I have this error:
ValueError: Tensor conversion requested dtype float64 for Tensor with dtype float32: 'Tensor("pearson_r/covariance/Cast:0", shape=(), dtype=float32)'
我的代码如下：
def correlation_coefficient(y_true, y_pred):
return tf.contrib.metrics.streaming_pearson_correlation(y_pred, y_true)[1]
def construct_embedding():
# load the whole embedding into memory
embeddings_index = dict()
f = open('../input/embedding/word_embedding50d.txt')
for line in f:
values = line.split()
word = values[0]
coefs = asarray(values[1:], dtype='float32')
embeddings_index[word] = coefs
f.close()
print('Loaded %s word vectors.' % len(embeddings_index))
return embeddings_index
# define the model
def define_model(length, vocab_size, embedding_matrix):
# channel 1
inputs1 = Input(shape=(length,))
embedding1 = Embedding(vocab_size, 50, weights=[embedding_matrix],trainable=False)(inputs1)
conv1 = Conv1D(filters=350, kernel_size=3, activation='relu')(embedding1)
drop1 = Dropout(0.2)(conv1)
nor11=keras.layers.BatchNormalization()(drop1)
pool1 = MaxPooling1D(pool_size=5)(nor11)
pdrop1 = Dropout(0.2)(pool1)
nor12=keras.layers.BatchNormalization()(pdrop1)
ls1=LSTM(200)(nor12)
ldrop1 = Dropout(0.2)(ls1)
lnor1=keras.layers.BatchNormalization()(ldrop1)
# channel 2
inputs2 = Input(shape=(length,))
embedding2 = Embedding(vocab_size, 50, weights=[embedding_matrix],trainable=False)(inputs2)
conv2 = Conv1D(filters=350, kernel_size=4, activation='relu')(embedding2)
drop2 = Dropout(0.2)(conv2)
nor21=keras.layers.BatchNormalization()(drop2)
pool2 = MaxPooling1D(pool_size=5)(nor21)
pdrop2 = Dropout(0.2)(pool2)
nor22=keras.layers.BatchNormalization()(pdrop2)
ls2=LSTM(200)(nor22)
ldrop2 = Dropout(0.2)(ls2)
lnor2=keras.layers.BatchNormalization()(ldrop2)
# channel 3
inputs3 = Input(shape=(length,))
embedding3 = Embedding(vocab_size, 50, weights=[embedding_matrix],trainable=False)(inputs3)
conv3 = Conv1D(filters=350, kernel_size=5, activation='relu')(embedding3)
drop3 = Dropout(0.2)(conv3)
nor31=keras.layers.BatchNormalization()(drop3)
pool3 = MaxPooling1D(pool_size=5)(nor31)
pdrop3 = Dropout(0.2)(pool3)
nor32=keras.layers.BatchNormalization()(pdrop3)
ls3=LSTM(250)(nor32)
ldrop3 = Dropout(0.2)(ls3)
lnor3=keras.layers.BatchNormalization()(ldrop3)
# merge
merged=concatenate([lnor1, lnor2, lnor3])
# interpretation
dense1 = Dense(100, activation='elu')(merged)
nor4=keras.layers.BatchNormalization()(dense1)
outputs = Dense(1, activation='elu')(nor4)
noroutputs=keras.layers.BatchNormalization()(outputs)
model = Model(inputs=[inputs1, inputs2, inputs3], outputs=noroutputs)
model.load_weights("../input/bestweight/bestweights.hdf5")
# compile
model.compile(loss='mse', optimizer=optimizers.Adam(lr=0.003), metrics=[correlation_coefficient, 'accuracy'])
K.get_session().run(tf.local_variables_initializer())
# summarize
print(model.summary())
plot_model(model, show_shapes=True, to_file='multichannel.png')
return model
# load a clean dataset
def load_dataset(filename):
return load(open(filename, 'rb'))
#preprocessing text
def preprocess(lines):
#print(lines)
ps = PorterStemmer()
for i in range(len(lines)):
tokens = lines[i].split()
# filter out stop words then stem the remaining words
stop_words = set(stopwords.words('english'))
tokens = [ps.stem(w) for w in tokens if not w in stop_words]
lines[i]=' '.join(tokens)
#print('lines: ')
#print(lines)
return lines
# encode a list of lines
def encode_text(tokenizer, lines, length):
# integer encode
encoded = tokenizer.texts_to_sequences(lines)
# pad encoded sequences
padded = pad_sequences(encoded, maxlen=length, padding='post')
return padded
# fit a tokenizer
def create_tokenizer(lines):
tokenizer = Tokenizer()
tokenizer.fit_on_texts(lines)
return tokenizer
# calculate the maximum document length
def max_length(lines):
return max([len(s.split()) for s in lines])
# encode a list of lines
def encode_text(tokenizer, lines, length):
