forked from PacktPublishing/Graph-Machine-Learning
-
Notifications
You must be signed in to change notification settings - Fork 1
Commit
This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
[MISC] Introduction on Neural Networks (#2)
- Loading branch information
Showing
10 changed files
with
4,928 additions
and
1 deletion.
There are no files selected for viewing
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Original file line number | Diff line number | Diff line change |
---|---|---|
@@ -0,0 +1,237 @@ | ||
{ | ||
"cells": [ | ||
{ | ||
"cell_type": "markdown", | ||
"id": "8c4e9e09-b0c6-4671-86a0-ca6bc73056b6", | ||
"metadata": {}, | ||
"source": [ | ||
"# Image Classification with TensorFlow" | ||
] | ||
}, | ||
{ | ||
"cell_type": "code", | ||
"execution_count": null, | ||
"id": "012237ce-0396-4c88-8b13-994c7a830421", | ||
"metadata": {}, | ||
"outputs": [], | ||
"source": [ | ||
"import tensorflow as tf\n", | ||
"from tensorflow.keras.datasets import fashion_mnist\n", | ||
"from matplotlib import pyplot as plt" | ||
] | ||
}, | ||
{ | ||
"cell_type": "markdown", | ||
"id": "6080305f-eaac-49d2-a4cb-658a907186ac", | ||
"metadata": {}, | ||
"source": [ | ||
"### Load and re-scale input data" | ||
] | ||
}, | ||
{ | ||
"cell_type": "code", | ||
"execution_count": null, | ||
"id": "1135c9e8-1765-48cc-beb8-25fd6ff363d4", | ||
"metadata": {}, | ||
"outputs": [], | ||
"source": [ | ||
"(x_train, y_train), (x_test, y_test) = fashion_mnist.load_data()" | ||
] | ||
}, | ||
{ | ||
"cell_type": "code", | ||
"execution_count": null, | ||
"id": "ee2989f4-9b32-48f6-b669-8255aa9e9c79", | ||
"metadata": {}, | ||
"outputs": [], | ||
"source": [ | ||
"x_train = x_train.astype('float32') / 255.\n", | ||
"x_test = x_test.astype('float32') / 255.\n", | ||
"\n", | ||
"print (x_train.shape)\n", | ||
"print (x_test.shape)" | ||
] | ||
}, | ||
{ | ||
"cell_type": "code", | ||
"execution_count": null, | ||
"id": "0525097f-4b57-4e9c-b850-966540589a30", | ||
"metadata": {}, | ||
"outputs": [], | ||
"source": [ | ||
"classes = {\n", | ||
" 0: \"T-shirt\",\n", | ||
" 1: \"Trouser\",\n", | ||
" 2: \"Pullover\",\n", | ||
" 3: \"Dress\",\n", | ||
" 4: \"Coat\",\n", | ||
" 5: \"Sandal\",\n", | ||
" 6: \"Shirt\",\n", | ||
" 7: \"Sneaker\",\n", | ||
" 8: \"Bag\",\n", | ||
" 9: \"Ankle boot\", \n", | ||
"}" | ||
] | ||
}, | ||
{ | ||
"cell_type": "code", | ||
"execution_count": null, | ||
"id": "a0e2bc95-ee33-4024-99d2-4ba7cb4fd0c6", | ||
"metadata": {}, | ||
"outputs": [], | ||
"source": [ | ||
"n = 6\n", | ||
"plt.figure(figsize=(20, 4))\n", | ||
"for i in range(n):\n", | ||
" # display original\n", | ||
" ax = plt.subplot(1, n, i + 1)\n", | ||
" plt.imshow(x_test[i])\n", | ||
" plt.title(classes[y_test[i]])\n", | ||
" plt.gray()\n", | ||
" ax.get_xaxis().set_visible(False)\n", | ||
" ax.get_yaxis().set_visible(False)\n", | ||
"\n", | ||
"plt.show()" | ||
] | ||
}, | ||
{ | ||
"cell_type": "markdown", | ||
"id": "c7ace701-0cd8-4173-982c-8682a860dd26", | ||
"metadata": {}, | ||
"source": [ | ||
"### Build model" | ||
] | ||
}, | ||
{ | ||
"cell_type": "code", | ||
"execution_count": null, | ||
"id": "a2d549c8-a410-4caa-95a4-b0bb20a05236", | ||
"metadata": {}, | ||
"outputs": [], | ||
"source": [ | ||
"model = tf.keras.models.Sequential([\n", | ||
" tf.keras.layers.Flatten(input_shape=(28, 28)),\n", | ||
