, compiler=compiler, result=result)
  File "C:\Users\kkothari\AppData\Local\Continuum\Anaconda3\lib\site-packages\IPython\core\interactiveshell.py", line 2821, in run_ast_nodes
    if self.run_code(code, result):
  File "C:\Users\kkothari\AppData\Local\Continuum\Anaconda3\lib\site-packages\IPython\core\interactiveshell.py", line 2881, in run_code
    exec(code_obj, self.user_global_ns, self.user_ns)
  File "<ipython-input-18-395d2873044e>", line 2, in <module>
    model = model_bi_LSTM(MAX_DOCUMENT_LENGTH,n_words)
  File "C:\Users\kkothari\Desktop\text_mining\deep_learning.py", line 112, in model_bi_LSTM
    model = tflearn.DNN(net, clip_gradients=0., tensorboard_verbose=2)
  File "C:\Users\kkothari\AppData\Local\Continuum\Anaconda3\lib\site-packages\tflearn\models\dnn.py", line 63, in __init__
    best_val_accuracy=best_val_accuracy)
  File "C:\Users\kkothari\AppData\Local\Continuum\Anaconda3\lib\site-packages\tflearn\helpers\trainer.py", line 145, in __init__
    keep_checkpoint_every_n_hours=keep_checkpoint_every_n_hours)
  File "C:\Users\kkothari\AppData\Local\Continuum\Anaconda3\lib\site-packages\tensorflow\python\training\saver.py", line 1000, in __init__
    self.build()
  File "C:\Users\kkothari\AppData\Local\Continuum\Anaconda3\lib\site-packages\tensorflow\python\training\saver.py", line 1030, in build
    restore_sequentially=self._restore_sequentially)
  File "C:\Users\kkothari\AppData\Local\Continuum\Anaconda3\lib\site-packages\tensorflow\python\training\saver.py", line 624, in build
    restore_sequentially, reshape)
  File "C:\Users\kkothari\AppData\Local\Continuum\Anaconda3\lib\site-packages\tensorflow\python\training\saver.py", line 361, in _AddRestoreOps
    tensors = self.restore_op(filename_tensor, saveable, preferred_shard)
  File "C:\Users\kkothari\AppData\Local\Continuum\Anaconda3\lib\site-packages\tensorflow\python\training\saver.py", line 200, in restore_op
    [spec.tensor.dtype])[0])
  File "C:\Users\kkothari\AppData\Local\Continuum\Anaconda3\lib\site-packages\tensorflow\python\ops\gen_io_ops.py", line 441, in restore_v2
    dtypes=dtypes, name=name)
  File "C:\Users\kkothari\AppData\Local\Continuum\Anaconda3\lib\site-packages\tensorflow\python\framework\op_def_library.py", line 759, in apply_op
    op_def=op_def)
  File "C:\Users\kkothari\AppData\Local\Continuum\Anaconda3\lib\site-packages\tensorflow\python\framework\ops.py", line 2240, in create_op
    original_op=self._default_original_op, op_def=op_def)
  File "C:\Users\kkothari\AppData\Local\Continuum\Anaconda3\lib\site-packages\tensorflow\python\framework\ops.py", line 1128, in __init__
    self._traceback = _extract_stack()

NotFoundError (see above for traceback): Key val_loss_2 not found in checkpoint
     [[Node: save_5/RestoreV2_122 = RestoreV2[dtypes=[DT_FLOAT], _device="/job:localhost/replica:0/task:0/cpu:0"](_recv_save_5/Const_0, save_5/RestoreV2_122/tensor_names, save_5/RestoreV2_122/shape_and_slices)]]
4

1 に答える 1