# integer encode
encoded = tokenizer.texts_to_sequences(lines)
# pad encoded sequences
padded = pad_sequences(encoded, maxlen=length, padding='post')
return padded
def embed (vocab_size, embeddings_index, t):
embedding_matrix = zeros((vocab_size, 50))
for word, i in t.word_index.items():
embedding_vector = embeddings_index.get(word)
if embedding_vector is not None:
embedding_matrix[i] = embedding_vector
return embedding_matrix
# define training data
f = pd.read_csv('../input/satexasdataset/texasDatasetForHAN.csv', encoding='ISO-8859-1')
ftest = pd.read_csv('../input/satexasdataset/testtexasDatasetForHAN.csv', encoding='ISO-8859-1')
train=[]
test=[]
#print(f.read())
data_train = pd.DataFrame(data=f)
for i in range(data_train.shape[0]):
train.append(data_train.manswer[i]+ ' ' +data_train.sanswer[i])
trainLabels=data_train.score
Lines=pd.DataFrame(train, columns=['train'])
trainLines=Lines.train
trainLines=preprocess(trainLines)
data_test = pd.DataFrame(data=ftest)
for i in range(data_test .shape[0]):
test.append(data_test.manswer[i] + ' '+data_test.sanswer[i])
testLabels=data_test.score
tLines=pd.DataFrame(test, columns=['test'])
testLines=tLines.test
testLines=preprocess(testLines)
mergedLines = [trainLines , testLines]
allmerged = pd.concat(mergedLines)
# create tokenizer
tokenizer = create_tokenizer(allmerged.str.lower())
# calculate max document length
length = max_length(allmerged)
# calculate vocabulary size
vocab_size = len(tokenizer.word_index) + 1
print('Max answerlength: %d' % length)
print('Vocabulary size: %d' % vocab_size)
# encode data
alldataX = encode_text(tokenizer, allmerged, length)
s=(trainLines.size)
trainX=alldataX[0:s]
testX=alldataX[s:]
print(trainX.shape, testX.shape)
embeddings_index=construct_embedding()
embedding_matrix=embed (vocab_size, embeddings_index, tokenizer)
# define model
model = define_model(length, vocab_size, embedding_matrix)
ynew = model.predict([testX,testX,testX])
corr=correlation_coefficient(ynew, array(testLabels))
print('Test Correlation: %f' % (cor))
完整的错误消息如下：
---------------------------------------------------------------------------
ValueError Traceback (most recent call last)
<ipython-input-4-3ce58b1f4f26> in <module>
274 #testLabels = tf.convert_to_tensor(array(testLabels), dtype=tf.float64)
275
--> 276 corr=correlation_coefficient(ynew, array(testLabels))
277 print('Test Correlation: %f' % (cor*100))
278
<ipython-input-4-3ce58b1f4f26> in correlation_coefficient(y_true, y_pred)
45
46 def correlation_coefficient(y_true, y_pred):
---> 47 return tf.contrib.metrics.streaming_pearson_correlation(y_pred, y_true)[1]
48
49
/opt/conda/lib/python3.6/site-packages/tensorflow/contrib/metrics/python/ops/metric_ops.py in streaming_pearson_correlation(predictions, labels, weights, metrics_collections, updates_collections, name)
3334 weights = weights_broadcast_ops.broadcast_weights(weights, labels)
3335 cov, update_cov = streaming_covariance(
-> 3336 predictions, labels, weights=weights, name='covariance')
3337 var_predictions, update_var_predictions = streaming_covariance(
3338 predictions, predictions, weights=weights, name='variance_predictions')
/opt/conda/lib/python3.6/site-packages/tensorflow/contrib/metrics/python/ops/metric_ops.py in streaming_covariance(predictions, labels, weights, metrics_collections, updates_collections, name)
3218 # batch_mean_prediction is E[x_B] in the update equation
3219 batch_mean_prediction = math_ops.div_no_nan(
-> 3220 math_ops.reduce_sum(weighted_predictions), batch_count)
3221 delta_mean_prediction = math_ops.div_no_nan(
3222 (batch_mean_prediction - mean_prediction) * batch_count, update_count)
/opt/conda/lib/python3.6/site-packages/tensorflow/python/util/dispatch.py in wrapper(*args, **kwargs)
178 """Call target, and fall back on dispatchers if there is a TypeError."""
