σ UΎχXc@`sŒdZddlmZddlmZddlmZddlZddlZdZdZ e e Z d„Z d „Z d „Z d „ZdS( sΛBuilds the MNIST network. Implements the inference/loss/training pattern for model building. 1. inference() - Builds the model as far as is required for running the network forward to make predictions. 2. loss() - Adds to the inference model the layers required to generate loss. 3. training() - Adds to the loss model the Ops required to generate and apply gradients. This file is used by the various "fully_connected_*.py" files and not meant to be run. i(tabsolute_import(tdivision(tprint_functionNi icC`sΊtjdƒ…tjtjt|gddtjttƒƒƒddƒ}tjtj|gƒddƒ}tj j tj ||ƒ|ƒ}WdQXtjdƒ…tjtj||gddtjt|ƒƒƒddƒ}tjtj|gƒddƒ}tj j tj ||ƒ|ƒ}WdQXtjd ƒytjtj|t gddtjt|ƒƒƒddƒ}tjtjt gƒddƒ}tj ||ƒ|}WdQX|S( s)Build the MNIST model up to where it may be used for inference. Args: images: Images placeholder, from inputs(). hidden1_units: Size of the first hidden layer. hidden2_units: Size of the second hidden layer. Returns: softmax_linear: Output tensor with the computed logits. thidden1tstddevgπ?tnametweightstbiasesNthidden2tsoftmax_linear( ttft name_scopetVariablettruncated_normalt IMAGE_PIXELStmathtsqrttfloattzerostnntrelutmatmult NUM_CLASSES(timagest hidden1_unitst hidden2_unitsRRRRtlogits((sk/tmp/pip-build-h1VYrz/tensorflow/tensorflow-1.0.1.data/purelib/tensorflow/examples/tutorials/mnist/mnist.pyt inference-s2   (  (  cC`sCtj|ƒ}tjjd|d|ddƒ}tj|ddƒS(sίCalculates the loss from the logits and the labels. Args: logits: Logits tensor, float - [batch_size, NUM_CLASSES]. labels: Labels tensor, int32 - [batch_size]. Returns: loss: Loss tensor of type float. tlabelsRRtxentropyt xentropy_mean(R tto_int64Rt(sparse_softmax_cross_entropy_with_logitst reduce_mean(RRt cross_entropy((sk/tmp/pip-build-h1VYrz/tensorflow/tensorflow-1.0.1.data/purelib/tensorflow/examples/tutorials/mnist/mnist.pytlossVs  cC`sYtjjd|ƒtjj|ƒ}tjddddtƒ}|j|d|ƒ}|S(sΏSets up the training Ops. Creates a summarizer to track the loss over time in TensorBoard. Creates an optimizer and applies the gradients to all trainable variables. The Op returned by this function is what must be passed to the `sess.run()` call to cause the model to train. Args: loss: Loss tensor, from loss(). learning_rate: The learning rate to use for gradient descent. Returns: train_op: The Op for training. R#iRt global_stept trainable(R tsummarytscalarttraintGradientDescentOptimizerR tFalsetminimize(R#t learning_ratet optimizerR$ttrain_op((sk/tmp/pip-build-h1VYrz/tensorflow/tensorflow-1.0.1.data/purelib/tensorflow/examples/tutorials/mnist/mnist.pyttrainingfs cC`s4tjj||dƒ}tjtj|tjƒƒS(s`Evaluate the quality of the logits at predicting the label. Args: logits: Logits tensor, float - [batch_size, NUM_CLASSES]. labels: Labels tensor, int32 - [batch_size], with values in the range [0, NUM_CLASSES). Returns: A scalar int32 tensor with the number of examples (out of batch_size) that were predicted correctly. i(R Rtin_top_kt reduce_sumtcasttint32(RRtcorrect((sk/tmp/pip-build-h1VYrz/tensorflow/tensorflow-1.0.1.data/purelib/tensorflow/examples/tutorials/mnist/mnist.pyt evaluationƒs(t__doc__t __future__RRRRt tensorflowR Rt IMAGE_SIZERRR#R/R5(((sk/tmp/pip-build-h1VYrz/tensorflow/tensorflow-1.0.1.data/purelib/tensorflow/examples/tutorials/mnist/mnist.pyts    )