From 333dc32ff79af21484695157f3d141dc776f7c02 Mon Sep 17 00:00:00 2001 From: Martin Wicke Date: Wed, 4 Jan 2017 21:25:34 -0800 Subject: Change arg order for {softmax,sparse_softmax,sigmoid}_cross_entropy_with_logits to be (labels, predictions), and force use of named args to avoid accidents. Change: 143629623 --- tensorflow/examples/image_retraining/retrain.py | 2 +- tensorflow/examples/tutorials/mnist/mnist.py | 5 ++--- tensorflow/examples/tutorials/mnist/mnist_softmax.py | 3 ++- tensorflow/examples/tutorials/mnist/mnist_with_summaries.py | 2 +- tensorflow/examples/udacity/2_fullyconnected.ipynb | 4 ++-- tensorflow/examples/udacity/4_convolutions.ipynb | 2 +- tensorflow/examples/udacity/6_lstm.ipynb | 2 +- 7 files changed, 10 insertions(+), 10 deletions(-) (limited to 'tensorflow/examples') diff --git a/tensorflow/examples/image_retraining/retrain.py b/tensorflow/examples/image_retraining/retrain.py index 0d5ba84c2d..c5518e2603 100644 --- a/tensorflow/examples/image_retraining/retrain.py +++ b/tensorflow/examples/image_retraining/retrain.py @@ -723,7 +723,7 @@ def add_final_training_ops(class_count, final_tensor_name, bottleneck_tensor): with tf.name_scope('cross_entropy'): cross_entropy = tf.nn.softmax_cross_entropy_with_logits( - logits, ground_truth_input) + labels=ground_truth_input, logits=logits) with tf.name_scope('total'): cross_entropy_mean = tf.reduce_mean(cross_entropy) tf.summary.scalar('cross_entropy', cross_entropy_mean) diff --git a/tensorflow/examples/tutorials/mnist/mnist.py b/tensorflow/examples/tutorials/mnist/mnist.py index e97a6c48ef..d533697976 100644 --- a/tensorflow/examples/tutorials/mnist/mnist.py +++ b/tensorflow/examples/tutorials/mnist/mnist.py @@ -95,9 +95,8 @@ def loss(logits, labels): """ labels = tf.to_int64(labels) cross_entropy = tf.nn.sparse_softmax_cross_entropy_with_logits( - logits, labels, name='xentropy') - loss = tf.reduce_mean(cross_entropy, name='xentropy_mean') - return loss + labels=labels, logits=logits, name='xentropy') + return tf.reduce_mean(cross_entropy, name='xentropy_mean') def training(loss, learning_rate): diff --git a/tensorflow/examples/tutorials/mnist/mnist_softmax.py b/tensorflow/examples/tutorials/mnist/mnist_softmax.py index 42a406d386..4fa89ff246 100644 --- a/tensorflow/examples/tutorials/mnist/mnist_softmax.py +++ b/tensorflow/examples/tutorials/mnist/mnist_softmax.py @@ -54,7 +54,8 @@ def main(_): # # So here we use tf.nn.softmax_cross_entropy_with_logits on the raw # outputs of 'y', and then average across the batch. - cross_entropy = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits(y, y_)) + cross_entropy = tf.reduce_mean( + tf.nn.softmax_cross_entropy_with_logits(labels=y_, logits=y)) train_step = tf.train.GradientDescentOptimizer(0.5).minimize(cross_entropy) sess = tf.InteractiveSession() diff --git a/tensorflow/examples/tutorials/mnist/mnist_with_summaries.py b/tensorflow/examples/tutorials/mnist/mnist_with_summaries.py index 83879d0807..ff78f151c3 100644 --- a/tensorflow/examples/tutorials/mnist/mnist_with_summaries.py +++ b/tensorflow/examples/tutorials/mnist/mnist_with_summaries.py @@ -119,7 +119,7 @@ def train(): # So here we use tf.nn.softmax_cross_entropy_with_logits on the # raw outputs of the nn_layer above, and then average across # the batch. - diff = tf.nn.softmax_cross_entropy_with_logits(y, y_) + diff = tf.nn.softmax_cross_entropy_with_logits(labels=y_, logits=y) with tf.name_scope('total'): cross_entropy = tf.reduce_mean(diff) tf.summary.scalar('cross_entropy', cross_entropy) diff --git a/tensorflow/examples/udacity/2_fullyconnected.ipynb b/tensorflow/examples/udacity/2_fullyconnected.ipynb index 8a845171a4..a6a206307a 100644 --- a/tensorflow/examples/udacity/2_fullyconnected.ipynb +++ b/tensorflow/examples/udacity/2_fullyconnected.ipynb @@ -271,7 +271,7 @@ " # cross-entropy across all training examples: that's our loss.\n", " logits = tf.matmul(tf_train_dataset, weights) + biases\n", " loss = tf.reduce_mean(\n", - " tf.nn.softmax_cross_entropy_with_logits(logits, tf_train_labels))\n", + " tf.nn.softmax_cross_entropy_with_logits(labels=tf_train_labels, logits=logits))\n", " \n", " # Optimizer.\n", " # We are going to find the minimum of this loss using gradient descent.\n", @@ -448,7 +448,7 @@ " # Training computation.\n", " logits = tf.matmul(tf_train_dataset, weights) + biases\n", " loss = tf.reduce_mean(\n", - " tf.nn.softmax_cross_entropy_with_logits(logits, tf_train_labels))\n", + " tf.nn.softmax_cross_entropy_with_logits(labels=tf_train_labels, logits=logits))\n", " \n", " # Optimizer.\n", " optimizer = tf.train.GradientDescentOptimizer(0.5).minimize(loss)\n", diff --git a/tensorflow/examples/udacity/4_convolutions.ipynb b/tensorflow/examples/udacity/4_convolutions.ipynb index 464d2c836e..d607dddbb2 100644 --- a/tensorflow/examples/udacity/4_convolutions.ipynb +++ b/tensorflow/examples/udacity/4_convolutions.ipynb @@ -286,7 +286,7 @@ " # Training computation.\n", " logits = model(tf_train_dataset)\n", " loss = tf.reduce_mean(\n", - " tf.nn.softmax_cross_entropy_with_logits(logits, tf_train_labels))\n", + " tf.nn.softmax_cross_entropy_with_logits(labels=tf_train_labels, logits=logits))\n", " \n", " # Optimizer.\n", " optimizer = tf.train.GradientDescentOptimizer(0.05).minimize(loss)\n", diff --git a/tensorflow/examples/udacity/6_lstm.ipynb b/tensorflow/examples/udacity/6_lstm.ipynb index 64e913acf8..7e78c5328f 100644 --- a/tensorflow/examples/udacity/6_lstm.ipynb +++ b/tensorflow/examples/udacity/6_lstm.ipynb @@ -576,7 +576,7 @@ " logits = tf.nn.xw_plus_b(tf.concat_v2(outputs, 0), w, b)\n", " loss = tf.reduce_mean(\n", " tf.nn.softmax_cross_entropy_with_logits(\n", - " logits, tf.concat_v2(train_labels, 0)))\n", + " labels=tf.concat_v2(train_labels, 0), logits=logits))\n", "\n", " # Optimizer.\n", " global_step = tf.Variable(0)\n", -- cgit v1.2.3