I keep getting a typeError when I try to use to_categorical from tflearn. The output error is:`
trainY = to_categorical(y = trainY, nb_classes=2)
File "C:\Users\saleh\Anaconda3\lib\site-packages\tflearn\data_utils.py", line 46, in to_categorical
return (y[:, None] == np.unique(y)).astype(np.float32)
TypeError: list indices must be integers or slices, not tuple
This is the reproducible code that I am trying to run:
import tflearn
from tflearn.data_utils import to_categorical
from tflearn.datasets import imdb
#IMDB dataset loading
train, test, _ = imdb.load_data(path = 'imdb.pkl', n_words = 10000, valid_portion = 0.1)
trainX, trainY = train
testX, testY = test
#converting labels to binary vectors
trainY = to_categorical(y = trainY, nb_classes=2) # **This is where I get the error**
testY = to_categorical(y = testY, nb_classes=2)
Cannot reproduce your error:
import tflearn
from tflearn.data_utils import to_categorical
from tflearn.datasets import imdb
train, test, _ = imdb.load_data(path = 'imdb.pkl', n_words = 10000, valid_portion = 0.1)
trainX, trainY = train
testX, testY = test
trainY[0:5]
# [0, 0, 0, 1, 0]
trainY = to_categorical(y = trainY, nb_classes=2)
trainY[0:5]
# array([[ 1., 0.],
# [ 1., 0.],
# [ 1., 0.],
# [ 0., 1.],
# [ 1., 0.]])
System configuration:
Python 2.7.12
Tensorflow 1.3.0
TFLearn 0.3.2
Ubuntu 16.04
UPDATE: It seems that some recent TFLearn commit has broken to_categorical - see here and here. I suggest to uninstall your current version and install the latest stable one with pip install tflearn (this is actually what I have done myself above).
Related
import pandas as pd
import numpy as np
df = pd.read_csv('shops.csv', sep='|')
df.columns = ['name', # 상호명
'cate_1', # 중분류명
'cate_2', # 소분류명
'cate_3', # 표준산업분류명
'dong', # 행정동명
'lon', # 위도
'lat' # 경도
]
df['cate_mix'] = df['cate_1'] + df['cate_2'] + df['cate_3']
df['cate_mix'] = df['cate_mix'].str.replace("/", " ")
from sklearn.feature_extraction.text import CountVectorizer # 피체 벡터화
from sklearn.metrics.pairwise import cosine_similarity # 코사인 유사도
count_vect_category = CountVectorizer(min_df=0, ngram_range=(1,2))
place_category = count_vect_category.fit_transform(df['cate_mix'])
place_simi_cate = cosine_similarity(place_category, place_category)
place_simi_cate_sorted_ind = place_simi_cate.argsort()[:, ::-1]
At this time, I want to calculate the cosine similarity as above,
via tensorflow
Is there any way to calculate it?
Example:
y_true = [[0., 1.], [1., 1.]]
y_pred = [[1., 0.], [1., 1.]]
cosine_loss = tf.keras.losses.CosineSimilarity(axis=1)
cosine_loss(y_true, y_pred).numpy()
Source: TensorFlow docs
I’m trying to re-define keras’s binary_crossentropy loss function so that I can customize it but it’s not giving me the same results as the existing one.
I'm using TF 1.13.1 with Keras 2.2.4.
I went through Keras’s github code. My understanding is that the loss in model.compile(optimizer='adam', loss='binary_crossentropy', metrics =['accuracy']), is defined in losses.py, using binary_crossentropy defined in tensorflow_backend.py.
