ValueError：沒有為任何變量提供梯度（Tensorflow）

Question

我是機器學習和 tensorflow 的新手，所以我現在正在做一個個人項目來嘗試學習一點。 我現在遇到了這個錯誤，我所有的在線研究並沒有幫助我准確地縮小問題范圍。 我最好的猜測是，引擎蓋下發生了一些我無法識別的事情，這使我的損失 function 不可微分，我知道這對 RNN 來說是個問題。 我很感激任何幫助！

$ python3 Stocker.py APIKEY MSFT

ValueError: No gradients provided for any variable: ['lstm/lstm_cell/kernel:0', 'lstm/lstm_cell/recurrent_kernel:0', 'lstm/lstm_cell/bias:0', 'dense/kernel:0', 'dense/bias:0']

代碼：

import pandas as pd
import numpy as np
import argparse
import tensorflow as tf
from matplotlib import pyplot

import data_helpers as dh

class Stocker:
    def __init__(self, training, test, loss='mse', optimizer='adam'):
        """ Creating Stocker instance immediately creates model 

            Model (WIP) is a two-layer LSTM. Defaults to Mean Squared Error
            loss function and ADAM optimizer function.
        """
        self.training_data = training
        self.test_data = test

        self.model = tf.keras.Sequential()
        self.model.add(tf.keras.layers.LSTM(100, activation='tanh', recurrent_activation='sigmoid', \
                                            input_shape=(training.shape[1], training.shape[2])))
        self.model.add(tf.keras.layers.Dense(5))
        self.model.compile(loss=loss, optimizer=optimizer)
        print(self.model.summary())

    def train(self):
        self.fit = self.model.fit(self.training_data, epochs=50, \
                            batch_size=100, \
                            validation_data=self.test_data, verbose=2, shuffle=False)

        pyplot.plot(self.fit['loss'], label='train')
        pyplot.plot(self.fit['val_loss'], label='test')
        pyplot.legend()
        pyplot.show()



if __name__ == '__main__':

    """ Test/Demo of Stocker module """

    parser = argparse.ArgumentParser(description="Model Training Script")
    parser.add_argument('key', help='User API Key')
    parser.add_argument('-outdir', metavar='out', default='/models/', help="Directory for stored model(s) (one for each symbol).")
    parser.add_argument('symbols', nargs=argparse.REMAINDER, help="List of symbols to train (Place all at end of command)")
    parse = parser.parse_args()

    data = {}

    for symbol in parse.symbols:

        # read historical daily data from alpha_vantage
        # store in python dict
        hist = dh.daily(symbol, parse.key, compact=False)
        data[symbol] = hist
        print(hist)
        #print()

        """ Data Preprocessing """ 

        # turn dataframe to numpy array
        tmp = hist.to_numpy()

        # split into training and testing sets 90-10
        split = round(tmp.shape[0]*1/10)
        test, training = tmp[:split], tmp[split:]

        test = dh.array_to_supervised(test, 3)
        test = test.reshape((test.shape[0], 1, test.shape[1]))

        training = dh.array_to_supervised(training, 3)
        training = training.reshape((training.shape[0], 1, training.shape[1]))

        # convert numpy arrays to tensors and reshape for LSTM
        training_tensor = tf.convert_to_tensor(training, np.float32)
        test_tensor = tf.convert_to_tensor(test, np.float32)

        """ -------------------------------- """
        #print(training_tensor)
        #print(test_tensor)

        model = Stocker(training_tensor, test_tensor)
        model.train()

Answer 1

當您僅傳遞訓練數據並錯過傳遞model.fit()中的標簽時，您會收到此錯誤。 我能夠使用以下代碼重新創建您的錯誤。 您可以從這里下載我在程序中使用的數據集。 我正在使用Tensorflow version 2.2.0 。

重新創建問題的代碼 -

%tensorflow_version 2.x
# MLP for Pima Indians Dataset saved to single file
import numpy as np
from numpy import loadtxt
import tensorflow as tf
print(tf.__version__)
from tensorflow.keras.models import Sequential
from tensorflow.keras.layers import Dense

