ai basic1 snippets

3d_mesh.ipynb

activation.ipynb

axis.ipynb

broadcasting.ipynb

entropy.ipynb

mnist.ipynb

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {},
   "outputs": [],
   "source": [
    "import tensorflow as tf\n",
    "\n",
    "mnist = tf.keras.datasets.mnist\n",
    "(train_images, train_labels), (test_images, test_labels) = mnist.load_data()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [],
   "source": [
    "network = tf.keras.models.Sequential()\n",
    "network.add(tf.keras.layers.Dense(512, activation='relu', input_shape=(28 * 28,)))\n",
    "network.add(tf.keras.layers.Dense(10, activation='softmax'))\n",
    "network.compile(optimizer='Adam', loss='categorical_crossentropy', metrics=['accuracy'])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {},
   "outputs": [],
   "source": [
    "train_images = train_images.reshape((60000, 28 * 28))\n",
    "train_images = train_images.astype('float32') / 255\n",
    "\n",
    "test_images = test_images.reshape((10000, 28 * 28))\n",
    "test_images = test_images / 255.0\n",
    "\n",
    "train_labels = tf.keras.utils.to_categorical(train_labels)\n",
    "test_labels = tf.keras.utils.to_categorical(test_labels)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Train on 60000 samples\n",
      "Epoch 1/5\n",
      "60000/60000 [==============================] - 4s 72us/sample - loss: 0.2628 - accuracy: 0.9259\n",
      "Epoch 2/5\n",
      "60000/60000 [==============================] - 4s 63us/sample - loss: 0.1062 - accuracy: 0.9689\n",
      "Epoch 3/5\n",
      "60000/60000 [==============================] - 4s 63us/sample - loss: 0.0696 - accuracy: 0.9796\n",
      "Epoch 4/5\n",
      "60000/60000 [==============================] - 4s 73us/sample - loss: 0.0498 - accuracy: 0.9854\n",
      "Epoch 5/5\n",
      "60000/60000 [==============================] - 4s 68us/sample - loss: 0.0373 - accuracy: 0.9888\n"
     ]
    },
    {
     "data": {
      "text/plain": [
       "<tensorflow.python.keras.callbacks.History at 0x10e066d10>"
      ]
     },
     "execution_count": 4,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "network.fit(train_images, train_labels, epochs=5, batch_size=128)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "10000/10000 [==============================] - 1s 146us/sample - loss: 0.0634 - accuracy: 0.9799\n"
     ]
    }
   ],
   "source": [
    "test_loss, test_acc = network.evaluate(test_images, test_labels)"
   ]
  },
  {
   "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": "3.7.6"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 4
}

numpy_speed.ipynb

torch_speed.ipynb