I ran a dummy data and model to test it. Here are my findings:
The custom loss function outputs the same results as keras’s one
Using the custom loss in a keras model gives different accuracy results
from numpy.random import seed
seed(1)
from tensorflow import set_random_seed
set_random_seed(2)
import tensorflow as tf
from keras import losses
import keras.backend as K
import keras.backend.tensorflow_backend as tfb
from keras.layers import Dense
from keras import Sequential
#Dummy check of loss output
def binary_crossentropy_custom(y_true, y_pred):
return K.mean(binary_crossentropy_custom_tf(y_true, y_pred), axis=-1)
def binary_crossentropy_custom_tf(target, output, from_logits=False):
"""Binary crossentropy between an output tensor and a target tensor.
# Arguments
target: A tensor with the same shape as `output`.
output: A tensor.
from_logits: Whether `output` is expected to be a logits tensor.
By default, we consider that `output`
encodes a probability distribution.
# Returns
A tensor.
"""
# Note: tf.nn.sigmoid_cross_entropy_with_logits
# expects logits, Keras expects probabilities.
if not from_logits:
# transform back to logits
_epsilon = tfb._to_tensor(tfb.epsilon(), output.dtype.base_dtype)
output = tf.clip_by_value(output, _epsilon, 1 - _epsilon)
output = tf.log(output / (1 - output))
return tf.nn.sigmoid_cross_entropy_with_logits(labels=target,
logits=output)
logits = tf.constant([[-3., -2.11, -1.22],
[-0.33, 0.55, 1.44],
[2.33, 3.22, 4.11]])
labels = tf.constant([[1., 1., 1.],
[1., 1., 0.],
[0., 0., 0.]])
custom_sigmoid_cross_entropy_with_logits = binary_crossentropy_custom(labels, logits)
keras_binary_crossentropy = losses.binary_crossentropy(y_true=labels, y_pred=logits)
with tf.Session() as sess:
print('CUSTOM sigmoid_cross_entropy_with_logits: ', sess.run(custom_sigmoid_cross_entropy_with_logits), '\n')
print('KERAS keras_binary_crossentropy: ', sess.run(keras_binary_crossentropy), '\n')
#CUSTOM sigmoid_cross_entropy_with_logits: [16.118095 10.886106 15.942386]
#KERAS keras_binary_crossentropy: [16.118095 10.886106 15.942386]
#Dummy check of model accuracy
X_train = tf.random.uniform((3, 5), minval=0, maxval=1, dtype=tf.dtypes.float32)
labels = tf.constant([[1., 0., 0.],
[0., 0., 1.],
[1., 0., 0.]])
model = Sequential()
#First Hidden Layer
model.add(Dense(5, activation='relu', kernel_initializer='random_normal', input_dim=5))
#Output Layer
model.add(Dense(3, activation='sigmoid', kernel_initializer='random_normal'))
#I ran model.fit for each model.compile below 10 times using the same X_train and provide the range of accuracy measurement
# model.compile(optimizer='adam', loss='binary_crossentropy', metrics =['accuracy']) #0.748 < acc < 0.779
# model.compile(optimizer='adam', loss=losses.binary_crossentropy, metrics =['accuracy']) #0.761 < acc < 0.778
model.compile(optimizer='adam', loss=binary_crossentropy_custom, metrics =['accuracy']) #0.617 < acc < 0.663
history = model.fit(X_train, labels, steps_per_epoch=100, epochs=1)
I'd expect the custom loss function to give similar model accuracy output but it does not. Any idea? Thanks!
Keras automatically selects which accuracy implementation to use according to the loss, and this won't work if you use a custom loss. But in this case you can just explictly use the right accuracy, which is binary_accuracy:
model.compile(optimizer='adam', loss=binary_crossentropy_custom, metrics =['binary_accuracy'])
The variable saver program is as following:
import tensorflow as tf
sess = tf.InteractiveSession()
raw_data = [1., 2., 8., -1., 0., 5.5, 6., 13]
spikes = tf.Variable([False] * len(raw_data), name='spikes')
spikes.initializer.run()
tf.global_variables_initializer().run() #add by cs
saver = tf.train.Saver()
for i in range(1, len(raw_data)):
if raw_data[i] - raw_data[i-1] > 5:
spikes_val = spikes.eval()
spikes_val[i] = True
updater = tf.assign(spikes, spikes_val)
updater.eval()
save_path = saver.save(sess, "spikes.ckpt")
print("spikes data saved in file: %s" % save_path)
sess.close()
the restore program is as following:
import tensorflow as tf
sess = tf.InteractiveSession()
spikes = tf.Variable([False]*8, name='spikes')
saver = tf.train.Saver()
try:
saver.restore(sess, 'spikes.ckpt')
print(spikes.eval())
except:
print('file not found')
sess.close()
there is always an exception "file not found".