179 try:
--> 180 return target(*args, **kwargs)
181 except (TypeError, ValueError):
182 # Note: convert_to_eager_tensor currently raises a ValueError, not a
/opt/conda/lib/python3.6/site-packages/tensorflow/python/ops/math_ops.py in div_no_nan(x, y, name)
1095 with ops.name_scope(name, "div_no_nan", [x, y]) as name:
1096 x = ops.convert_to_tensor(x, name="x")
-> 1097 y = ops.convert_to_tensor(y, name="y", dtype=x.dtype.base_dtype)
1098 x_dtype = x.dtype.base_dtype
1099 y_dtype = y.dtype.base_dtype
/opt/conda/lib/python3.6/site-packages/tensorflow/python/framework/ops.py in convert_to_tensor(value, dtype, name, preferred_dtype, dtype_hint)
1085 preferred_dtype = deprecation.deprecated_argument_lookup(
1086 "dtype_hint", dtype_hint, "preferred_dtype", preferred_dtype)
-> 1087 return convert_to_tensor_v2(value, dtype, preferred_dtype, name)
1088
1089
/opt/conda/lib/python3.6/site-packages/tensorflow/python/framework/ops.py in convert_to_tensor_v2(value, dtype, dtype_hint, name)
1143 name=name,
1144 preferred_dtype=dtype_hint,
-> 1145 as_ref=False)
1146
1147
/opt/conda/lib/python3.6/site-packages/tensorflow/python/framework/ops.py in internal_convert_to_tensor(value, dtype, name, as_ref, preferred_dtype, ctx, accept_symbolic_tensors, accept_composite_tensors)
1222
1223 if ret is None:
-> 1224 ret = conversion_func(value, dtype=dtype, name=name, as_ref=as_ref)
1225
1226 if ret is NotImplemented:
/opt/conda/lib/python3.6/site-packages/tensorflow/python/framework/ops.py in _TensorTensorConversionFunction(t, dtype, name, as_ref)
1016 raise ValueError(
1017 "Tensor conversion requested dtype %s for Tensor with dtype %s: %r" %
-> 1018 (dtype.name, t.dtype.name, str(t)))
1019 return t
1020
ValueError: Tensor conversion requested dtype float64 for Tensor with dtype float32: 'Tensor("pearson_r/covariance/Cast:0", shape=(), dtype=float32)'
测试相关性： Tensor("pearson_r_1/update_op:0", shape=(), dtype=float32)。不幸的是，它没有返回相关值。 - zeinab ezzK.get_session().run(...)时一样。 - jdehesaynew = model.predict([testX,testX,testX]) K.get_session().run(tf.local_variables_initializer()) corr=correlation_coefficient(ynew, testLabels) K.get_session().run(tf.local_variables_initializer()) print('Test Correlation: ', corr)结果是：Test Correlation: Tensor("pearson_r_7/update_op:0", shape=(), dtype=float32)。不幸的是，相关性值没有被打印出来。你能告诉我如何打印出这个值吗？ - zeinab ezzprint('测试相关性: ', K.get_session().run(corr))。 - jdehesa