I'm pretty new to tensorflow and trying to do some experiments with the Iris dataset. I created following model function (MWE):
def model_fn(features, labels, mode):
net = tf.feature_column.input_layer(features, [tf.feature_column.numeric_column(key=key) for key in FEATURE_NAMES])
logits = tf.layers.dense(inputs=net, units=3)
loss = tf.nn.softmax_cross_entropy_with_logits(labels=labels, logits=logits)
optimizer = tf.train.GradientDescentOptimizer(learning_rate=0.001)
train_op = optimizer.minimize(
loss=loss,
global_step=tf.train.get_global_step())
return tf.estimator.EstimatorSpec(mode=mode, loss=loss, train_op=train_op)
Unfortunately I get the following error:
InvalidArgumentError: Input to reshape is a tensor with 256 values, but the requested shape has 1
[[Node: Reshape = Reshape[T=DT_FLOAT, Tshape=DT_INT32, _device="/job:localhost/replica:0/task:0/device:CPU:0"](softmax_cross_entropy_with_logits_sg, Reshape/shape)]]
Seems to be some problem with the shapes of the tensors. However both logits and labels have an equal shape of (256, 3) - as it is required by the documentation . Also both tensors have type float32.
Just for the sake of completeness, here is the input function for the estimator:
import pandas as pd
import tensorflow as tf
import numpy as np
IRIS_DATA = "data/iris.csv"
FEATURE_NAMES = ["sepal_length", "sepal_width", "petal_length", "petal_width"]
CLASS_NAME = ["class"]
COLUMNS = FEATURE_NAMES + CLASS_NAME
# read dataset
iris = pd.read_csv(IRIS_DATA, header=None, names=COLUMNS)
# encode classes
iris["class"] = iris["class"].astype('category').cat.codes
# train test split
np.random.seed(1)
msk = np.random.rand(len(iris)) < 0.8
train = iris[msk]
test = iris[~msk]
def iris_input_fn(batch_size=256, mode="TRAIN"):
def prepare_input(data=None):
#do mean normaization across all samples
mu = np.mean(data)
sigma = np.std(data)
data = data - mu
data = data / sigma
is_nan = np.isnan(data)
is_inf = np.isinf(data)
if np.any(is_nan) or np.any(is_inf):
print('data is not well-formed : is_nan {n}, is_inf: {i}'.format(n= np.any(is_nan), i=np.any(is_inf)))
data = transform_data(data)
return data
def transform_data(data):
data = data.astype(np.float32)
return data
def load_data():
global train
trn_all_data=train.iloc[:,:-1]
trn_all_labels=train.iloc[:,-1]
return (trn_all_data.astype(np.float32),
trn_all_labels.astype(np.int32))
data, labels = load_data()
data = prepare_input(data)
labels = tf.one_hot(labels, depth=3)
labels = tf.cast(labels, tf.float32)
dataset = tf.data.Dataset.from_tensor_slices((data.to_dict(orient="list"), labels))
dataset = dataset.shuffle(1000).repeat().batch(batch_size)
return dataset.make_one_shot_iterator().get_next()
Dataset from UCI repo
Solved the problem by replacing the loss function from nn module:
loss = tf.nn.softmax_cross_entropy_with_logits(labels=labels, logits=logits)
by the loss function of losses module
loss = tf.losses.softmax_cross_entropy(onehot_labels=labels, logits=logits)
or by
loss = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits(labels=labels, logits=logits))
loss which is fed to the minimize method of GradientDescentOptimizer needed to be a scalar. A single value for the whole batch.
Problem was, I computed the softmax cross entropy for each element in the batch, which resulted in a tensor containing 256 (batch size) cross entropy values, and tried to feed this in the minimize method. Therefore the error message
Input to reshape is a tensor with 256 values, but the requested shape has 1
The technical post webpages of this site follow the CC BY-SA 4.0 protocol. If you need to reprint, please indicate the site URL or the original address.Any question please contact:yoyou2525@163.com.