Add files via upload

20191020-AM-Keras-MNIST-手寫辨識-Starter-複習.ipynb

@@ -0,0 +1,233 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# 如何知道有多少數據\n",
+    "from keras import datasets\n",
+    "from keras.utils import to_categorical\n",
+    "from keras.datasets import mnist\n",
+    "import numpy as np\n",
+    "import matplotlib.pyplot as plt\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# tuple (a, b)\n",
+    "# list  [a, b]\n",
+    "# dict  {'a':b}"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# mnist.load_data()[1][1].shape"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# 數據是28 * 28 = 784\n",
+    "(X_train, y_train), (X_test, y_test) = mnist.load_data()\n",
+    "X_train.shape, y_train.shape, X_test.shape, y_test.shape"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# 圖片\n",
+    "X_train[0].shape"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# 畫一張\n",
+    "%matplotlib inline\n",
+    "plt.figure(figsize=(3/4, 3/4))\n",
+    "plt.imshow(X_train[0], cmap='gray_r')\n",
+    "plt.axis('off')\n",
+    "plt.show()\n",
+    "\n",
+    "# '''\n",
+    "# alueError: Colormap xxx is not recognized. Possible values are: \n",
+    "# Accent, Accent_r, Blues, Blues_r, BrBG, BrBG_r, BuGn, BuGn_r, BuPu, BuPu_r, CMRmap, CMRmap_r, Dark2, Dark2_r, GnBu, GnBu_r, Greens, Greens_r, Greys, Greys_r, OrRd, OrRd_r, Oranges, Oranges_r, PRGn, PRGn_r, Paired, Paired_r, Pastel1, Pastel1_r, Pastel2, Pastel2_r, PiYG, PiYG_r, PuBu, PuBuGn, PuBuGn_r, PuBu_r, PuOr, PuOr_r, PuRd, PuRd_r, Purples, Purples_r, RdBu, RdBu_r, RdGy, RdGy_r, RdPu, RdPu_r, RdYlBu, RdYlBu_r, RdYlGn, RdYlGn_r, Reds, Reds_r, Set1, Set1_r, Set2, Set2_r, Set3, Set3_r, Spectral, Spectral_r, Wistia, Wistia_r, YlGn, YlGnBu, YlGnBu_r, YlGn_r, YlOrBr, YlOrBr_r, YlOrRd, YlOrRd_r, afmhot, afmhot_r, autumn, autumn_r, binary, binary_r, bone, bone_r, brg, brg_r, bwr, bwr_r, cividis, cividis_r, cool, cool_r, coolwarm, coolwarm_r, copper, copper_r, cubehelix, cubehelix_r, flag, flag_r, gist_earth, gist_earth_r, gist_gray, gist_gray_r, gist_heat, gist_heat_r, gist_ncar, gist_ncar_r, gist_rainbow, gist_rainbow_r, gist_stern, gist_stern_r, gist_yarg, gist_yarg_r, gnuplot, gnuplot2, gnuplot2_r, gnuplot_r, gray, gray_r, hot, hot_r, hsv, hsv_r, inferno, inferno_r, jet, jet_r, magma, magma_r, nipy_spectral, nipy_spectral_r, ocean, ocean_r, pink, pink_r, plasma, plasma_r, prism, prism_r, rainbow, rainbow_r, seismic, seismic_r, spring, spring_r, summer, summer_r, tab10, tab10_r, tab20, tab20_r, tab20b, tab20b_r, tab20c, tab20c_r, terrain, terrain_r, twilight, twilight_r, twilight_shifted, twilight_shifted_r, viridis, viridis_r, winter, winter_r'''"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "X_test.shape"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# data pre-processing\n",
+    "X_train, X_test = X_train.astype(np.float32).reshape(60000, 784), X_test.astype(np.float32).reshape(10000, 784)\n",
+    "# one_hot encoding\n",
+    "y_train_oh, y_test_oh = to_categorical(y_train), to_categorical(y_test) "
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "y_train[0] , y_train_oh[0]"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# build model Sequential = 底座 , Dense : 神經層 , optimizers 找出所有參數的最小誤差(loss) adam sgd \n",
+    "# activation feedward 計算過程 判斷神經是否可以從上一層 到 下一層  relu sigmoid softmax\n",
+    "# 60000 : 筆數 , (28, 28) :每一張相片(row,col), 784 : flatten of (28, 28)\n",
+    "# 60000 : 攸關到 batch_size 產生要訓練幾次\n",
+    "# 784   : input layer features(dim)\n",
+    "# 1000  : 1st hidden layer units \n",
+    "# 500   : 2nd hidden layer units\n",
+    "# 10    : output layer units\n",
+    "# epochs: 針對那全部的六萬(60000)每一次批次，要循環幾次，訓練上述的參數 1,290,510\n",
+    "from keras.models import Sequential\n",
+    "from keras.layers import Dense\n",
+    "from keras import optimizers\n",
+    "model = Sequential()\n",
+    "model.add( Dense(units=1000, activation='relu', input_shape=(784,) ) )\n",
+    "model.add( Dense(units=500, activation='relu') )\n",
+    "model.add( Dense(units=10, activation='softmax') )\n",
+    "model.summary()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# train model \n",
+    "# ValueError: Error when checking target: expected dense_3 to have 2 dimensions\n",
+    "# but got array with shape (60000, 10, 2, 2)\n",
+    "# ValueError: Error when checking target: expected dense_6 to have shape (10,) but got array with shape (1,)\n",
+    "\n",
+    "model.compile(optimizer=optimizers.Adam(lr=0.01), loss='categorical_crossentropy', metrics=['accuracy'] )\n",
+    "history = model.fit(X_train, y_train_oh, validation_split=0.1, epochs=10, verbose=1, batch_size= 1000)\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Plot\n",
+    "plt.title('Accuracy of Keras')\n",
+    "plt.plot(history.history['acc'], color='red')\n",
+    "plt.plot(history.history['val_acc'], color='blue')\n",
+    "plt.grid()\n",
+    "plt.show()\n",
+    "\n",
+    "\n",
+    "plt.title('Loss of Keras')\n",
+    "plt.plot(history.history['loss'], color='red')\n",
+    "plt.plot(history.history['val_loss'], color='blue')\n",
+    "plt.grid()\n",
+    "plt.show()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# evaluate model \n",
+    "print(model.evaluate(X_train, y_train_oh), model.evaluate(X_test, y_test_oh) )\n",
+    "# predict model \n",
+    "y_pred = model.predict(X_test)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# top 10 \n",
+    "# 請你找一下那些數字是錯誤 slicing \n",
+    "index_error = np.argmax(y_pred, axis=1) != np.argmax(y_test_oh, axis=1)\n",
+    "\n",
+    "X_error      =  X_test[ index_error ]\n",
+    "y_error      =  y_test_oh[ index_error ]\n",
+    "y_error_pred =  y_pred[ index_error ]\n",
+    "\n",
+    "print('Total error amount is {}'.format(X_error.shape[0]))\n",
+    "\n",
+    "# Plot for top 10 [:10]\n",
+    "for i in range(10):\n",
+    "    plt.figure(figsize=(1,1))\n",
+    "    plt.title('GT:{} --> Pred:{}'.format(np.argmax(y_error[i]), np.argmax(y_error_pred[i])) )\n",
+    "    plt.imshow(X_error[i].reshape(28,28), cmap='gray' )\n",
+    "    plt.axis('off')\n",
+    "    plt.show()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  }
+ ],
+ "metadata": {
+  "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": "3.6.8"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 2
+}