clean tensorflow udacity 2

Author: mGalarnyk

TensorFlow/Udacity/.ipynb_checkpoints/2_fullyconnected-checkpoint.ipynb

@@ -384,15 +384,13 @@
     "    # arrays.\n",
     "    _, l, predictions = session.run([optimizer, loss, train_prediction])\n",
     "    if (step % 100 == 0):\n",
-    "      print('Loss at step %d: %f' % (step, l))\n",
-    "      print('Training accuracy: %.1f%%' % accuracy(\n",
-    "        predictions, train_labels[:train_subset, :]))\n",
-    "      # Calling .eval() on valid_prediction is basically like calling run(), but\n",
-    "      # just to get that one numpy array. Note that it recomputes all its graph\n",
-    "      # dependencies.\n",
-    "      print('Validation accuracy: %.1f%%' % accuracy(\n",
-    "        valid_prediction.eval(), valid_labels))\n",
-    "  print('Test accuracy: %.1f%%' % accuracy(test_prediction.eval(), test_labels))"
+    "        print('Loss at step %d: %f' % (step, l))\n",
+    "        print('Training accuracy: %.1f%%' % accuracy(predictions, train_labels[:train_subset, :]))\n",
+    "        # Calling .eval() on valid_prediction is basically like calling run(), but\n",
+    "        # just to get that one numpy array. Note that it recomputes all its graph\n",
+    "        # dependencies.\n",
+    "        print('Validation accuracy: %.1f%%' % accuracy(valid_prediction.eval(), valid_labels))\n",
+    "        print('Test accuracy: %.1f%%' % accuracy(test_prediction.eval(), test_labels))"
    ]
   },
   {

TensorFlow/Udacity/.ipynb_checkpoints/2_ref_fullyconnected-checkpoint.ipynb

@@ -629,44 +629,7 @@
    },
    "outputs": [],
    "source": [
-    "batch_size = 128\n",
-    "num_hidden_nodes = 1024\n",
-    "\n",
-    "graph = tf.Graph()\n",
-    "with graph.as_default():\n",
-    "\n",
-    "  # Input data. For the training data, we use a placeholder that will be fed\n",
-    "  # at run time with a training minibatch.\n",
-    "  tf_train_dataset = tf.placeholder(tf.float32,\n",
-    "                                    shape=(batch_size, image_size * image_size))\n",
-    "  tf_train_labels = tf.placeholder(tf.float32, shape=(batch_size, num_labels))\n",
-    "  tf_valid_dataset = tf.constant(valid_dataset)\n",
-    "  tf_test_dataset = tf.constant(test_dataset)\n",
-    "  beta_regul = tf.placeholder(tf.float32)\n",
-    "  \n",
-    "  # Variables.\n",
-    "  weights1 = tf.Variable(\n",
-    "    tf.truncated_normal([image_size * image_size, num_hidden_nodes]))\n",
-    "  biases1 = tf.Variable(tf.zeros([num_hidden_nodes]))\n",
-    "  weights2 = tf.Variable(\n",
-    "    tf.truncated_normal([num_hidden_nodes, num_labels]))\n",
-    "  biases2 = tf.Variable(tf.zeros([num_labels]))\n",
-    "  \n",
-    "  # Training computation.\n",
-    "  lay1_train = tf.nn.relu(tf.matmul(tf_train_dataset, weights1) + biases1)\n",
-    "  logits = tf.matmul(lay1_train, weights2) + biases2\n",
-    "  loss = tf.reduce_mean(\n",
-    "    tf.nn.softmax_cross_entropy_with_logits(logits, tf_train_labels))\n",
-    "  \n",
-    "  # Optimizer.\n",
-    "  optimizer = tf.train.GradientDescentOptimizer(0.5).minimize(loss)\n",
-    "  \n",
-    "  # Predictions for the training, validation, and test data.\n",
-    "  train_prediction = tf.nn.softmax(logits)\n",
-    "  lay1_valid = tf.nn.relu(tf.matmul(tf_valid_dataset, weights1) + biases1)\n",
-    "  valid_prediction = tf.nn.softmax(tf.matmul(lay1_valid, weights2) + biases2)\n",
-    "  lay1_test = tf.nn.relu(tf.matmul(tf_test_dataset, weights1) + biases1)\n",
-    "  test_prediction = tf.nn.softmax(tf.matmul(lay1_test, weights2) + biases2)"
+    "-"
    ]
   },
   {