squeeze file structure

mnist_number_recognition/mnist_optimization.py

@@ -165,7 +165,7 @@ def train(mnist):
 
 
 def main(argv=None):
-    mnist = input_data.read_data_sets("MNIST_data", one_hot=True)
+    mnist = input_data.read_data_sets("../MNIST_data", one_hot=True)
     print "basic information of mnist dataset"
     print "mnist training data size: ", mnist.train.num_examples
     print "mnist validating data size: ", mnist.validation.num_examples

mnist_restructured/mnist_train.py

@@ -12,13 +12,13 @@ BATCH_SIZE = 1000
 LEARNING_RATE_BASE = 0.8
 LEARNING_RATE_DECAY = 0.99
 REGULARIZATION_RATE = 0.0001
-TRAINING_STEPS = 50000
+TRAINING_STEPS = 30000
 MOVING_AVERAGE_DECAY = 0.99
 
 MODEL_SAVE_PATH = "model/"
 MODEL_NAME = "model.ckpt"
 
-
+# train a fully connected neural network
 def train(mnist):
     x = tf.placeholder(tf.float32, [None, mnist_inference.INPUT_NODE], name='x-input')
     y_ = tf.placeholder(tf.float32, [None, mnist_inference.OUTPUT_NODE], name='y-input')

mnist_restructured/model/checkpoint

@@ -1,6 +1,6 @@
-model_checkpoint_path: "model.ckpt-47501"
-all_model_checkpoint_paths: "model.ckpt-37501"
-all_model_checkpoint_paths: "model.ckpt-40001"
-all_model_checkpoint_paths: "model.ckpt-42501"
-all_model_checkpoint_paths: "model.ckpt-45001"
-all_model_checkpoint_paths: "model.ckpt-47501"
+model_checkpoint_path: "model.ckpt-27501"
+all_model_checkpoint_paths: "model.ckpt-17501"
+all_model_checkpoint_paths: "model.ckpt-20001"
+all_model_checkpoint_paths: "model.ckpt-22501"
+all_model_checkpoint_paths: "model.ckpt-25001"
+all_model_checkpoint_paths: "model.ckpt-27501"