# load pima indians dataset
dataset = np.loadtxt("/content/pima-indians-diabetes.csv", delimiter=",")

# split into input (X) and output (Y) variables
X = dataset[:,0:8]
Y = dataset[:,8]

# define model
model = Sequential()
model.add(Dense(12, input_dim=8, activation='relu'))
model.add(Dense(8, activation='relu'))
model.add(Dense(1, activation='sigmoid'))

# compile model
model.compile(loss='binary_crossentropy', optimizer='adam', metrics=['accuracy'])

# Model Summary
#model.summary()

# Fit the model
model.fit(X, epochs=150, batch_size=10, verbose=0)

Output -

2.2.0
---------------------------------------------------------------------------
ValueError                                Traceback (most recent call last)
<ipython-input-4-7ddca8f2992e> in <module>()
     28 
     29 # Fit the model
---> 30 model.fit(X, epochs=150, batch_size=10, verbose=0)

10 frames
/usr/local/lib/python3.6/dist-packages/tensorflow/python/framework/func_graph.py in wrapper(*args, **kwargs)
    966           except Exception as e:  # pylint:disable=broad-except
    967             if hasattr(e, "ag_error_metadata"):
--> 968               raise e.ag_error_metadata.to_exception(e)
    969             else:
    970               raise

ValueError: in user code:

    /usr/local/lib/python3.6/dist-packages/tensorflow/python/keras/engine/training.py:571 train_function  *
        outputs = self.distribute_strategy.run(
    /usr/local/lib/python3.6/dist-packages/tensorflow/python/distribute/distribute_lib.py:951 run  **
        return self._extended.call_for_each_replica(fn, args=args, kwargs=kwargs)
    /usr/local/lib/python3.6/dist-packages/tensorflow/python/distribute/distribute_lib.py:2290 call_for_each_replica
        return self._call_for_each_replica(fn, args, kwargs)
    /usr/local/lib/python3.6/dist-packages/tensorflow/python/distribute/distribute_lib.py:2649 _call_for_each_replica
        return fn(*args, **kwargs)
    /usr/local/lib/python3.6/dist-packages/tensorflow/python/keras/engine/training.py:541 train_step  **
        self.trainable_variables)
    /usr/local/lib/python3.6/dist-packages/tensorflow/python/keras/engine/training.py:1804 _minimize
        trainable_variables))
    /usr/local/lib/python3.6/dist-packages/tensorflow/python/keras/optimizer_v2/optimizer_v2.py:521 _aggregate_gradients
        filtered_grads_and_vars = _filter_grads(grads_and_vars)
    /usr/local/lib/python3.6/dist-packages/tensorflow/python/keras/optimizer_v2/optimizer_v2.py:1219 _filter_grads
        ([v.name for _, v in grads_and_vars],))

    ValueError: No gradients provided for any variable: ['dense_5/kernel:0', 'dense_5/bias:0', 'dense_6/kernel:0', 'dense_6/bias:0', 'dense_7/kernel:0', 'dense_7/bias:0'].

解決方案 -通過model.fit()中的訓練標簽，您的錯誤將得到修復。

修改的，

model.fit(X , epochs=150, batch_size=10, verbose=0)

至

model.fit(X , Y, epochs=150, batch_size=10, verbose=0)

代碼 -

%tensorflow_version 2.x
# MLP for Pima Indians Dataset saved to single file
import numpy as np
from numpy import loadtxt
import tensorflow as tf
print(tf.__version__)
from tensorflow.keras.models import Sequential
from tensorflow.keras.layers import Dense

# load pima indians dataset
dataset = np.loadtxt("/content/pima-indians-diabetes.csv", delimiter=",")

# split into input (X) and output (Y) variables
X = dataset[:,0:8]
Y = dataset[:,8]

# define model
model = Sequential()
model.add(Dense(12, input_dim=8, activation='relu'))
model.add(Dense(8, activation='relu'))
model.add(Dense(1, activation='sigmoid'))

# compile model
model.compile(loss='binary_crossentropy', optimizer='adam', metrics=['accuracy'])

# Model Summary
#model.summary()

# Fit the model
model.fit(X , Y, epochs=150, batch_size=10, verbose=0)

Output -

2.2.0
<tensorflow.python.keras.callbacks.History at 0x7f9208433eb8>

希望這能回答你的問題。 快樂學習。