What's wrong?
I am following tensorflow's getting started. I downloaded and installed anaconda today. when run, the program below produces:
File "p3.py", line 35, in <module>
eval_loss = estimator.evaluate(input_fn=eval_input_fn)
NameError: name 'eval_input_fn' is not defined
import numpy as np
import tensorflow as tf
# Declare list of features, we only have one real-valued feature
def model(features, labels, mode):
# Build a linear model and predict values
W = tf.get_variable("W", [1], dtype=tf.float64)
b = tf.get_variable("b", [1], dtype=tf.float64)
y = W*features['x'] + b
# Loss sub-graph
loss = tf.reduce_sum(tf.square(y - labels))
# Training sub-graph
global_step = tf.train.get_global_step()
optimizer = tf.train.GradientDescentOptimizer(0.01)
train = tf.group(optimizer.minimize(loss),
tf.assign_add(global_step, 1))
# ModelFnOps connects subgraphs we built to the
# appropriate functionality.
return tf.contrib.learn.ModelFnOps(
mode=mode, predictions=y,
loss=loss,
train_op=train)
estimator = tf.contrib.learn.Estimator(model_fn=model)
# define our data sets
x_train = np.array([1., 2., 3., 4.])
y_train = np.array([0., -1., -2., -3.])
x_eval = np.array([2., 5., 8., 1.])
y_eval = np.array([-1.01, -4.1, -7, 0.])
input_fn = tf.contrib.learn.io.numpy_input_fn({"x": x_train}, y_train, 4, num_epochs=1000)
# train
estimator.fit(input_fn=input_fn, steps=1000)
# Here we evaluate how well our model did.
train_loss = estimator.evaluate(input_fn=input_fn)
eval_loss = estimator.evaluate(input_fn=eval_input_fn) #line 35
print("train loss: %r"% train_loss)
print("eval loss: %r"% eval_loss)
For some reason you haven't copy-pasted the definition of the evaluation input function.
You can find it directly in the tutorial you linked.
Here's the line
eval_input_fn = tf.contrib.learn.io.numpy_input_fn(
{"x":x_eval}, y_eval, batch_size=4, num_epochs=1000)
I am using Eclipse's PyDev for tensorflow version:0.12.1
I directly copy the sample code from tensorflow documentation,
but a attribute is not found and it returned
input_fn = tf.contrib.learn.io.numpy_input_fn({"x":x}, y, batch_size=4,
AttributeError: module 'tensorflow.contrib.learn.python.learn.learn_io' has no attribute 'numpy_input_fn'
Tried to re-download pydev and tensorflow but none of them work
The source code:
import tensorflow as tf
import numpy as np
features = [tf.contrib.layers.real_valued_column("x", dimension=1)]
estimator = tf.contrib.learn.LinearRegressor(feature_columns=features)
x = np.array([1., 2., 3., 4.])
y = np.array([0., -1., -2., -3.])
input_fn = tf.contrib.learn.io.numpy_input_fn({"x":x}, y, batch_size=4,num_epochs=1000)
estimator.fit(input_fn=input_fn, steps=1000)
estimator.evaluate(input_fn=input_fn)
I encountered the same problem and fixed it by upgrading:
pip install --upgrade tensorflow
upgrade tensorflowd to '1.1.0'