" tf.keras.layers.Dense(128, activation='relu'),\n", | ||
" tf.keras.layers.Dropout(0.2),\n", | ||
" tf.keras.layers.Dense(10)\n", | ||
"])\n" | ||
] | ||
}, | ||
{ | ||
"cell_type": "code", | ||
"execution_count": null, | ||
"id": "f20ef704-3435-4f12-b41b-db42fcfb3b43", | ||
"metadata": {}, | ||
"outputs": [], | ||
"source": [ | ||
"model.summary()" | ||
] | ||
}, | ||
{ | ||
"cell_type": "markdown", | ||
"id": "9af979aa-9ccb-4b92-b0fd-ef39fcf6f317", | ||
"metadata": {}, | ||
"source": [ | ||
"### Train the network" | ||
] | ||
}, | ||
{ | ||
"cell_type": "code", | ||
"execution_count": null, | ||
"id": "53f02c48-3d8f-4e41-a9d4-703016a0dc19", | ||
"metadata": {}, | ||
"outputs": [], | ||
"source": [ | ||
"loss_fn = tf.keras.losses.SparseCategoricalCrossentropy(from_logits=True)\n", | ||
"optimizer = tf.keras.optimizers.Adam()" | ||
] | ||
}, | ||
{ | ||
"cell_type": "code", | ||
"execution_count": null, | ||
"id": "6427e500-41d2-43f1-b235-622d1d59572e", | ||
"metadata": {}, | ||
"outputs": [], | ||
"source": [ | ||
"model.compile(optimizer=optimizer,\n", | ||
" loss=loss_fn,\n", | ||
" metrics=['accuracy'])" | ||
] | ||
}, | ||
{ | ||
"cell_type": "code", | ||
"execution_count": null, | ||
"id": "ef1fea96-97cc-4c84-bb0c-78417a571575", | ||
"metadata": {}, | ||
"outputs": [], | ||
"source": [ | ||
"model.fit(\n", | ||
" x_train, \n", | ||
" y_train, \n", | ||
" validation_data=(x_test, y_test), \n", | ||
" epochs=20, \n", | ||
" batch_size=128,\n", | ||
" shuffle=True\n", | ||
")" | ||
] | ||
}, | ||
{ | ||
"cell_type": "markdown", | ||
"id": "a8c64c99-cbab-4503-8a1d-84f80c6f2af7", | ||
"metadata": {}, | ||
"source": [ | ||
"### More advanced model" | ||
] | ||
}, | ||
{ | ||
"cell_type": "markdown", | ||
"id": "c4649c36-1157-438b-bff0-01e980aa7da3", | ||
"metadata": {}, | ||
"source": [ | ||
"For a slightly more complex and deeper network, try to train the model below" | ||
] | ||
}, | ||
{ | ||
"cell_type": "raw", | ||
"id": "e9af3bfc-7b19-4441-9dc4-46df1b3739cc", | ||
"metadata": {}, | ||
"source": [ | ||
"input_img = tf.keras.layers.Input(shape=(28, 28, 1))\n", | ||
"\n", | ||
"x = tf.keras.layers.Conv2D(16, (3, 3), activation='relu', padding='same')(input_img)\n", | ||
"x = tf.keras.layers.MaxPooling2D((2, 2), padding='same')(x)\n", | ||
"x = tf.keras.layers.Conv2D(8, (3, 3), activation='relu', padding='same')(x)\n", | ||
"x = tf.keras.layers.MaxPooling2D((2, 2), padding='same')(x)\n", | ||
"x = tf.keras.layers.Conv2D(8, (3, 3), activation='relu', padding='same')(x)\n", | ||
"x = tf.keras.layers.MaxPooling2D((2, 2), padding='same')(x)\n", | ||
"x = tf.keras.layers.Flatten(input_shape=(26, 26))(x)\n", | ||
"x = tf.keras.layers.Dense(128, activation='relu')(x)\n", | ||
"x = tf.keras.layers.Dropout(0.2)(x)\n", | ||
"x = tf.keras.layers.Dense(10)(x)\n", | ||
"\n", | ||
"model = tf.keras.Model(input_img, x)" | ||
] | ||
} | ||
], | ||
"metadata": { | ||
"kernelspec": { | ||
"display_name": "chap-nn", | ||
"language": "python", | ||
"name": "chap-nn" | ||
}, | ||
"language_info": { | ||
"codemirror_mode": { | ||
"name": "ipython", | ||
"version": 3 | ||
}, | ||
"file_extension": ".py", | ||
"mimetype": "text/x-python", | ||
"name": "python", | ||
"nbconvert_exporter": "python", | ||
"pygments_lexer": "ipython3", | ||
"version": "3.8.18" | ||
} | ||
}, | ||
"nbformat": 4, | ||
"nbformat_minor": 5 | ||
} |
Oops, something went wrong.