{ "cells": [ { "cell_type": "code", "execution_count": null, "metadata": { "_cell_guid": "a42d8335-7241-0a78-ff14-7a761c9beecf" }, "outputs": [], "source": [ "%matplotlib inline\n", "import mxnet as mx\n", "import numpy as np\n", "import matplotlib.pyplot as plt\n", "import logging\n", "\n", "logger = logging.getLogger()\n", "logger.setLevel(logging.DEBUG)" ] }, { "cell_type": "code", "execution_count": null, "metadata": { "_cell_guid": "b3a3cce9-8501-a8a4-952a-623279a96bdb" }, "outputs": [], "source": [ "# Variables are place holders for input arrays. We give each variable a unique name.\n", "data = mx.symbol.Variable('data')\n", "\n", "# The input is fed to a fully connected layer that computes Y=WX+b.\n", "# This is the main computation module in the network.\n", "# Each layer also needs an unique name. We'll talk more about naming in the next section.\n", "fc1 = mx.symbol.FullyConnected(data = data, name='fc1', num_hidden=128)\n", "# Activation layers apply a non-linear function on the previous layer's output.\n", "# Here we use Rectified Linear Unit (ReLU) that computes Y = max(X, 0).\n", "act1 = mx.symbol.Activation(data = fc1, name='relu1', act_type=\"relu\")\n", "\n", "fc2 = mx.symbol.FullyConnected(data = act1, name = 'fc2', num_hidden = 64)\n", "act2 = mx.symbol.Activation(data = fc2, name='relu2', act_type=\"relu\")\n", "\n", "fc3 = mx.symbol.FullyConnected(data = act2, name='fc3', num_hidden=10)\n", "# Finally we have a loss layer that compares the network's output with label and generates gradient signals.\n", "mlp = mx.symbol.SoftmaxOutput(data = fc3, name = 'softmax')\n", "mx.viz.plot_network(mlp)" ] }, { "cell_type": "code", "execution_count": null, "metadata": { "_cell_guid": "230ac3e2-d0bc-bf56-2f0b-3d2ae957833a" }, "outputs": [], "source": [ "import numpy as np\n", "import pandas as pd\n", "# load data to numpy\n", "\n", "train_file ='../input/train.csv'\n", "test_file = \"../input/test.csv\"\n", "result_file = '../input/submission.csv'\n", "\n", "df_train_data = pd.read_csv(train_file)\n", "df_test_data = pd.read_csv(test_file)\n", "\n", "label = np.array(df_train_data.pop('label'), dtype=int)\n", "train_data = np.array(df_train_data.values, dtype=float)\n", "test_data = np.array(df_test_data.values, dtype=float)" ] }, { "cell_type": "code", "execution_count": null, "metadata": { "_cell_guid": "5241ccc3-5c5f-dc08-6ef1-532a144cbd40" }, "outputs": [], "source": [ "# plot data as grey image\n", "for i in range(10):\n", " plt.subplot(1, 10, i + 1)\n", " plt.imshow(train_data[i].reshape(28, 28) * 255, cmap='Greys_r')\n", " plt.axis('off')\n", "plt.show()" ] }, { "cell_type": "code", "execution_count": null, "metadata": { "_cell_guid": "737836e7-7258-83de-dfe7-301e13bf490c" }, "outputs": [], "source": [ "# sub mean value\n", "mean_data = np.mean(train_data, axis=0)\n", "X_train = (train_data - mean_data)/128\n", "Y_train = label\n", "X_test = (test_data - mean_data)/128\n", "\n", "print(X_train.shape, X_test.shape)" ] }, { "cell_type": "code", "execution_count": null, "metadata": { "_cell_guid": "759304e0-702c-ae11-f9cd-49823e6720ff" }, "outputs": [], "source": [ "batch_size = 128\n", "train_iter = mx.io.NDArrayIter(X_train, Y_train, batch_size=batch_size)\n", "test_iter = None" ] }, { "cell_type": "code", "execution_count": null, "metadata": { "_cell_guid": "ba372870-df04-8165-e230-fa9bc582ff45" }, "outputs": [], "source": [ "data = data.astype(np.float32) / 255\n", "data_test = data_test.astype(np.float32) / 255" ] }, { "cell_type": "code", "execution_count": null, "metadata": { "_cell_guid": "53898b7c-f5d0-e687-f69b-81ca7f13e8d7" }, "outputs": [], "source": [ "model = mx.model.FeedForward(\n", " ctx = mx.cpu(0), # Run on GPU 0\n", " symbol = mlp, # Use the network we just defined\n", " num_epoch = 15, # Train for 10 epochs\n", " learning_rate = 0.1, # Learning rate\n", " momentum = 0.9, # Momentum for SGD with momentum\n", " wd = 0.00001)\n", "model.fit(\n", " X=train_iter, # Training data set\n", " eval_data=test_iter, # Testing data set. MXNet computes scores on test set every epoch\n", " batch_end_callback = mx.callback.Speedometer(batch_size, 100)) # Logging module to print out progress" ] }, { "cell_type": "code", "execution_count": null, "metadata": { "_cell_guid": "3b95861d-697d-3199-5250-4df1b18320e4", "collapsed": true }, "outputs": [], "source": "" }, { "cell_type": "code", "execution_count": null, "metadata": { "_cell_guid": "7aadbf65-a0f7-0075-0b2b-91d43889ab0c" }, "outputs": [], "source": [ "# Predict the test data\n", "result = []\n", "for i in range(X_test.shape[0]):\n", " label = model.predict(X_test[i:i+1])[0].argmax()\n", " result.append(label)" ] }, { "cell_type": "code", "execution_count": null, "metadata": { "_cell_guid": "bd776e3a-2256-00cf-9f37-ce68b4a09a26" }, "outputs": [], "source": [ "submission = pd.DataFrame(data={'ImageId':(np.arange(len(result)) + 1), 'Label':np.array(result)})\n", "submission.to_csv('./submission.csv', index=False)\n", "submission.tail()" ] } ], "metadata": { "_change_revision": 0, "_is_fork": false, "kernelspec": { "display_name": "Python 3", "language": "python", "name": "python3" }, "language_info": { "codemirror_mode": { "name": "ipython", "version": 3 }, "file_extension": ".py", "mimetype": "text/x-python", "name": "python", "nbconvert_exporter": "python", "pygments_lexer": "ipython3", "version": "3.6.0" } }, "nbformat": 4, "nbformat_minor": 0 }